Soybean, a pivotal global source of oil and protein, exhibits heightened sensitivity to soil moisture conditions throughout its growth cycle. Accurate monitoring of soil moisture (SM) in soybean fields during the growing season is indispensable for optimizing yields and forecasting sustainable agricultural practices. Leveraging advancements in remote sensing technology, passive microwave soil moisture retrieval has emerged as a crucial tool for large-scale precision agriculture and enduring environmental monitoring. However, challenges in the L-band Microwave Emission of the Biosphere (L-MEB) model, particularly in the computation of vegetation transmissivity, may compromise the accuracy of soil moisture retrieval. In this study, we improved the Beer-Lambert law to more accurately quantify the attenuation effect of the vegetation layer on microwave signals, aiming to ameliorate the inherent limitations in the L-MEB model. The proposed soil moisture retrieval method, primarily validated in soybean fields, was also subjected to supplementary experiments in canola and wheat fields to further assess its effectiveness and generalizability. The proposed method integrates passive microwave and optical data, demonstrating a substantial improvement in accuracy. Experimental results reveal that our enhanced method significantly outperforms the L-MEB model in soybean fields: Pearson correlation coefficients of soil moisture, derived using vegetation water content and leaf area index, are 0.712 and 0.692 respectively. Furthermore, root mean square errors have decreased to 0.056m3/m3and 0.050 m3/m3, a reduction of 39.78% and 19.35%, respectively. In canola and wheat fields, the method exhibited an approximate 10% enhancement in retrieval accuracy. This advancement not only furnishes novel technical support for water management in soybean cultivation but also contributes theoretical and technical insights to the domain of passive microwave soil moisture retrieval. Index Terms-L-MEB model, passive microwave, soil moisture retrieval, vegetation transmissivity.

Leaf area index (LAI) serves as a key ecophysiological parameter for assessing plant growth and is particularly vital for crop monitoring. Using unmanned aerial vehicle (UAV)-based point cloud data generated through photogrammetry techniques offers valuable structural insights into crops, facilitating LAI retrieval. This study introduces a method for estimating LAI from 3-D point clouds. By employing spherical voxel partitioning, the vegetation gap fraction is computed based on the spatial distribution of point clouds. Furthermore, the leaf inclination angle is determined through triangular patch collections reconstructed from 3-D point clouds. Projection functions, accounting for varying zenith perspectives, are developed considering the leaf inclination angle. Subsequently, the combination of vegetation gap fraction and projection functions is used within the Beer–Lambert law framework to calculate LAI. Validation against ground measurements demonstrates a strong correlation between measured and retrieved LAI ($R^{2} = 0.64$, RMSE = 0.43), affirming the effectiveness of the proposed method in estimating LAI using UAV-based structure from motion (SfM) point cloud data.

Current iterative multiple-input multiple-output (MIMO) detectors suffer from slow convergence when the wireless channel is ill-conditioned. The ill-conditioning is mainly caused by spatial correlation between channel columns corresponding to the same user equipment, known as intra-user interference. In addition, in the emerging MIMO systems using an extremely large aperture array (ELAA), spatial non-stationarity can make the channel even more ill-conditioned. In this paper, user-wise singular value decomposition (UW-SVD) is proposed to accelerate the convergence of iterative MIMO detectors. Its basic principle is to perform SVD on each user’s sub-channel matrix to eliminate intra-user interference. Then, the MIMO signal model is effectively transformed into an equivalent signal (e-signal) model, comprising an e-channel matrix and an e-signal vector. Existing iterative algorithms can be used to recover the e-signal vector, which undergoes post-processing to obtain the signal vector. It is proven that the e-channel matrix is better conditioned than the original MIMO channel for spatially correlated (ELAA-)MIMO channels. This implies that UW-SVD can accelerate current iterative algorithms, which is confirmed by our simulation results. Specifically, it can speed up convergence by up to 10 times in both uncoded and coded systems.

The cumulative distribution function (CDF) of a non-central$\chi ^{2}$-distributed random variable (RV) is often used when measuring the outage probability of communication systems. For ultra-reliable low-latency communication (URLLC), it is important but mathematically challenging to determine the outage threshold for an extremely small outage target. This motivates us to investigate lower bounds of the outage threshold, and it is found that the one derived from the Chernoff inequality (named Cher-LB) is the most effective lower bound. This finding is associated with three rigorously established properties of the Cher-LB with respect to the mean, variance, reliability requirement, and degrees of freedom of the non-central$\chi ^{2}$-distributed RV. The Cher-LB is then employed to predict the beamforming gain in URLLC for both conventional multi-antenna systems (i.e., MIMO) under first-order Markov time-varying channel and reconfigurable intellgent surface (RIS) systems. It is exhibited that, with the proposed Cher-LB, the pessimistic prediction of the beamforming gain is made sufficiently accurate for guaranteed reliability as well as the transmit-energy efficiency.

The cumulative distribution function (CDF) of a non-central$\chi^{2}$-distributed random variable (RV) is often used when measuring the outage probability of communication systems. For adaptive transmitters, it is important but mathematically challenging to determine the outage threshold for an extreme target outage probability (e.g., 10−5or less). This motivates us to investigate lower bounds of the outage threshold, and it is found that the one derived from the Chernoff inequality (named Cher-LB) is the most effective lower bound. The Cher-LB is then employed to predict the multi-antenna transmitter beamforming-gain in ultra-reliable and low-latency communication, concerning the first-order Markov time-varying channel. It is exhibited that, with the proposed Cher-LB, pessimistic prediction of the beamforming gain is made sufficiently accurate for guaranteed reliability as well as the transmit-energy efficiency.

The design of iterative linear precoding is recently challenged by extremely large aperture array (ELAA) systems, where conventional preconditioning techniques could hardly improve the channel condition. In this paper, it is proposed to regularize the extreme singular values to improve the channel condition by deducting a rank-one matrix from the Wishart matrix of the channel. Our analysis proves the feasibility to reduce the largest singular value or to increase multiple small singular values with a rank-one matrix when the singular value decomposition of the channel is available. Knowing the feasibility, we propose a low-complexity approach where an approximation of the regularization matrix can be obtained based on the statistical property of the channel. It is demonstrated, through simulation results, that the proposed low-complexity approach significantly outperforms current preconditioning techniques in terms of reduced iteration number for more than 10% in both ELAA systems as well as symmetric multi-antenna (i.e., MIMO) systems when the channel is i.i.d. Rayleigh fading.

Synthetic aperture radar (SAR), as an active microwave sensor, has proven to be effective in retrieving soil moisture (SM) over the past few decades. However, accurately estimating SM over agricultural regions is challenging due to the complex interactions between SM, soil roughness, and vegetation, resulting in mixed backscattering signals. The change detection (CD) method eliminates the influence of soil roughness by employing the ratio of two consecutive SAR images. However, the volume scattering caused by the crop canopy still affects SM estimation. To mitigate this limitation, we propose an advanced change detection method for SM retrieval using the random volume over ground (RVoG) decomposition on time-series compact-polarization SAR data. Experimental results using high-resolution time-series RCM in corn and soybean fields show promising performance, with root-mean-square-error (RMSE) values of 10.34 Vol.% and 7.41 Vol.% for RCH and RCV polarization in the corn field and 6.47 Vol.% and 5.03 Vol.% in the soybean field, respectively. The proposed method outperforms the original CD method, highlighting its potential as a reliable alternative for consistent SM retrieval from the RCM.

In this paper, a novel nonlinear precoding (NLP) technique, namely constellation-oriented perturbation (COP), is proposed to tackle the scalability problem inherent in conventional NLP techniques. The basic concept of COP is to apply vector perturbation (VP) in the constellation domain instead of symbol domain; as often used in conventional techniques. By this means, the computational complexity of COP is made independent to the size of multi-antenna (i.e., MIMO) networks. Instead, it is related to the size of symbol constellation. Through widely linear transform, it is shown that COP has its complexity flexibly scalable in the constellation domain to achieve a good complexity-performance tradeoff. Our computer simulations show that COP can offer very comparable performance with the optimum VP in small MIMO systems. Moreover, it significantly outperforms current sub-optimum VP approaches (such as degree-2 VP) in large MIMO whilst maintaining much lower computational complexity.

In vehicle-to-infrastructure (V2I) networks, a cluster of multi-antenna access points (APs) can collaboratively conduct transmitter beamforming to provide data services (e.g., eMBB or URLLC). The collaboration between APs effectively forms a networked linear antenna-array with extra-large aperture (i.e., network-ELAA), where the wireless channel exhibits spatial non-stationarity. Major contribution of this work lies in the analysis of beamforming gain and radio coverage for network-ELAA non-stationary Rician channels considering the AP clustering. Assuming that: 1) the total transmit-power is fixed and evenly distributed over APs, 2) the beam is formed only based on the line-of-sight (LoS) path, it is found that the beamforming gain is concave to the cluster size. The optimum size of the AP cluster varies with respect to the user’s location, channel uncertainty as well as data services. A user located farther from the ELAA requires a larger cluster size. URLLC is more sensitive to the channel uncertainty when comparing to eMBB, thus requiring a larger cluster size to mitigate the channel fading effect and extend the coverage. Finally, it is shown that the network-ELAA can offer significant coverage extension (50% or more in most of cases) when comparing with the single-AP scenario.

Concerning ultra-reliable low-latency communication (URLLC) for the downlink operating in the frequency-division multiple-access with random channel assignment, a lightweight power allocation approach is proposed to maximize the number of URLLC users subject to transmit-power and individual user-reliability constraints. Provided perfect channel-state-information at the transmitter (CSIT), the proposed approach is proven to ensure maximized URLLC users. Assuming imperfect CSIT, the proposed approach still aims to maximize the URLLC users without compromising the individual user reliability by using a pessimistic evaluation of the channel gain. It is demonstrated, through numerical results, that the proposed approach can significantly improve the user capacity and the transmit-power efficiency in Rayleigh fading channels. With imperfect CSIT, the proposed approach can still provide remarkable user capacity at limited cost of transmit-power efficiency.

In this paper, a novel spatially non-stationary channel model is proposed for link-level computer simulations of massive multiple-input multiple-output (mMIMO) with extremely large aperture array (ELAA). The proposed channel model allows a mix of non-line-of-sight (NLoS) and LoS links between a user and service antennas. The NLoS/LoS state of each link is characterized by a binary random variable, which obeys a correlated Bernoulli distribution. The correlation is described in the form of an exponentially decaying window. In addition, the proposed model incorporates shadowing effects which are non-identical for NLoS and LoS states. It is demonstrated, through computer emulation, that the proposed model can capture almost all spatially non-stationary fading behaviors of the ELAA-mMIMO channel. Moreover, it has a low implementational complexity. With the proposed channel model, Monte-Carlo simulations are carried out to evaluate the channel capacity of ELAA-mMIMO. It is shown that the ELAA-mMIMO channel capacity has considerably different stochastic characteristics from the conventional mMIMO due to the presence of channel spatial non-stationarity.

This study evaluated three geometric transformations in an image registration method applied to non-georeferenced multispectral images acquired at close range over greenhouse cucumber plants with a Micasense®RedEdge camera. The detection of matching points was performed using SURF features, and outliers matching points were removed using the MSAC algorithm. For each geometric transformation (affine, similarity, and projective), we mapped the matching points of the blue, green, red, and NIR band images into the red-edge band space and computed the root mean square error (RMSE in pixel) to estimate the accuracy of each transformation. Our results achieved an RMSE of less than 1 pixel with the similarity and affine transformations and of less than 2 pixels with the projective transformation, whatever the band image. We determined that the best transformation was the affine transformation because it produces RMSEs of less than 1 pixel and having a Gaussian distribution.

Multi-access edge computing for mobile computing-task offloading is driving the extreme utilization of available degrees of freedom (DoF) for ultra-reliable low-latency downlink communications. The fundamental aim of this work is to find latency-constrained transmission protocols that can achieve a very-low outage probability (e.g. 0.001%). Our investigation is mainly based upon the Polyanskiy-Poor-Verdú formula on the finite-length coded channel capacity, which is extended from the quasi-static fading channel to the frequency selective channel. Moreover, the use of a suitable duplexing mode is also critical to the downlink reliability. Specifically, time-division duplexing (TDD) outperforms frequency-division duplexing (FDD) in terms of the frequency diversity-gain. On the other hand, FDD takes the advantage of having more temporal DoF in the downlink, which can be exchanged into the spatial diversity-gain through the use of space-time coding. Numerical study is carried out to compare the reliability between FDD and TDD under various latency constraints.

The majority of current dimension reduction methods are restricted to the use of spectral information, when the spatial information is left out. In order to overcome this defect, two different solutions: patch-based and tensor-patch-based approaches, were studied in this paper. This paper applies the two solutions to a group of graph-based dimension reduction methods. We found that the patch-based and tensor-patch-based variations greatly boost the final classification results by 5%-15% from the traditional methods. As graph-based methods heavily rely on the calculation of adjacency graphs/weight matrices, this paper proposed the use of a new method: weighted region covariance matrix, to produce the adjacency graphs/weight matrices. In results, the newly proposed method can further improve the dimension reduction results in both the patch-based and tensor-patch-based methods. To reduce the intense computation in the adjacency graphs/weight matrix calculation, the principle component analysis (PCA) is proposed by this paper as a preprocess step.

In this study, Sentinel-2 and VENμS remote sensing data were combined to estimate corn biomass based on a simple light use efficiency method. The RMSE between the measured dry aboveground biomass and estimated dry aboveground biomass is 112.36 g/m2. The estimates show good agreements with the measured biomass, indicating that the effective light use efficiency (ELUE) can be effectively estimated using maximal fAPAR throughout the growing season.

Currently, Unmanned Aerial Vehicle (UAV)-based remote sensing is a flexible and reliable approach to gather data for agricultural crop intra-field monitoring. This study proposes real-time and low-cost approaches for crop leaf area index (LAI) estimation using UAV-based 3D point cloud data at field-scale. Crop LAI is an indicator of crop growth variation within crop fields which is one of the most essential crop parameters in crop growth models to predict other crop parameters including chlorophyll, biomass and final yield. After converting a circle with a radius of 2 meters 3D point cloud data to spherical projection, the sampling 3D point cloud data will be converted to a hemispherical photograph. The crop canopy LAI is then calculated from this hemispherical photograph using the gap fraction method. From the experiments over a winter wheat field, the estimated LAI from the UAV-based 3D point cloud data is highly correlated with the LAI estimated from an in-situ fisheye camera, the R2are 0.8995 and 0.8658 for 4 rings and 5 rings view angles calculation, respectively.

In recent years, a new genre of hyperspectral unmixing methods based on nonnegative matrix factorization (NMF) have been proposed. Unlike traditional spectral unmixing methods, the NMF-based hyperspectral unmixing methods no longer depend on pure pixels in the original image. The NMF is based on linear algebra, which requires that the hyperspectral data cube is converted from 3-D cube to a 2-D matrix. Due to this conversion, the spatial information in the relative positions of the pixels is lost. With the emergence of multilinear algebra, the tensorial representation of hyperspectral imagery that preserves spectral and spatial information has become popular. The tensor-based spectral unmixing was first realized in 2017 using the matrix-vector nonnegative tensor factorization (MVNTF) decomposition. Using the construction of MVNTF spectral unmixing, this letter proposes to integrate three additional constraints (sparseness, volume, and nonlinearity) to the cost function. As we show in this letter, we found that the three constraints greatly improved the impervious surface area fraction/classification results. The constraints also shortened the processing time.

This reported study was intended to advance the retrieval of leaf area index (LAI) using synthetic aperture radar (SAR) data. A novel method was proposed by introducing the vegetation coverage into the Water Cloud Model (WCM) to improve the retrieval accuracy of the LAI. LAI is a strong indicator of crop productivity, and vegetation coverage has a strong relationship with the LAI (R2=0.9733), a function can be created to express their relation. Finally, the accuracy in this innovative LAI retrieval method were evaluated. The results showed that the accuracy of estimation was improved greatly (R2was increased to 0.6055 and 0.6422 from 0.3491 and 0.3561 in VH and HH polarization). Thus, the method has operational potential for the LAI retrieval of crop in agriculture regions.

This study investigates surface roughness properties of the Haughton impact structure in the Canadian Arctic using L-, C-, and X-band SAR. Meteorite impact structures are highly localized geological features, providing impact-exposed subsurfaces of a range of regional stratigraphic columns [1]. The Haughton impact structure exposes a wide range of geological features of central Devon Island including impact-generated products. Thus, geologic mapping of an impact structure can be an effective way to expand our remote predictive mapping throughout the Canadian Arctic.

The future launch of EnMAP satellite in 2019 will enable the acquirement of hyperspectral data for obtaining more accurate relevant surface parameters on a global scale. This paper will discuss the application of EnMAP in extracting impervious surface area (ISA) from urban-rural gradient scenes. Considering the need for ISA extraction in urban studies, the choice of endmembers are made of five mixed types: vegetation, high and low albedo (impervious surface area), soil, and water. This research uses the robust non-negative matrix factorization to simultaneously generate endmembers and the corresponding abundances. It has been found that the strategy of mixed endmembers is a reasonable approach in median spatial resolution spaceborne imagery. Even with the median resolution of 30m, the EnMAP derived ISA is comparable to the result from high spatial resolution (1m) airborne data.

A simple target scattering model is developed integrating the shape factor and geometric randomness that are less influenced by the SAR configuration, dielectric properties of crop, and the underlying soil conditions, to describe the shape and statistical distribution of the targets, respectively. 47 fully polarimetric RADARSAT-2 images in FQ1W, FQ6W, FQ10W, FQ15W and FQ19W modes with different incidence angles acquired over Temiskaming Shores, Ontario, Canada in 2015 are adopted for the validation. Comparisons of the geometric features with H, α, and RVI, demonstrate that geometric features of wheat, oat, alfalfa, and barely show less fluctuation and more consistent with their growing stages over time till their harvest, but crops with broad leaves such as corn and soybean still show some fluctuations with high geometric randomness. In addition, the plots of n and δ of different crops also shows their potential on the crop classification.

Spatio-temporal data fusion model is a feasible way to obtain high spatial resolution and high temporal resolution images in crop monitoring. As vegetation indices such as Normalized Difference Vegetation Index (NDVI) are generally used directly to monitor the vegetation growth, in this study, two recently proposed spatio-temporal data fusion methods (FSDAF and DPM-STVIFM) were evaluated for generating NDVI time series in cropland areas. It is found that both methods have limitations and the performances of the two methods vary with the dates of available fine-resolution images and the degree of land cover changes between the available fine-resolution images and the synthetic fine-resolution images.

Remote sensing techniques applied in crop monitoring and management can help to reduce the input of nitrogen without reducing crop yield and accurately predict nitrogen demand [1]. The objective of this study is to use the ground based multispectral images to predict canopy nitrogen level for soybeans in southwestern Ontario. A light weight multispectral camera were used to collect multispectral measurements for four soybean fields from July to September in 2015. An evaluation of existing nitrogen indices were carried on in this study for soybean canopy nitrogen to select the best fit index for the study area. The results show that the modified RENDVI780-730has the best correction between soybean nitrogen level and the spectral based index, the R2is 0.70. This index is sensitive to vegetation structures Leaf Area Index (LAI) which is a confounding factor for the remote estimation of nitrogen. This index will lead an inaccuracy nitrogen prediction for soybeans. Therefore, multi-linear regression (MLR) analysis method using five band information was carried on and established a canopy nitrogen model for soybeans in this study. The R2of the model is 0.745 and the RMSE is 0.51.

This paper examines the potential of Radarsat-2 C-band synthetic aperture radar (SAR) data for quantifying the spatial variability of soil moisture during the agriculture growth period. To remove the effect of crop within total backscattering, a method that adequately represents the scattering behavior of vegetation-covered area by defining the scattering of the vegetation and underlying soil was developed. The Dubois model was employed to determine the backscattering from the underlying soil. The modified Water Cloud Model was used to reduce the effect of backscattering caused by the vegetation. Soil moisture was derived by the inversion scheme which uses of the dual polarizations (HH and VV) available from the quad polarization Radarsat-2 data.

In this letter, we attempt to improve existing model-based decomposition methods to estimate the soil moisture for C-band RADARSAT-2 data. An adaptive two-component decomposition (ATCD) is developed that considers the surface and volume scattering caused by the soil and crop canopy, respectively. The surface scattering adopted is an X-Bragg scattering, with the orientation angle induced by the azimuthal slope under a zero-mean normal distribution function, whereas the volume scattering model is constructed based on the nth power of sine and cosine probability distribution functions. Five sets of fully polarimetric RADARSAT-2 data acquired, in 2013 and 2015, over two study areas, were used to demonstrate the proposed technique, showing that the volumetric soil moisture derived from the ATCD is more consistent with the verifiable ground conditions compared with other model-based decomposition methods.

Many research studies have investigated surface parameter inversion for bare soils. This paper attempts to take into account the agricultural fields with crop residues and fields under low vegetation cover in addition to bare soil fields. An integrated surface parameter inversion scheme (ISPIS) is proposed to invert surface parameters in these agricultural fields based on the analysis of H-α parameters at the early crop growing stages, in which the calibrated integral equation model (CIEM) is adopted to invert surface parameters for bare soils, and an adaptive two-component decomposition combined with the CIEM and a simplified adaptive volume scattering model is developed for fields with crop residues and under low vegetation cover. Fully polarimetric RADARSAT-2 data with ground truth collected on April 29 and May 9 in 2013 and from May to June in 2014 are used for validation. Compared with other methods, the derived volumetric soil moisture (MV) and surface roughness (KS) of all agricultural fields are consistent with verifiable observations with the lowest overall root mean square error: 6.12 [vol.%] and 0.48, respectively, when all sample sites are considered.

Many research studies have investigated the retrieval of surface parameters for bare soils. This study attempts to take into account agricultural fields with crop residues and low vegetation cover. An adaptive two-component decomposition (ATCD) method is developed in this paper to invert surface parameters in these fields. The study area is located in Southwestern Ontario, Canada where two wheat fields and two corn-residue fields are selected as sample sites. Three fully polarimetric RADARSAT-2 data, which were acquired in 2013 and 2014 respectively, are employed for the validation. The ATCD has 100% inversion rate compared with the Bragg and X-Bragg models, while its root mean square errors (RMSE) of the soil moisture and roughness have the lowest value of 6.72% and 0.33, respectively. The derived soil moisture in wheat field also has the lowest RMSE value of 3.97% compared with the Y-CIEM.

This letter proposes a multicriteria system to evaluate the accuracy of reconstructed 3-D buildings. Current 3-D evaluation methods are derived from 2-D pixel-based evaluation; however, the difference between 2-D and 3-D evaluation methods is not well presented in previous literature. Most 3-D building evaluation methods concentrate solely on rooftop accuracy while ignoring the degree of accuracy found with regard to walls. To address these problems, this letter designs a multicriteria evaluation system based on three components: volume, surface, and point. The volume accuracy component represents the traditional classification accuracy based on random samples. The surface accuracy component evaluates shape similarity which compares sample and reference buildings, including rooftops and walls, in a true 3-D environment. The point accuracy component measures distance at feature points between the sample building and the reference building. This multicriteria system aims to provide an improved evaluation method for building reconstruction using advanced algorithms and multiplatform data. The system is also expected to provide valuable information to guide applications with different accuracy requirements.

There are numerous building footprint extraction methods from various data sources and extraction strategies. However, the lack of a consistent standard to evaluate the accuracy of such methods impedes the comparison of different methods, as well as further exploration of new methods. In this study, a comprehensive evaluation system for building detection is proposed and implemented. In order to test its performance, four different building footprint extraction methods have been designed using LiDAR and Colour Infrared Aerial Images. The comparison of the proposed accuracy evaluation indices and the analysis of the results demonstrate that the designed evaluation system can provide a more complete assessment for building footprint detection.

This research proposed an object-oriented method to obtain the distribution of tree coverage in urban environment using 0.6m aerial multi-spectral images. With the support of eCognition Software, the whole tree coverage mapping process included the following steps. Firstly, selecting a set of appropriate parameters by trial and error process to obtain an optimal segmentation result for tree coverage. Then, a two-level class hierarchy was constructed combining the Nearest-Neighbor Classifier and the Fuzzy logic classifier. After classification, we created two abstract classes (tree and non-tree) and selected Error Matrix Based on Samples to perform accuracy assessment for tree coverage mapping. The result of accuracy assessment showed that the proposed method had produced 96.4% overall accuracy and 92.6% KIA. Finally, we calculated the tree coverage rate based on the statistical result of sum area of tree coverage classification.

In the paper, we adopted an object-oriented image analysis method to detect and classify road vehicles from airborne color digital orthoimagery at a ground pixel resolution of 20cm. Firstly; a vector-generated road mask was used to constrain detection and classification of vehicles to road region. Secondly, image segmentation and edge detection algorithms were performed to separate vehicles from the background in the road region. Then, a fuzzy logic classifier was constructed to classify the extracted object regions into the vehicle and the non-vehicle regions by using the feature information of image objects. Finally, based on the calculated average length and width of vehicles, we classified vehicles into three categories, that is, small, medium and big. And the counts of the three vehicle classes were derived. The automatic counts match manual counts very well.

Image fusion at pixel level without precise registration always causes pseudo colors and other problem. Classification-based fusion scheme can effectively eliminate the false color at the edge of objective. However, the traditional per-pixel classification results in the well-known salt and pepper effect. The only way to smooth the image is to use filters, while impacted on the result of fusion. This paper proposes a method consist of a sequential application of segmentation, classification and fusion techniques. First, the image was multi-resolutely segmented into homogenous areas, and classified it by using the membership functions classifier and additional empirical rules. Subsequently, according to the restriction of the precise classification result, adjusting the multi-spectral image then achieved the fusion by using HSV color transformation. Finally, after compared the statistical properties of the fusion result by different methods, the proposed method showed satisfied result. I. INTRODUCTION With the appearance of plentiful kinds of remote sensing imagery, fusion of satellite images of different spatial resolutions play an important role. Via image fusion, we can obtain more information than can be derived from single kind of image. Pohl prompted that according to the stage which image fusion is performed, there are pixel, feature and decision level. Image fusion at pixel level always was effected by the accuracy of registration, the number of mixed pixel and other factors. The pixel in high-resolution satellite image is smaller sizes and combined with fewer spectral bands that cause greater spectral variation within a class and a greater degree of shadow. Hence, color break and pseudo colors often occur at the edge of object and shadow which fusing the high-resolution image only at pixel levels. During the high-resolution image fusion, for eliminating color break and pseudo colors, using its classification image as the prior knowledge and restricting the fusion area can take full advantage of spectral information from multi-spectral bands and texture information come from pan band to realize the image fusion. It's a method of image fusion that performing at pixel level and integrate with feature level fusion. In this way, phenomenon of pseudo colors can be avoided. In this paper, we propose an image fusion method based on object-oriented classification. Via image segmentation, feature extraction and image fusion based on object-oriented classification, the fusion image can be achieved. In this method, object-oriented classification more appropriate for high-resolution image to get accuracy classification result and overcoming the limit of per-pixel image analyses. Because much information is acquired in the relationship between adjacent pixels, including texture and shape information, which allows for identification of individual objects as oppose to single pixels

A wavelet transform based method for road extraction is introduced. It characterizes the edges of roads in high-resolution remotely sensed images through their multi-scale wavelet transforms. Road networks are extracted efficiently from the images.

In this paper, a new procedure is proposed for land cover classification in a mountainous area using data derived from a stereo pair of RADARSAT images. Land cover classifications using the RADARSAT tonal and textural information and ancillary terrain data were evaluated. All the derived data were from the same source of the stereo pair of the RADARSAT images. An artificial neural networks (ANN) classifier is applied. The performance of the proposed method was evaluated over a mountainous study area in Southern Argentina. The results showed that the extra information, texture and DEM, extracted from the RADARSAT images can greatly improve the accuracy of classification using ANN. It can be concluded that RADARSAT images and terrain data derived from the RADARSAT images are valuable data sources for land cover mapping, especially in the mountainous areas where optical satellite data and DEM data are not always available.

The city of Beijing is going through a rapid developing period, both in the suburbs and inside the old city. To detect the buildings developed in and around the city at present, Landsat-7 ETM+ and SPOT panchromatic imagery of 2001 were collected. To make use of higher spatial resolution of the SPOT panchromatic imagery and higher spectral resolution of the ETM+ imagery, the two data sources were fused. To reduce the confusion between urban built-up areas and non built-up areas, an unsupervised classification was performed first. Agricultural and large urban green and open areas such as parks and lakes were separated from other built-up areas. Major roads were mapped from ETM+ band8. Buildings were then extracted from the SPOT PAN imagery within the built-up areas using a set of proposed high-pass filters. Traditional Chinese-style houses, which are small in size and unidentifiable individually from the satellite imagery, were not detected. Our result shows that many medium-to-large buildings of regular arrangement can be mapped from the fused dataset. The buildings extracted from the satellite imagery can provide useful information for urban change detection and environmental management.

Presents some new techniques of spectral and spatial decorrelation in lossless data compression of remotely sensed imagery. These techniques provide methods to efficiently compute the optimal band combination and band ordering based on the statistical properties of Landsat-TM data. Experiments on several Landsat-TM images show that using both the spectral and the spatial nature of the remotely sensed data results in significant improvement over spatial decorrelation alone. These techniques result in higher compression ratios and are computationally inexpensive.>

Visual interpretation of high-resolution satellite data has been useful for mapping linear features, such as roads and updating land-use changes. However, it would be beneficial to map new road networks digitally from satellite data to update digital databases using semi-automated techniques. In this paper, an algorithm called Gradient Direction Profile Analysis (GDPA) is used to extract road networks digitally from SPOT High Resolution Visible (HRV) panchromatic data. The roads generated are compared with a visual interpretation of the SPOT HRV multispectral and panchromatic data. The technique is most effective in areas where road development is relatively recent. This is due to the spectral consistency of new road networks. As new road networks are those of most interest to the land manager, this is a useful technique for updating digital road network files within a geographical information system of urban areas.