Oil spills are considered one of the major threats to the marine and coastal environment. Synthetic aperture radar (SAR) sensors are frequently employed for this purpose due to their ability to operate effectively under various weather and illumination conditions. SAR can clearly capture oil spills with distinctive radar backscatter intensity, resulting in dark regions in the images. This characteristic enables the monitoring and automatic detection of oil spills in SAR imagery. U-Net stands as one of the commonly employed semantic segmentation models, known for its ability to achieve superior segmentation performance even with limited training data. In this study, a modified lightweight U-Net model was introduced to enhance the performance of maritime multi-class segmentation in SAR images. First, a lightweight MobileNetv3 model served as the backbone for the U-Net encoder to perform feature extraction. Secondly, the convolutional block attention module (CBAM) was employed to enhance the network's capability in extracting multiscale features and to expedite the module calculation speed. The experimental results showed that the detection accuracy of the proposed method can achieve 77.07% of the mean Intersection-Over-Union (mIOU). Compared with the original U-Net model, the proposed architecture can improve the mIOU about 4.88%.

The high-resolution synthetic aperture radar (SAR) images reveal more details about the complex-structured targets. In this study, we simulate the SAR echo and images taking the Great Belt Bridge over the sea surface as an example. By decomposing the bounces, we show that the scattering feature patterns come from the different reflections or scatterings. The target models include three types: two suspension cables of the same height and suspension cables with curvatures. A detailed deck model was also constructed to compare the environment of bridge construction with and without a roadway deck. The results demonstrate the line characteristics of different slant ranges in the simulated SAR images. We can appropriately interpret the scattering features from such complex targets by comparing the results with the actual SAR images.

Convolutional neural networks (CNNs) have shown great promise in human activity recognition, but long-term dependencies in time series data can be difficult to capture using standard CNNs. This study introduces a new CNN architecture that incorporates a multi-head attention mechanism (CNN-MHA) to address this challenge. This mechanism is composed of several attention heads, each independently calculating attention weights for distinct segments of the input. The attention head outputs are then concatenated and processed through a fully connected layer to produce the final attention representation. The multi-head attention mechanism allows the network to focus on relevant features and maintain long-term dependencies in the input data. The proposed model is evaluated on the physical activity monitoring for aging people dataset (PAMAP2) from the UCI machine learning repository, which is preprocessed by cleaning, normalization, segmentation, and reshaping before splitting into training, validation, and testing sets. The experimental results demonstrate that the CNN-MHA model outperforms existing models, achieving F1-score of 95.7%. Particularly, the multi-head attention mechanism significantly improves the model’s ability to recognize complex activity patterns. Furthermore, our model attained an average inference latency of 0.304 seconds, which can be crucial in real-time applications. The findings clearly demonstrate the substantial promise of the proposed CNN-MHA architecture for optimizing human activity recognition tasks, offering a powerful tool for advancing the state-of-the-art in this domain.

With the characteristics of high resolution, strong penetration ability, all-day observation and wide spatial coverage, Synthetic Aperture Radar (SAR) image has been widely used in shoreline detection. However, the shoreline detection will be affected by the shadows of geometric distortion caused by the side-looking of SAR especially in areas with large terrain fluctuations, such as the eastern coast of Taiwan. Therefore, this study proposed an efficient shoreline detection method using dual-polarization Sentinel-1 SAR and digital elevation model (DEM) data based on deep learning methods. In this research, two common self-built datasets were introduced, which covered all coastal areas of the study area in Taiwan island. The datasets included a total of 4,029 and 3,522 images, respectively. One contains VH polarization images and the other consists of a three-layer stack with VH, VV polarization images and DEM data. The training images of the dataset were labeled by manual inspection and morphological processing. In this study, the shoreline detection was based on the semantic segmentation U-Net model with batch normalization (BN) module. The segmentation results of the U-Net model were then processed by morphological postprocessing and edge detection for shoreline detection. Experimental results show that the combination of dual-polarization SAR and DEM data significantly improves shoreline detection results compared to those using Sentinel-1 VH imagery.

Natural disasters are causing unpredictable and devastating effects on people and their property worldwide as extreme weather events become more frequent and severe due to global climate change. Early assessment of disaster situations by relief teams can help to minimize the loss of life and property. Remote sensing satellite imagery has been used to estimate disaster losses and reduce the time and cost involved in damage assessments. However, the accuracy and performance of deep learning methods used to assess damage to buildings still leave room for improvement. In this research, we propose a novel deep learning model architecture, ASPP-Attention-ResNeSt-Unet (AARNS-Unet), to identify building areas and assess damage using remote sensing satellite images taken before and after a disaster. We evaluate the performance of our model using the public dataset provided by the X-View2 competition. Our proposed model combines ResNeSt, Atrous Spatial Pyramid Pooling (ASPP), and Convolutional Block Attention Module (CBAM) for better generalization. Our experiments show that the proposed model achieves a 1.3% accuracy improvement and a 7-time reduction in training time compared to other deep learning methods. Our proposed method can aid disaster relief teams in evaluating the damage to buildings and informing their response efforts. This research contributes to the development of more accurate and efficient methods for disaster assessment, which can help to reduce the negative impact of natural disasters on society.

In this project, an experimental study on disease detection and nutrient extraction of plantation such as oil palm will be carried out using a drone based hyperspectral imaging system developed by Centre for Remote Sensing and Surveillance Technologies (CRSST), Multimedia University (MMU), Malaysia. The major advantages of this system are light weight (approximately 250g for sensor) and larger number of band selection (from 500nm to 900nm) compared to a conventional multispectral camera. A customised multirotor drone has been designed and developed for longer endurance operation and to carry the non-standard payload i.e. hyperspectral camera. Preliminary testing has been performed in laboratory and oil palm plantation to verify the developed system. Initial results show that the hyperspectral data are suitable to be used for differentiation of the healthiness level of the oil palm plantation.

This study proposed a paddy rice mapping based on hand-crafted features combined with deep learning methods. In this research, the rice growth-related features were extracted from time-series SAR data provided by C-band Sentinel-1A images. Four rice features were first extracted from the rice growth curve, including Average Normalized Backscatter (ANB), Backscatter Variation Rate (BVR), Time Interval (TI) and Backscatter Difference (BD). Then, the deep learning U-Net model with four combined rice features was used to obtain the mapping distribution of paddy rice-fields. In the study, the experimental areas were composed of two important rice growth counties in central Taiwan, including Yunlin and Changhua counties. The experimental results showed that the detection accuracy of the proposed method for rice and non-rice can achieve 92.3% and 98.2%, respectively. These results demonstrate the great potential of SAR data in mapping paddy fields using the U-Net model with proposed feature inputs.

Taiwan's agriculture is an important national economic industry. Ensuring food security and stabilizing the food supply are the government's primary goals. The Agriculture and Food Agency (AFA) of the Executive Yuan's Council of Agriculture has conducted agricultural and food surveys to address those issues. Synthetic aperture radar (SAR) images will not be affected by climatic factors, which makes them more suitable for the forecast of rice production. This research uses the spatial-temporal neural network convolutional long short-term memory network (ConvLSTM) to identify rice fields from SAR images. The results show that ConvLSTM can greatly reduce the proportion of model false positives to 51.16%, produced higher average precision of 95.70%, and F1-score of 0.9648. The ConvLSTM neural network has produced good results for rice field identification compared with state-of-the-art neural networks.

In recent years, artificial intelligence (AI) technology has been used in computer vision to extract and analyze specific information from images. This research aims to apply AI in the field of agriculture. In this study, the you only look once version4 (YOLOv4) based on scaled-up feature fusion (YOLOv4-SUFF) has been implemented for rice fields detection from high-resolution images taken by an unmanned aerial vehicle (UAV). YOLOv4-SUFF consists of an extra layer which can extract special feature maps for the detector. This makes the proposed model YOLOv4-SUFF get more information during the stage of feature fusion. The experimental results show that the YOLOv4-SUFF has provided the best performance in terms of an average precision at 86.78% compared with other models.

Synthetic Aperture Radar (SAR) imagery has been widely used in many maritime applications due to its high resolution, wide coverage, and real-time monitoring characteristics. Nevertheless, the size of SAR images is significantly large for real-time application. In recent years, High-Performance Computing (HPC)-related methods have been used to improve the precision and detection rate of SAR imagery analysis. In this paper, motivated by the state-of-the-art real time object detection You Only Look Once version 3 (YOLOv3), an enhanced GPU-based deep learning method has been proposed, namely Accelereated-YOLOv3 (A-YOLOv3), to detect ships from the SAR images. A-YOLOv3 aims to reduce the computational time with relatively competitive detection accuracy by constructing a new architecture with less layers and channels. The proposed A-YOLOv3 architecture achieves Average Precision (AP) of 97.4% on the Expand Diversified SAR Ship Detection Dataset (EDSSDD).

Ship detection is one of the most important researches in the field of navigation safety and marine environment monitoring. Synthetic aperture radar (SAR) imagery has been used as a promising data source for monitoring maritime activities. However, the resolution of SAR images is limited, and it cannot effectively detect densely distributed and small ships, especially near harbors. In order to effectively manage ships during the day and night, this research uses visible and infrared images for ship detection. In this study, an improved architecture based on You only look once version 3 (Yolov3) is proposed for ship detection. Yolov3 provided multi-scale feature extraction to enhance the recognition of small targets. In addition, the study also considered the influence of Yolov3 parameters on ship detection, including the input image size, the number of filters in convolution layers and the detection scales. The experiment is based on a data set containing six types of ships, and a total of 5, 513 visible and infrared images from the harbors in northern Taiwan. The experimental results show that when the model parameters are selected as: 352x352 input size, the scale of large target deleted and the convolution filters reduced by 30%, Yolov3 has better ship detection performance and computational efficiency. Compared with the original Yolov3 with 87.9% mean average precision (mAP) and 87.0 billion floating point operations per second (BFLOPs), the proposed architecture can achieve 89.1 % mAP and 24.3 BFLOPs.

Rice is the most important food source for many countries, which especially for Asia, includes Taiwan. Monitoring rice field distribution can effectively manage food security. This study proposed a feature-based decision approach to detect the mapping of rice cultivation using the time-series Synthetic Aperture Radar (SAR) data provided by Sentinel-1A. Instead of using the maximum and minimum backscatter of SAR data, as most studies in the literature, this study established a rice growth model based on complete time series data in the rice growth period. From the developed model, a feature related to rice growth time, that is, the time interval (TI) between vegetative growth and maturity stages was introduced. The proposed feature was first compared with the feature of backscatter difference (BD) between the maximum and minimum value of SAR data. The experimental results show that the proposed feature can achieve better rice detection accuracy. Then, a decision method based on the combination of TI and BD features was proposed for rice planting mapping. In the study, Yunlin and Changhua counties in central Taiwan were used as experimental areas. The experimental results show that the proposed method can achieve more than 90% overall accuracy in rice detection for VH polarization. Furthermore, comparing with the traditional method that uses growth height feature, BD, the proposed method can improve the overall accuracy of rice detection about 5%.

The FMCW radar has lots of advantages such as compact, energy effective and low cost. It is suitable for mounting on the vehicle and also on small sized UAV. In this paper, the high squint angle effect is considered for both the FMCW synthetic aperture radar (SAR) and the inverse synthetic aperture radar (ISAR) in the case of the high resolution vehicle radar. The 2ndrange compression is performed for removing the range and the azimuth coupling effect under the high squint angle situation. The polar reformatting is performed for improving the radar resolution in the ISAR. By keeping practical situation in mind, the image qualities under the squint angle with random error is investigated. In addition, the simulation software for the SAR and the ISAR are developed.

Rice is one of the most important and valuable crops in the world. People around the world mainly depend on rice as their daily diet. Therefore, efficient rice fields monitoring is a crucial factor in the improvement of rice crop yield estimation, damage evaluation, budget planning, and agricultural resource management. Synthetic aperture radar (SAR) is an effective tool in monitoring agricultural fields because of its ability to provide high resolution images regardless of weather conditions. However, precision agriculture has put higher requirements for SAR data analysis. In recent years, deep learning methods have achieved great success in various remote sensing applications. In this research, two of the most popular deep learning architectures for time series data, namely convolutional long short-term memory (ConvLSTM) and gated recurrent unit (GRU) have been explored and applied to detect rice fields from SAR images in Taiwan. The experimental results showed that time-series deep learning methods for analyzing SAR data have a great potential for improving the rice fields detection.

In recent years, the satellite technique has a tremendous progress. The images captured by satellites contain larger data and dimensions. The higher number of spectral bands increases the complexity of a classification task. Therefore, it is necessary to reduce highly correlated and redundant neighboring bands which cause the huge phenomenon. In this paper, we proposed a hybrid hierarchical approaches that combine the greedy modular eigenspace (GME) and impurity function band prioritization with hotspot analysis. Unfortunately, GME doesn't guarantee to reach a global optimal solution by the greedy algorithm except by the exhaustive search method. In order to mitigate this limitation, we used a particle swarm optimization (PSO) algorithm to cluster the highly correlated bands and hotspot analysis to give weighting to the clustered blocks. The experimental results on two publicly available benchmark dataset demonstrate that the presented approach can select those bands with discriminative information. The effectiveness of the proposed approach is tested on both images with different parameters of PSO. To verify the effectiveness of a hybrid hierarchical approach put forward in this paper, KNN classifier is performed on the selected bands. In MASTER dataset, the proposed method has 90.91% achievement in dimensionality redaction rate with classification accuracy of 95.3%. In Northwest Tippecanoe County (NTC) dataset, the dimensionality reduction rate is 87.7% and the method achieve a classification accuracy of 96.48%.The results clearly show that the proposed method has the better effects both in dimensionality reduction rate and classification accuracy.

Synthetic aperture radar automatic target recognition (SAR-ATR) typically consists of 3 main stages: preprocessing(also known as prescreening), feature extraction, and classification. For high-dimensional feature space, the computation time required to construct it by sequential programming is considerably long. In this study, parts of an ATR system, in particular the feature extraction stage, were implemented on Graphics Processing Unit (GPU) for speed up. For Moving and Stationary Target Acquisition and Recognition (MSTAR) data set, the 3-stage ATR process constructing a 28-dimension feature space using 2987 samples performed over 6 times faster running a GPU implemented code than that of a sequential code on average.

In inverse synthetic aperture radar (ISAR) imaging, the imaging results can be affected by the unexpected target motions. This results in a blurry and unrecognizable image. The motion parameters estimation is a compensation method to improve the ISAR image refocusing and quality. In this study, the backscattered echo signals are simulated by the linear geometry system of ISAR moving targets. The entropy of ISAR image is used as a criterion to evaluate the image quality. Furthermore, this entropy measure can be treated as a cost function of the particle swarm optimization (PSO) method and minimized by PSO to improve the quality of ISAR images. The experimental results showed that our proposed PSO motion estimation approach to entropy minimization for ISAR imaging can not only efficiently improve the estimation capability of motion parameters, but also significantly achieve a better performance of ISAR image refocusing.

In this study, an accelerating method of oriented FAST and rotated BRIEF combined with principal component analysis (ORB/PCA) is proposed for splicing detection of unmanned aerial vehicle (UAV) images. Compared to traditional scale-invariant feature transform (SIFT) and speeded up robust features (SURF) methods, the proposed ORB/PCA can not only be faster but also produce more accurate. Moreover, in order for the proposed ORB to be effective for image stitching process in near real-time, the Compute Unified Device Architecture (CUDA) application programming interface of graphics processing unit (GPU) is cooperated to speed up the proposed method. Experimental results show that the proposed GPU based ORB/PCA framework is suitable for splicing detection of UAV images in Earth remote sensing. It can improve the image stitching process both in time and accuracy compared to conventional methods.

In this paper, a novel technique, known as a modified adaptable nearest feature space (MANFS) classifier, is proposed for supervised classification of remote sensing images. The original nearest feature space (NFS) may cause misclassification if the test samples are close to the different class training samples which are highly overlapped. Thus it is difficult to discriminate different classes. Compared to the original NFS classifier, we propose a novel MANFS classifier, which can precisely analysis the coverage of the feature space used in NFS and perfectly confine the extensible ranges of each feature space of NFS, to reduce the impact of the overlapping training samples of different categories. Experimental results show that MANFS achieves better classification accuracy than the original NFS one for remote sensing image.

Modern satellite imaging technology has resulted in an increased number of hyperspectral bands acquired by state-of-the-art sensors. It significantly advances the field of remote sensing. Owing to the increasing number of bands, the huge data quantity causes the curse of dimensionality and leads to the worse accuracy. It also increases the computational complexity exponentially as the problem size increases. It's therefore important to reduce dimensionality in order to prevent the curse of dimensionality. In this paper, a novel dimensionality reduction, named impurity function band prioritization method based on the particle swarm optimization and the gravitational search algorithms, is proposed to reduce the number of hyperspectral bands. The experimental results show that our approach can efficiently reduce dimensionality of hyperspectral data sets and significantly achieve a better classification accuracy compared to other methods.

SAR is a complex system that integrates two major parts: data collector and image formatter [1-2]. In the phase of data collection, radar transmits electromagnetic waves toward the target and receives the scattered waves. The transmitted signal can be modulated into certain types, commonly linearly frequency modulated with pulse or continuous waveform. The process involves signal transmission from generator, through various types of guided device, to antenna, by which the signal is radiated into free space, and then undergoes propagation. The measured scattered signal been made in bistatic or monostatic configurations is essentially in time-frequency (delay time - Doppler frequency) domain. The role of image formatter is then to map the time-frequency data into spatial domain where the targets are located. The mapping from the data domain to image domain, and eventually, into target or object domain must minimize both geometric and radiometric distortions. Essentially, two models that define the SAR operational process: physical model and system model. This paper concentrates on the physical process of a SAR system from wave scattering to imaging. System simulation based on the stationary (frequency modulation continuous wave) FMCW is developed and implemented for both point target and extended target. To further validate the simulation and thus our physical understanding of the imaging chain, measurements at aniconic chamber with two mental spheres and two dielectric spheres displaced with varying spacing were conducted. Good agreement between the simulated by extend target model and real measured SAR images is obtained.

Differential Interferometric Synthetic Aperture Radar (DInSAR) is an effective technique to measures the surface displacement caused by strong earthquakes. In our previous work an adaptive local kriging (ALK) was proposed to recover surface deformation associated with the fault zones. The calculation of ALK needs a huge computing power. Thus a high-performance computing is needed. It can not only speedup the interpolation processes of ALK but also handle large volumes of widely distributed remote sensing dataset. As a result, a parallel image interpolation approach, referred to as the graphics processing unit (GPU) based ALK method, to the slant range motion maps derived by DInSAR is proposed in this paper. It makes use of the performance profiling to analyze the serial version of ALK and perform a parallel GPU computation for reducing the computation time efficiently. By employing the NVIDIA TITAN GPU, the proposed method achieves a speedup of 77.86× compared to its CPU counterpart part.

This paper presents a promising band selection algorithm, known as particle swarm optimization/impurity function class overlapping (PSO/IFCO) method, which adopts a novel multiple attribute decision making (MADM) model approach to the hyperspectral remote sensing images. The proposed MADM-based PSO/IFCO method can be divided into two steps: 1) PSO algorithm and 2) the IFCO scheme. With PSO band selection algorithm, the highly correlated bands of hyperspectral imagery can first be grouped into band modules, known as greedy modular eigenspace (GME), to coarsely reduce high-dimensional datasets in the first step. The more highly correlated small modules are further constructed with the statistics of impurity weights calculated by IFCO scheme in the second step. These statistics results of impurity weights are used to finely select the most important feature bands from the hyperspectral imagery. The proposed MADM-based PSO/IFCO makes use of the correlation coefficients matrix to cluster the highly correlated bands together and obtain GME in the first step. More specifically, we use the analytic hierarchy process (AHP) model, which is the most suitable implementation of MCDM for proposed method, to examine hierarchically the relations among different GME modules with the impurity weighted by IFCO in the second step. Finally, by accommodating the statistics of impurity weights, the proposed MADM-based PSO/IFCO method can effectively select the most representative features for hyperspectral band selection and reduction. The effectiveness of the proposed method is evaluated by MASTER and AVIRIS hyperspectral images. The experimental results demonstrate that the proposed method can not only enhance the high dimension reduction rate, but also offer a satisfactory classification performance.

In this paper a novel technique based on nearest feature space (NFS), known as incenter-based nearest feature space (INFS), is proposed for supervised hyperspectral image classification. Due to the class separability and neighborhood structure, the traditional NFS can perform well for classification of remote sensing images. However, in some instances, the overlapping training samples might cause classification errors in spite of the high classification accuracy of NFS for normal cases. In response, the INFS is proposed to overcome this problem in this paper. INFS method makes use of the incircle of a triangle which is tangent to its three sides and form a INFS. In addition, an incenter can be calculated by three training samples of the same class efficiently. Furthermore, in order to speed up the computation performance, this paper proposes a parallel computing version of INFS, namely parallel INFS (PINFS). It uses a modern graphics processing unit (GPU) architecture with NVIDIA's compute unified device architecture (CUDA) technology to improve the computational speed of INFS. Experimental results demonstrate the proposed INFS approach is suitable for land cover classification in earth remote sensing. It can achieve the better performance than NFS classifier when the class sample distribution overlaps. Through the computation of GPU by CUDA, we can also gain better speedup.

Eigenspace projection methods are widely used for feature extraction from hyperspectral images (HSI) for the classification of land cover. Projection transformation is used to reduce higher dimensional feature vectors to lower dimensional vectors for more accurate classification of land cover types. In this paper, a nearest feature line embedding (NFLE) transformation is proposed for the dimension reduction (DR) of an HSI. The NFL measurement is embedded in the transformation during the discriminant analysis phase, instead of the matching phase. Three factors, including class separability, neighborhood structure preservation, and NFL measurement, are considered simultaneously to determine an effective and discriminating transformation in the eigenspaces for land cover classification. Three state-of-the-art classifiers, the nearest-neighbor, support vector machine, and NFL classifiers, were used to classify the reduced features. The proposed NFLE transformation is compared with different feature extraction approaches and evaluated using two benchmark data sets, the MASTER set at Au-Ku and the AVIRIS set at Northwest Tippecanoe County. The experimental results demonstrate that the NFLE approach is effective for DR in land cover classification in the field of Earth remote sensing.

In recent years, with the improvement of sensor technologies, the volumes of remote sensing data are increased dramatically. The feature extraction of hyper spectral remotely sensed images can reduce such high-dimensional datasets, solve the big data problem, avoid the Hughes phenomena and improve the classification performance. Accordingly, this paper presents a framework for feature extraction of hyper spectral imagery, which consists of two approaches, referred to as parallel particle swarm optimization (PPSO) band selection and weighted voting impurity function (WVIF) band prioritization. The highly correlated bands of hyper spectral imagery can be grouped first into the some modules by PPSO band selection algorithm to coarsely reduce high-dimensional datasets, and these highly correlated band modules can then be analyzed with the statistical relationship between bands and classes by WVIF band prioritization method to finely select the most important feature bands form the datasets. Furthermore, a PPSO algorithm based on modern graphics processing unit (GPU) architecture using NVIDIA compute unified device architecture (CUDA) technology is using in this paper. It can improve the computational speed of PPSO band selection to group the high correlated band modules. The effectiveness of the proposed PPSO/WVIF framework is evaluated by MASTER and AVIRIS hyper spectral images. The experimental results demonstrated that the proposed method not only could reduction the dimension of datasets, but also can offer a satisfactory classification performance and computational speed.

The tsunami disaster triggered by a huge 9.0 magnitude earthquake strikes Japan on March 11th, 2011. It motivates us to get involved in a research work in tsunami topics of Taiwan and to simulate an impact of the tsunami on the coast of Taiwan. Tsunami propagation is often modeled by the shallow water equations. These equations are derived from conservation of mass and momentum equations. By adding friction slope to the conservation of momentum equations, it enables the system to simulate the propagation over the coastal area. This system is able to estimate inundation zone caused by the tsunami. By applying Neumann boundary condition and Hansen numerical filter, it brings more interesting complexities into this simulation system. The parallelizable two-step finite-difference MacCormack scheme is employed to simulate the tsunami. In this paper, the parallel implementation of the MacCormack scheme is proposed for the shallow water equations by using the modern graphics processing unit (GPU) which accommodates NVIDIA compute unified device architecture (CUDA) technology to speed up the computation of the assessment of tsunami inundation. Experimental results demonstrate that the proposed approach is an effective simulation method for evaluating the impact on land inundation in Taiwan coastal area. With this method, we can in real-time manner monitor the progress of the land inundation. The information is valuable for constructing and refining the further altering systems in a dynamic manner for minimizing impacts caused by tsunamis.

In this paper, a novel technique, known as nearest feature space (NFS) approach, is proposed for supervised classification of multisource images for the purpose of landslide hazard assessment. It is developed for land cover classification based on the fusion of remotely sensed images of the same scene collected from multiple sources. This approach presents a framework for data fusion of multisource remotely sensed images, which consists of two approaches, referred to as band generation process (BGP) and Fisher criterion based NFS classifier. Compared to the original NFS, we propose an improve NFS classifier which uses the Fisher criterion of between-class and within-class discrimination to enhance the original one. In the training phase, the labeled samples are discriminated by the Fisher criterion, which can be treated as a pre-processing of NFS. Finally, the classification results can be obtained by NFS algorithm. In order for the proposed NFS to be effective for multispectral images, a multiple adaptation BGP is introduced to create a new set of additional bands especially accommodated to landslide classes. Experimental results demonstrate the proposed BGP/NFS approach is suitable for land cover classification in earth remote sensing and improves the precision of image classification.

This paper presents a GPU-based spherical coordinate conversion system for panorama video image stitching. Modern programmable GPU makes it possible to process multiple images in an interactive frame rates. To perform image stitching to form a panorama view, we use OpenCL to stitch multiple images and then texture map it to a spherical object. This allows us to compose an immersive environment. In the case study presented in this paper, we achieve a speedup factor of 76x.

A typical LIDAR (Light Detection and Ranging) scan contains hundreds of millions of points. As such, the visualization of LIDAR point clouds poses a significant challenge in data analysis. One solution is to display LIDAR point clouds on a large display wall with an array of LCD monitors. This provides researchers with a high-resolution display environment for looking at and studying large datasets. In this paper, we present a case study that visualizes LIDAR point clouds on a tiled display wall termed HIPerDisplay (Highly Interactive Parallelized Display). It has twenty 24-inch LCDs with a total resolution of 46 megapixels. Interaction between the user and the display wall is achieved by using a video camera system that is able to track the position of a hand-held light ball device. A user holds it to manipulate point clouds on HIPerDisplay. Case studies are conducted to study the LIDAR scans of slopes in the Houshanyue mountain areas in Taiwan. Experiments were conducted to examine the advantages of using the HIPerDisplay for point clouds in data post-processing. The experiments assess two tasks for manipulating point cloud data designed to evaluate the efficiency of the interactive devices. To evaluate the efficiency of the system, a group of thirty graduate students participated in the experiment. User surveys were performed to evaluate the efficiency of the system and to discover the users' opinions about using the interactive device in a large display environment. The results showed that the participants preferred to perform LIDAR data operation tasks on a high-resolution large display environment rather than on a single monitor. The results also showed that HIPerDisplay offered superior performance for the processing of large LIDAR datasets.

This study presents efficient vision-based finger detection, tracking, and event identification techniques, as well as a low-cost hardware framework for multi-touch sensing and display applications. A fast bright-blob segmentation process based on automatic multilevel histogram thresholding is performed to extract pixels of touch blobs from the captured image sequences obtained from the scattered infrared lights by the video camera. Given the touch blobs extracted from each of the captured frames, a blob tracking and event recognition process is then conducted to analyze the spatial and temporal information of these touch blobs from consecutive frames and determine the possible touch events issued by users. This process also refines the detection results and corrects for errors and occlusions caused by noise and errors during the blob extraction processes. Our proposed blob tracking and touch event recognition process includes two phases. First, the phase of blob tracking associates the motion correspondence of blobs in succeeding frames by analyzing their spatial and temporal features. Then the phase of touch event recognition process can identify meaningful touch events activated by users from the motion information of touch blobs. Experimental results demonstrate that the proposed vision-based finger detection, tracking, and event identification system is feasible and effective for multi-touch sensing applications in various operational environments and conditions.

Earthquake simulations generate large-scale ground-motion velocity wave-field data sets. One way to look at the data is to make it volume rendered so that researchers can examine the data efficiently. However, the volume data is usually quite large and a commodity graphics device can store one set of volume data. When the researcher need to look at the acceleration or displacement wave-field. The velocity data has to be integrated into displacement wave-field. Sometimes, the velocity data has to be differentiated into displacement wave-field. In this study, we used CUDA to compute the ground acceleration and displacement from velocity data. Numerical quadrature and centred difference method were implemented using CUDA for on-the-fly data exploration. We used CUDA to speed up ray casting method, trapezoidal quadrature, and centered difference method. We achieved a speed up of 100 times faster than using a CPU.

For linear dynamic systems with hidden states, the Kalman filter can estimate the system state and its error covariance considering the uncertainties in transition and observation models. In each iteration of applying the Kalman filter, the two phases of predict and update contain a total of 18 matrix operations which include addition, subtraction, multiplication and inversion. As recent graphic processor units (GPU) have shown to provide high speedup in matrix operations, we implemented a GPU accelerated Kalman filter in this work. For general reference purposes, we tested the filter on typical large-scale over-determined systems with thousands of components in states and measurements. For the various combinations of configurations in our test, the GPU accelerated filter shows a scalable speedup as either the state or the measurement dimension increases. The obtained 2 to 3 orders of magnitude speedup over its single-threaded CPU counterpart shows a promising direction of using the GPU-based Kalman filter in large-scale time-critical applications.

The needs for reliable and flexible downlink communications incorporated with high volume of satellite images in the ground station have inspired the demands for high performance and flexibility computing in the field of Earth remote sensing. Low-density parity-check (LDPC) codes have had a strong impact on achieving reliable communication links. Finding a fast and reconfigurable developing platform for designing high throughput LDPC decoders has become important. In this paper, a graphic processing unit (GPU) platform is proposed to realize this practical implementation. Experimental results show that the proposed GPU-based platform is compatible to serve as a high-throughput LDPC decoder.

Band selection for hyperspectral images is an effective technique to mitigate the curse of dimensionality. A variety of band selection methods have been suggested in the past. This paper presents a novel band prioritization based on impurity function (IF) for the band selection of hyperspectral images. The proposed IF band selection (IFBS) is incorporated with particle swarm optimization (PSO) band selection which has been developed to effectively group highly correlated bands of hyperspectral images into high corrected modules. It uses a particle swarm optimization scheme, which is a well-known method to solve the optimization problems, to develop an effective feature extraction algorithm for hyperspectral imagery. After PSO method is applied to the band reduction of hyperspectral images, the proposed IFBS is applied to enhance the efficiency of band selection. The propose method is evaluated by MODIS/ASTER airborne simulator (MASTER) for land cover classification during the Pacrim II campaign. The performance of IFBS is validated by the supervised k-nearest neighbor (KNN) classifier. Experimental results demonstrate that the proposed IFBS approach is an effective method for dimensionality reduction and feature extraction. Compared to other band selection methods, IFBS can effectively select the most significant bands for the image classification of hyperspectral images.

In the study, an efficient compression approach, group and region based KLT (GR-KLT), is proposed for hyperspectral imagery. The GR-KLT contains one clustering signal subspace projection (CSSP) segmentation method and the maximum correlation band clustering (MCBC) method. The CSSP first divides the image into proper regions and the MCBC partitions the spectral bands into several groups according to their associated band correlation for each image region. By the way, the image is further compressed by the KLT-JPEG for each group in each image region. Furthermore, we develop a parallel architecture for the GR-KLT compression algorithm. Simulation results performed on AVIRIS images have demonstrated the efficiency of the proposed approaches.

In the study, we propose a novel unsupervised classification technique for hyperspectral images, which consists of two algorithms, referred to as the maximum correlation band clustering (MCBC) and hierarchical binary quaternion-moment-preserving (BQMP) thresholding technique. By the MCBC, we partition the bands into groups and transfer the high-dimensional image data into low-dimensional image features. Afterwards, the hierarchical BQMP approach partitions the feature image into proper regions according to the spectral characteristics. Simulation results performed on AVIRIS images have demonstrated the efficiency of the proposed approaches.

In this paper we present a new supervised classification method, referred to as the k-way tree semi-greedy (KTSG) classifier, for the classification of multisource remote sensing images. The generalized positive Boolean function (GPBF) classifier scheme is recently proposed based on minimum classification error (MCE) criteria to improve classification performance. It makes use of MCE criteria to apply positive and negative samples as training parameters. Unfortunately, the classification performance of GPBF is limited when the number of classes increases. This is occurred in training phase by the unbalanced numbers of positive and negative samples caused by the use of a large number of classes. The proposed KTSG overcomes this drawback by modifying the scheme from the perception of pattern-node based semi-greedy (bottom-up scheme used in GPBF) to the conception of region-based semi-greedy (also known as the top-down scheme in KTSG). It is organized by a k-way tree in which every node is composed of a set of k-dimensional positive and negative labeled samples as represented as a percentage, i.e. the corresponding ratio of number of a specific (positive) class samples to the total number of the other (negative) classes. It iteratively divides the d-dimensional hyperplane into 2dsubspaces according to the centroids of the labeled (training) samples of all classes. The statistical ratios between different classes are then compared as a basis for stopping the new subspace separation and identifying which subspace belongs to which class. By delivering both positive and negative samples of different classes to KTSG learning modules, KTSG outperforms GPBF and traditional classifiers in terms of classification accuracies. The effectiveness of the proposed KTSG is evaluated by fusing MODIS/ASTER airborne simulator (MASTER) hyperspectral images and airborne synthetic aperture radar (AIRSAR) images for land cover classification during the Pacrim II campaign.

Greedy modular eigenspaces (GME) has been developed for the band selection of hyperspectral images (HSI). GME attempts to greedily select uncorrelated feature sets from HSI. Unfortunately, GME is hard to find the optimal set by greedy operations except by exhaustive iterations. The long execution time has been the major drawback in practice. Accordingly, finding an optimal (or near-optimal) solution is very expensive. In this study we present a novel parallel mechanism, referred to as parallel particle swarm optimization (PPSO) band selection, to overcome this disadvantage. It makes use of a new particle swarm optimization scheme, a well-known method to solve the optimization problems, to develop an effective parallel feature extraction for HSI. The proposed PPSO improves the computational speed by using parallel computing techniques which include the compute unified device architecture (CUDA) of graphics processor unit (GPU), the message passing interface (MPI) and the open multi-processing (OpenMP) applications. These parallel implementations can fully utilize the significant parallelism of proposed PPSO to create a set of near-optimal GME modules on each parallel node. The experimental results demonstrated that PPSO can significantly improve the computational loads and provide a more reliable quality of solution compared to GME. The effectiveness of the proposed PPSO is evaluated by MODIS/ASTER airborne simulator (MASTER) HSI for band selection during the Pacrim II campaign.

The main purpose of this paper is to describe available (HPC)-based implementations of remotely sensed hyperspectral image processing algorithms on multi-computer clusters, heterogeneous networks of computers, and specialized hardware architectures such as field programmable gate arrays (FPGAs) and graphic processing units (GPUs). Combined, the revision of existing techniques conducted in this paper, along with the description of performance results for a parallel hyperspectral processing chain on different architectures, delivers an excellent snapshot of the state-of-the-art in the area of HPC-based hyperspectral image processing and a thoughtful perspective of the potential and emerging challenges of applying HPC paradigms to hyperspectral imaging problems.

Simplex growing algorithm (SGA) was recently developed as an alternative to the N-finder algorithm (N-FINDR) which is shown to be a promising endmember extraction technique. This paper further extends the SGA to a real-time processing algorithm, referred to as real-time SGA (RT SGA) that can effectively address four major issues arising in practical implementation for N-FINDR, (1) use of random initial endmembers which causes inconsistent final results, (2) very high computational complexity which results from an exhaustive search for finding all endmembers simultaneously, (3) requirement of dimensionality reduction because of enormous data volumes to be processed and (4) lack of real-time capability.

In this paper we present a parallel classification learning method, referred to as parallel minimum classification error (PMCE) learning, for supervised classification of multisource remote sensing images. The approach is based on the positive Boolean function (PBF) classifier scheme. The PBF implements the minimum classification error (MCE) as a criterion to improve classification performance. By evenly distributing both positive and negative samples of MCE learning modules to different PMCE learning nodes, PMCE outperforms the original one in terms of execution time. It fully utilizes the significant parallelism embedded in MCE learning of PBF to create a set of PMCE learning nodes implemented by using the message passing interface (MPI) library and the open multi-processing (OpenMP) application programming interface. A sophisticated hierarchical structure of hybrid PMCE, which combines cluster based MPI with multicore-based OpenMP, is proposed to demonstrate the flexibility of implementation of the proposed scheme. The effectiveness of the proposed PMCE is evaluated by fusing MODIS/ASTER airborne simulator (MASTER) hyperspectral images and the Airborne Synthetic Aperture Radar (AIRSAR) images for land cover classification during the Pacrim II campaign. The experimental results demonstrated that PMCE can improve the computational speed of PBF classification significantly.

In this paper we present a parallel band selection approach, referred to asparallelsimulatedannealingbandselection(PSABS), for hyperspectral imagery. The approach is based on thesimulatedannealingbandselection(SABS) scheme. The SABS algorithm is originally designed to group highly correlated hyperspectral bands into a smaller subset of band modules regardless of the original order in terms of wavelengths. SABS selects sets of non-correlated hyperspectral bands based onsimulatedannealing(SA) algorithm and utilizes the inherent separability of different classes in hyperspectral images to reduce dimensionality. In order to be effective, the proposed PSABS is introduced to improve the computational speed by using parallel computing techniques. It allowsmultipleMarkovchains(MMC) to be traced simultaneously and fully utilizes the significant parallelism embedded in SABS to create a set of PSABS modules on each parallel node implemented by themessagepassinginterface(MPI) cluster-based library and theopenmulti-processing(OpenMP) multicore-based application programming interface. The effectiveness of the proposed PSABS is evaluated byMODIS/ASTERairbornesimulator(MASTER) hyperspectral images for hyperspectral band selection during the PACRIM II campaign. The experimental results demonstrated that PSABS can significantly improve the computational loads and provide a more reliable quality of solution compared to the original SABS method.

Anomaly detection for remote sensing has drawn a lot of attention lately. An anomaly has distinct spectral features from its neighborhood, whose spectral signature is not known a priori, and it usually has small size with only a few pixels. It is very challenge to detect anomalies, especially without any information of the background environment in hyperspectral data with hundreds of co-registered image bands. Several methods are devoted to this problem, including the well-known RX algorithm which takes advantage of the second-order statistics and other algorithms which detect anomaly based on higher order statistics such as skewness and kurtosis. It has been proved that the High-Order Automatic Anomaly Detection Algorithm can outperform RX algorithm by distinguishing different types of anomalies. However, the initialization of the High-Order Automatic Anomaly Detection Algorithm remains a challenge problem. When the initial vectors are selected randomly for this recursive algorithm, they might be trapped in the local maximums and give different projection directions. But in our experiments, all those directions will show different types of anomalies. Therefore, this algorithm is particular suitable for parallel processing to increase the computing efficiency. In the parallel architecture, we will first randomly generate initial vectors for each process, and then united those output results for the orthogonal projection base. We will also compare the computational efficiency with the number of parallel processes we used.

In recent years, dynamic voltage and frequency scaling (DVFS) has been considered as one of the most efficient techniques to decrease energy consumption, especially for battery-powered portable devices. However, many DVFS algorithms discuss the issue from the perspective of the processors only. Some researches have started to study the effects of memories in the DVFS algorithms. In this paper, an approximation equation (called MAR-CSE) based on the correlation of the memory access rate and the critical speed for the minimum energy consumption is conducted for frequency and voltage prediction. The memory access information is obtained from the performance monitoring unit (PMU) provided on an Intel XScale platform which we used in this study. With MAR-CSE, an MA-DVFS (memory-aware DVFS) algorithm is proposed. The algorithm has been realized in the Linux kernel. Experiment results show that the energy consumption of the memory bound benchmarks can be reduced from 50% to 65%, much better than the result of 19% to 53% energy saving for the on-demand mechanism which is already supported by the Linux kernel.

For most Portable Media Player (PMP), the demands for large storage space and longer working time usually can not be satisfied at the same time. In this paper, a low power wireless LAN based PMP called WiPMP is proposed. WiPMP is basically a diskless PMP. Instead, it can retrieve a large number of multimedia data from a remote storage device wirelessly. A prototype of WiPMP has been realized on an Intel Xscale embedded platform with Embedded Linux as the operating system. A systematic power measurement and analysis method is used in this paper to evaluate the prototype from the perspective of power consumption. The result shows that WiPMP does consume less power and is able to access much more multimedia data than the hard disk based PMP.

In this paper, we present a parallel computing technique, referred to as parallel positive Boolean function (PPBF), for supervised classification of multispectral images. The approach is based on the generalized positive Boolean function (GPBF) scheme, which has been successfully applied in multispectral image classification. The GPBF classifier is developed from a stack filter. The stack filter is defined as the class of all nonlinear digital filters. Each stack filter corresponding to a GPBF possesses the weak superposition property and the ordering property. In order for the GPBF to be effective, the proposed PPBF is performed to improve the computational speed by using parallel cluster computing techniques. It creates a set of stack filters in each parallel node implemented by message passing interface (MPI). The proposed PPBF technique reduces the structure complexity of original GPBF. The effectiveness of the proposed PPBF is evaluated by fusing Systeme Pour l’Observation de la Terre (SPOT) images and digital elevation model (DEM) information for land cover classification during the post 921 Earthquake period in Taiwan. The experimental results demonstrated that PPBF not only significantly improves the computational loads of GPBF classification, but also substantially improves the precision of classification compared to conventional classification.

In this paper, a novel study is proposed for the feature extraction of high volumes of remote sensing images by using a simulated annealing feature extraction (SAFE) approach. For hyperspectral imagery, complete modular eigenspace (CME) has been developed by clustering highly correlated hyperspectral bands into a smaller subset of band modular based on greedy algorithm. Instead of greedy paradigm as adopted in CME approach, this paper introduces a simulated annealing (SA) approach for hyperspectral imagery. It presents a framework which consists of three algorithms, referred to as SAFE, CME and the feature scale uniformity transformation (FSUT). SAFE selects the sets of non-correlated hyperspectral bands based on SA algorithm while utilizing the inherent separability of different classes in hyperspectral images to reduce dimensionality and further to effectively generate a unique CME feature. The proposed SA features avoids the bias problems of transforming the information into linear combinations of bands as does the traditional principal components analysis and provides a fast procedure to simultaneously select the most significant features according to a scheme of SA. The experimental results show that the SAFE approach is effective and can be used as an alternative to the existing feature extraction algorithms.

Earthquakes or torrential rains often lead to landslides. The Chichi earthquake in 1999 struck Nantou County of central Taiwan and caused civilian casualties of more than 2,400. The earthquake also turned the disaster areas into the sites of tens of thousands of landslides and rock avalanches. Added with the annual April–June Mei-Yu rain season and July–September typhoon season, Nantou County is further victimized by these elemental factors because it is one of the most affected areas during those seasons. With respect to the worsening scenario, this project attempts an in-depth look at the most damaged regions, using the high resolution SPOT satellite images taken in Septembers of 1999, 2002 and 2005. Landslide prediction is of spatial and temporal concerns, since these targeted sites cannot be thoroughly understood without knowledge of its geological past. This study thus examines the prospective changes in the entire measures of area of landslide sites in Nantou using Markov’s statistics model. The purpose is to develop a comprehensive methodology for conducting a random prediction of spatial and environmental factors in response to the transitory processes of the landslide areas. With the application of transition matrices derived from Markov’s model in the changes in future landslide coverage, it is estimated that the ratio of landslide will gradually stabilize from 1.02% in 2002 and 0.93% in 2005 to 0.82% in 2032. And from the analysis of Logit model, it is clear that the landslides are closely related to cumulated rainfall, altitude, slope gradients and geological formations, and in particular slope gradients having the greatest effect.

In this paper, a novel technique is proposed for a supervised classification of multisource images for the purpose of landslide hazard assessment. The method, known as the generalized positive Boolean function (GPBF), is developed for land cover classification based on the fusion of remotely sensed images of the same scene collected from multiple sources. It presents a framework for data fusion of multisource remotely sensed images, which consists of two approaches, referred to as the band generation process (BGP) and the positive Boolean function (PBF) classifier. The PBF classifier developed from a stack filter has been successfully applied in hyperspectral image classification. For the PBF to be effective for multispectral images, a multiple adaptation BGP is introduced to create a new set of additional bands especially accommodated to landslide classes. These bands include nonlinear normalized difference vegetation index data and morphological information in the form of digital elevation model (DEM)-derived slope values that originate from multiple sources. The performance of the proposed method is evaluated by fusing Systeme Pour l'Observation de la Terre images and DEM information for land cover classification during the post 921 Earthquake period in Taiwan. Experimental results demonstrate the proposed GPBF multiclassification approach is suitable for land cover classification in Earth remote sensing and improves the precision of image classification compared to conventional classifiers

In this paper, we present a parallel computing technique for the feature extraction of hyperspectral images. The approach is based on the complete modular eigenspace (CME) scheme, which was designed to extract the simplest and most efficient feature modules by a newly defined multi-dimensional correlation matrix to optimize the modular eigenspace for high- dimensional datasets. The CME feature extraction scheme improves the performance of feature extraction by modifying the correlation coefficient operations. The proposed parallel CME (PCME) scheme is introduced to reduce the computational load of CME feature extraction using the parallel computing technique. It is implemented by parallel virtual machine (PVM) to solve the huge matrix problems of CME feature extraction. The performance of the proposed method is evaluated by applying to hyperspectral images of MODIS/ASTER (MASTER) airborne simulator during the Pacrim II project. The experiments demonstrate the proposed PCME approach is an effective scheme not only for the feature extraction but also for the band selection of high-dimensional datasets. It can improve the precision of hyperspectral image classification compared to conventional multispectral classification schemes.