Passive object detectors, trained on large-scale static datasets, often overlook the feedback from object detection to image acquisition. Embodied vision and active detection mitigate this issue by interacting with the environment. Nevertheless, the materialization of activeness hinges on resource-intensive data collection and annotation. To tackle these challenges, we propose a collaborative student-teacher framework. Technically, a replay buffer is built based on the trajectory data to encapsulate the relationship of state, action, and reward. In addition, the student network diverges from reinforcement learning by redefining sequential decision pathways using a GPT structure enriched with causal self-attention. Moreover, the teacher network establishes a subtle state-reward mapping based on adjacent benefit differences, providing reliable rewards for student adaptively self-tuning with the vast unlabeled replay buffer data. Additionally, an innovative yet straightforward benefit reference value is proposed within the teacher network, adding to its effectiveness and simplicity. Leveraging a flexible replay buffer and embodied collaboration between teacher and student, the framework learns to see before detection with shallower features and shorter inference steps. Experiments highlight significant advantages of our algorithm over state-of-the-art detectors. The code is released at https://github.com/lydonShen/STF.

Content-based video retrieval aims to retrieve near-duplicate entries from a database of a given query video. It plays an important role in combating video piracy. Robustness to video temporal dynamics is crucial for a representation model in video retrieval, as frames extracted from two copied videos are hardly temporally aligned in actual situations. However, current image retrieval datasets have difficulty in evaluating this robustness. To address this issue, we collect Similar Frame Dataset (SFD), which consists of 32,923 query-target pairs with 128,240 distraction images. The task of SFD is to retrieve the target frame from all items given a query frame. SFD is constructed by sampling frames from Kinetics-700 action classification dataset. An object detection model (Faster R-CNN) and a Multimodal Large Language Model (BLIP2) are used during sampling to select those valid frames. Besides, we propose Adjacent Frames Contrastive Learning (AFCL) framework. In AFCL, adjacent frames are sampled from unlabeled videos as positive pairs. An image representation model with robustness to changing frames can be trained under AFCL framework and achieve the state-of-the-art performance on SFD. The code will be released at https://github.com/Chuan-shanjia/Similar-Frame-Dataset.

With the emergence of diffusion models, the image generation has experienced a significant advancement. In super-resolution tasks, diffusion models surpass generative adversarial network (GAN)-based methods in generating more realistic samples. However, these models come with significant costs: denoising networks rely on large U-Net, making them computationally intensive for high-resolution (HR) images, and the extensive sampling steps in diffusion models lead to prolonged inference time. This complexity limits their application in remote sensing, due to the high demand for high-resolution images in such scenarios. To address this, we propose a lightweight diffusion model (LWTDM), which simplifies the denoising network and efficiently incorporates conditional information using a cross-attention-based encoder–decoder architecture. Furthermore, LWTDM serves as the pioneering model that incorporates the accelerated sampling technique from denoising diffusion implicit models (DDIMs). This integration involves the meticulous selection of sampling steps, ensuring the quality of the generated images. The experiments confirm that LWTDM strikes a favorable balance between precision and perceptual quality, while its faster inference speed makes it suitable for diverse remote sensing scenarios with specific requirements. The source code is available at:https://github.com/Suanmd/LWTDM.

In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and heavily relying on high-quality downstream data. Recently, prompt-based learning, which adds the task-relevant prompt to adapt the pre-trained models to downstream tasks, has drastically boosted the performance of many natural language downstream tasks. In this work, we extend this notable transfer ability benefited from prompt into vision models as an alternative to fine-tuning. To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt diverse frozen pre-trained models to a wide variety of downstream vision tasks. The key to Pro-tuning is prompt-based tuning, i.e., learning task-specific vision prompts for downstream input images with the pre-trained model frozen. By only training a small number of additional parameters, Pro-tuning can generate compact and robust downstream models both for CNN-based and transformer-based network architectures. Comprehensive experiments evidence that the proposed Pro-tuning outperforms fine-tuning on a broad range of vision tasks and scenarios, including image classification (under generic objects, class imbalance, image corruption, natural adversarial examples, and out-of-distribution generalization), and dense prediction tasks such as object detection and semantic segmentation.

Humans are proficient at continuously acquiring and integrating new knowledge. By contrast, deep models forget catastrophically, especially when tackling highly long task sequences. Inspired by the way our brains constantly rewrite and consolidate past recollections, we propose a novel Bilateral Memory Consolidation (BiMeCo) framework that focuses on enhancing memory interaction capabilities. Specifically, BiMeCo explicitly decouples model parameters into short-term memory module and long-term memory module, responsible for representation ability of the model and generalization over all learned tasks, respectively. BiMeCo encourages dynamic interactions between two memory modules by knowledge distillation and momentum-based updating for forming generic knowledge to prevent forgetting. The proposed BiMeCo is parameter-efficient and can be integrated into existing methods seamlessly. Extensive experiments on challenging benchmarks show that BiMeCo significantly improves the performance of existing continual learning methods. For example, combined with the state-of-the-art method CwD [55], BiMeCo brings in significant gains of around 2% to 6% while using 2x fewer parameters on CIFAR-100 under ResNet-18.

The landslide detection methods using remote sensing images are mostly based on the traditional convolutional neural network model with high depth and complexity. The paper proposes a lightweight method based on Depth Separable Convolution and Double Self-Attention Mechanism (DSC-DSAM) for detecting landslides in remote sensing images. This method aims to reduce storage space and improve detection speed while maintaining accuracy. In our model, it starts with using a lightweight convolutional neural network model. Then, the dual self-attention mechanism is applied to improve the accuracy. The proposed method is compared with other existing classification models, and it is shown to have advantages in memory space and detection speed while maintaining accuracy.

Bi-temporal semantic change detection(SCD) is more sophisticated than binary change detection and it provides more detailed changing information with categories. Naturally, it is more challenging than traditional binary change detection. In this paper, a Siamese CNN is proposed for SCD. For the problems of complex backgrounds of remote sensing images, we use multiscale context information and correlation to enhance SCD performance. For the problem of insufficient feature utilization between subtasks, a channel fusion module is proposed to explore the temporal correlation between bi-temporal images, which benefits the extraction of the final changing map. The experiments in this paper are conducted on the SECOND dataset. Our proposed method outperforms compared methods and obtains more completed changing maps than other methods.

High-Efficient landslide recognition on remote sensing images is of great importance to hazard monitoring. In this paper, we introduce MobileL-K, a light Convolutional neural networks(CNNs) to achieve highly efficient landslide recognition. In this network, the depthwise separable convolutions with a large kernel is borrowed to exploit global features on an image. Moreover, an improved EC-based network pruning method was proposed based on continual masking. We prune the MobileL-K to apply to landslide recognition. The experiment results on a benchmark dataset show that proposed method outperforms other compared methods with smaller model size, less FLOPs and higher running speed on GPU.

It is challenging to perform robust road detection on remote sensing images in a complex scene with occlusions by plants and buildings. In this paper, an elaborate dual-decoded U-Net combined with atrous spatial pyramid pooling is proposed to tackle this scenario. In the proposed network, a dual-decoder structure is designed, where a small decoder aims to extract the attention information and it is delivered to the other decoder to enhance the context. Finally, the proposed method is verified on the DeepGlobe dataset. The experiment results demonstrate that the proposed method outperforms other compared methods.

Water area segmentation in remote sensing images is of great importance for flood monitoring. Convolutional neural networks have been successfully applied to various computer vision tasks. Among them, a U-shaped CNN known as U-Net achieves state-of-the-art performance on various types of image segmentation, including remote sensing images. However, there are still some difficulties in the water area segmentation of remote sensing images, such as complex backgrounds, cloud shading, and rough edges. In this work, we propose a multi-branch fusion U-Net (MFU-Net) method for water area segmentation with multi-modality remote sensing images. The experimental results showed that our MFU-Net can effectively and efficiently segment water area from Sentinel-1 and Sentinel-2 images, which F1, IoU and PA on the Sen1Floods11 dataset are 91.462%, 84.598% and 98.123%, respectively.

Change detection of high resolution remote sensing images is more attractive, since it can not only identify areas of changes, but also identify types of changes. In this context, simultaneous change detection and semantic segmentation are natural and necessary. However, traditional methods put less emphasis on the cooperation of the above two tasks. In this paper, a novel method is proposed to realize the collaborative learning of change detection and semantic segmentation. By elaborately exploring the relevance and consistency between change detection and semantic segmentation, the proposed method synchronously enhanced feature separability of two tasks, and it outperformed a single change detection network or semantic segmentation network. Specifically, the proposed approach extracts multi-level bi-temporal features by a backbone network, followed by two layer-by-layer decoders for learning change features and semantic features. On the one hand, the Interactive Fusion Module(IFM) fuses the changing features and semantic features together to increase the collaboration between the two tasks. On the other hand, the contrastive loss enhances the constraints between the two tasks. The advantages of the proposed method are demonstrated with respect to change region detection and change type identification.

In single image super-resolution (SISR), although PSNR is a key metric for signal fidelity, images with high PSNR do not necessarily render high visual quality. As a result, current perception-driven SISR methods employ perceptual metrics close to the human eye to measure the quality of the generated images. Unfortunately, the perceptual loss and adversarial loss, widely used by the perception-driven SISR methods, still underperform on these non-differentiable perceptual metrics. To this end, we propose a generic multi-scale perceptual loss, i.e., the patch loss, which can be easily plugged into off-the-shelf SISR methods to improve a broad range of perceptual metrics. Specifically, the proposed patch loss minimizes the multi-scale similarity of image patches and enhances the restoration of regions with complex textures and sharp edges via parameter-free adaptive patch-wise attention. Our proposed patch loss introduces more realistic details compared to the perceptual loss and fewer artifacts compared to the adversarial loss.

Training Deep Neural Networks (DNNs) is inherently subject to sensitive hyper-parameters and untimely feedbacks of performance evaluation. To solve these two difficulties, an efficient parallel hyper-parameter optimization model is proposed under the framework of Deep Reinforcement Learning (DRL). Technically, we develop Attention and Memory Enhancement (AME), that includes multi-head attention and memory mechanism to enhance the ability to capture both the short-term and long-term relationships between different hyper-parameter configurations, yielding an attentive sampling mechanism for searching high-performance configurations embedded into a huge search space. During the optimization of transformer-structured configuration searcher, a conceptually intuitive yet powerful strategy is applied to solve the problem of insufficient number of samples due to the untimely feedback. Experiments on three visual tasks, including image classification, object detection, semantic segmentation, demonstrate the effectiveness of AME.

A novel change detection approach is proposed in this paper, which is based on dual task learning model and unchanged area loss-function(UAL). Dual task model combines change detection(CD) and semantic segmentation(SS) based on Siamese neural network to improve the feature separability, and UAL aims to establish the semantic label correspondence within unchanged regions. Experiments demonstrate the effectiveness and advantages of the proposed approach. Our code and models are available at https://github.com/Chuan-shanjial/A-loss-function-for-change-detection.

Remote Sensing Images Change Detection (RSICD) aims to locate the changed regions between bitemporal very-high-resolution (VHR) sensing images. However, existing deep learning-based RSICD methods are from the requirements by practical application, mainly due to the low feature discrim-ination and limited accuracy. We propose a novel multi-task and multi-temporal encoder-decoder changed detection net-work (MMNet) for VHR images, which accomplished both semantic segmentation and change detection at the same time. The encoder extracts multi-level contextual information, which contains two semantic segmentation branches (SSB) and a change detection branch (CDB). In this way, change representation constrains semantic representation during training, which introduces a novel loss function to en-sure the semantic consistency within the unchanged regions. Furthermore, to utilize multi-level feature representation for enhancing the separability of features, a multi-scale feature fusion module (MFFM) is presented.

VHR(Very High Resolution) image change detection is a hot topic in remote sensing. With the development of deep learning, change detection performances have been improved significantly. However, the data imbalance between the unchanged class and the changed class as well as the data imbalance between different change types greatly impacts the network training process and the final performance. To address this problem, a novel method is proposed in this paper based on dual network structure and cumulative learning strategy. With the help of dual network structure, the deep learning network is more robust in balancing unchanged class and changed class. By cumulative learning, the network training procedure is more stable. Extensive experiments demonstrate the effectiveness of the proposed method on a variety of change detection datasets and existing change detection frameworks.

Semantic segmentation plays an important role in very high resolution (VHR) image understanding. Despite the potentials of the deep convolutional network in improving performance by end-to-end feature learning, each model has its limitations, and it is hard to discriminate complex features purely by a single model. Ensemble learning is promising for integrating the strengths of different models, however, the ensemble of deep models is challenging due to the huge amount of parameters and computation of the deep model itself as well as the difficulty in capturing complementarity between different models. To tackle these problems, a head-level ensemble network (HENet) is proposed in this letter, which reduces model complexity by sharing feature extraction networks and improves complementarity between models by novel cooperative learning (CL). Experiments on ISPRS 2-D semantic labeling benchmark demonstrate the effectiveness and advantage of the proposed method.

Detecting ships from synthetic aperture radar (SAR) images is inherently subject to its imaging mechanism. With the development of deep learning, advanced learning-based techniques have been migrated from optical images to SAR images. However, the default hyperparameters (e.g., learning rate, size of the anchor box) predefined by a heuristic strategy on optical images might be suboptimal for SAR datasets. In addition, the low-quality imaging in SAR images further reduces the portability of hyperparameters. To solve this problem, a new optimization method, named reinforcement learning and hyperband (RLH), is proposed to dynamically learn hyperparameter configurations by deep reinforcement learning (DRL), where a neural network is adopted to capture the relationship between different configurations and predict new configurations to further improve the performance. Hyperparameter configuration is able to be automatically learned to accommodate various SAR image datasets, and experiments on two SAR image datasets demonstrate the effectiveness and advantage of the proposed approach.

Exploiting convolutional neural networks for point cloud processing is quite challenging, due to the inherent irregular distribution and discrete shape representation of point clouds. To address these problems, many handcrafted convolution variants have sprung up in recent years. Though with elaborate design, these variants could be far from optimal in sufficiently capturing diverse shapes formed by discrete points. In this paper, we propose PointSeaConv, i.e., a novel differential convolution search paradigm on point clouds. It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling. We also propose a joint optimization framework for simultaneous search of internal convolution and external architecture, and introduce epsilon-greedy algorithm to alleviate the effect of discretization error. As a result, PointSeaNet, a deep network that is sufficient to capture geometric shapes at both convolution level and architecture level, can be searched out for point cloud processing. Extensive experiments strongly evidence that our proposed PointSeaNet surpasses current handcrafted deep models on challenging benchmarks across multiple tasks with remarkable margins.

Object monitoring can be performed by change detection algorithms. However, for the image pair with a large perspective difference, the change detection performance is usually impacted by inaccurate image registration. To address the above difficulties, a novel object-specific change detection approach is proposed for object monitoring in this paper. In contrast to traditional approaches, the proposed approach is robust to view angle variation and does not require explicit image registration. Experiments demonstrate the effectiveness and advantages of the proposed approach.

In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and detection performance, and do not take into account the importance of detection performance feedback for improving image quality. Therefore, detection performance is limited by the passive nature of the conventional object detection framework. In order to solve the above limitations, this paper takes adaptive brightness adjustment and scale adjustment as examples, and proposes an active object detection method based on deep reinforcement learning. The goal of adaptive image attribute learning is to maximize the detection performance. With the help of active object detection and image attribute adjustment strategies, low-quality images can be converted into high-quality images, and the overall performance is improved without retraining the detector.

Pixel-level classification for very high resolution (VHR) images is a crucial but challenging task in remote sensing. However, since the diverse ways of satellite image acquisition and the distinct structures of various regions, the distributions of the same semantic classes among different data sets are dissimilar. Therefore, the classification model trained on one data set (source domain) may collapse, when it is directly applied to another one (target domain). To solve this problem, many adversarial-based domain adaptation methods have been proposed. However, these methods only consider the source and the target domains independently in the adversarial training, where only the target domain is explicitly contributed to narrow the gap between the distributions of both domains. Unlike previous methods, we propose a triplet adversarial domain adaptation (TriADA) method that jointly considers both domains to learn a domain-invariant classifier by a novel domain similarity discriminator. Specifically, the discriminator takes a triplet of segmentation maps as input, where two segmentation maps from the same domain are to be distinguished from the two maps from the different domains during the adversarial learning. Consequently, it explicitly considers both domains' information to narrow the distribution gap across domains. To enhance the discriminability of the classifier on the target domain, a class-aware self-training strategy, which depends on the output of the discriminator, is proposed to assign pseudo-labels with high adapted confidence on target data to retrain the classifier. Extensive experiments on several VHR pixel-level classification benchmarks demonstrate the effectiveness of our method as well as its superiority to the-state of the art.

State-of-the-art object detection methods based on deep learning achieved promising performances in recent years. However, the performances are limited by the passive nature of the traditional object recognition framework in ignoring the relationship between imaging configuration and recognition performance as well as the importance of recognition performance feedback for improving image quality. To address the above limitations, an active object recognition method based on reinforcement learning is proposed in this paper by taking adaptive brightness adjustment as an example. Progressive brightness adjustment strategy is learned by maximizing recognition performance on reference high-quality training samples. With the help of active object recognition and brightness adjustment strategy, low-quality images can be converted into high-quality images, and overall performances are improved without retraining the detector.

Object detection of high-resolution optical remote sensing images is challenging due to two fundamental problems. One is the huge scale variation of objects in images, e.g., small vehicle and cross-sea bridge. The other one is the objects could take on arbitrary orientations because of the high angle shot. In this paper, we propose a Rotation and Scale-invariant Detector (RS-Det) for remote sensing images to solve the above problem in an unified network. Specifically, RS-Det consists of a deformable convolution module to learn spatial transformation (such as rotation, transition, etc) and a feature pyramid architecture for multi-scale feature representation. These two modules enable a better feature learning of convolutional neural network and boost the performance by 3.6% compared with the baseline method. In DOTA, a large-scale dataset for aerial image object detection, our RS-Det achieves the state-of-the-art accuracy, which verifies our method's superiority.

Remote sensing image classification is challenging due to low separation between different classes and difficulty in learning discriminative features. GAN (Generative Adversarial Model) is promising for this task due to the generator in reproducing samples and the discriminator for improving the generator. Among GANs variants for image translation and image classification tasks, Pix2Pix performs best. However, Pix2Pix is limited in explicitly capturing the relationship between the source domain and the reconstructed ones from the target domain. To address the above problem, an improved Pix2Pix is proposed in this paper, where a controller is added to Pix2Pix whose role is to improve classification performance and enhance training stability. Experiments demonstrate the effectiveness and advantages of the proposed approach.

Online target recognition within time-sensitive space information networks is appealing for emergent applications. However, the contradiction between time-sensitive response requirement and resource constraints makes online target recognition challenging. To tackle this problem, an effective online target recognizing approach is proposed based on task-adapted hash metric learning. Hash metric learning improves the overall separability with low memory cost, and coupled hash learning recognizes targets online based on a small amount of training samples with the help of rich training samples collected on the historical tasks. Compared with traditional methods, the proposed approach is more promising for time-sensitive space information networks. The experiments demonstrate the effectiveness of the proposed approach.

Very high resolution image change detection is difficult due to the low interclass variability and the resulting high overlap between the changed class and the unchanged class. To address the above difficulties, the concept “relationship” is proposed to represent the intraclass similarity and interclass difference, which is established by interclass couples and intraclass couples. By relationship representation and relationship learning, intraclass couples can be compressed into a compact cluster, and the distances between interclass couples are enlarged. To better discover the complex relationship hidden in change features, relationship learning is integrated into a deep learning framework, where the relationship is learned progressively. In consequence, the final change detection performance is improved with the reduced overlap between the changed class and the unchanged class. Experiments demonstrate the effectiveness of the proposed approach.

Hashing-based semantic similarity search is becoming increasingly important for building large-scale content-based retrieval system. The state-of-the-art supervised hashing techniques use flexible two-step strategy to learn hash functions. The first step learns binary codes for training data by solving binary optimization problems with millions of variables, thus usually requiring intensive computations. Despite simplicity and efficiency, locality-sensitive hashing (LSH) has never been recognized as a good way to generate such codes due to its poor performance in traditional approximate neighbor search. We claim in this paper that the true merit of LSH lies in transforming the semantic labels to obtain the binary codes, resulting in an effective and efficient two-step hashing framework. Specifically, we developed the locality-sensitive two-step hashing (LS-TSH) that generates the binary codes through LSH rather than any complex optimization technique. Theoretically, with proper assumption, LS-TSH is actually a useful LSH scheme, so that it preserves the label-based semantic similarity and possesses sublinear query complexity for hash lookup. Experimentally, LS-TSH could obtain comparable retrieval accuracy with state of the arts with two to three orders of magnitudes faster training speed.

Hashing techniques with asymmetric schemes (e.g., only bi-narizing the database points) have recently attracted wide attention in the circle of image retrieval. In comparison with those methods which binarize simultaneously both of the query and database points, they not only enjoy the storage and search efficiencies, but also provide higher accuracy. Gearing to this line, this paper proposes a metric-embedded asymmetric hashing (MEAH) that learns jointly a bilinear similarity measure and binary codes of database points in an unsupervised manner. Technically, the learned similarity measure is able to bridge the gap between the binary codes and the real-valued codes, which are represented possibly with different dimensions. What is more, this measure is capable of preserving the global structure hidden in the database. Extensive experiments on two public image benchmarks demonstrate the superiority of our approach over the several state-of-the-art unsupervised hashing methods.

Due to the query effectiveness and efficiency, cross-modal similarity search based on hashing has acquired extensive attention in the multimedia community. Most existing methods do not explicitly employ the ranking information when learning hash functions, which is quite important for building practical retrieval systems. To solve this issue, this paper proposes a rank-order preserving hashing (RoPH) method with a novel regression-based rank-order preserving loss that has provable large margin property and is easy to optimize. Moreover, we jointly learn the binary codes and hash functions instead of using any relaxation trick. To solve the induced optimization problem, the alternating descent technique is adopted and each subproblem can be solved conveniently. Specifically, we show that the involved binary quadratic programming subproblem with respect to an introduced auxiliary binary variable satisfies submodularity, enabling us to use the off-the-shelf graph-cut algorithms to solve it exactly and efficiently. Extensive experiments on three benchmarks demonstrate that RoPH significantly improves the ranking quality over the state of the arts.

Very high resolution images are promising for detecting change regions and identifying change patterns. However, the low overall separability makes it difficult to discriminate change features. In this paper, a framework is proposed to simultaneously detect change regions and identify change patterns. A supervised approach is illustrated within this framework, which is aimed at reducing the overlaps between change classes by capturing the interclass difference and the intraclass similarity. Experiments demonstrate the effectiveness of the proposed approach.

Hashing is very effective for many tasks in reducing the processing time and in compressing massive databases. Although lots of approaches have been developed to learn data-dependent hash functions in recent years, how to learn hash functions to yield good performance with acceptable computational and memory cost is still a challenging problem. Based on the observation that retrieval precision is highly related to the kNN classification accuracy, this paper proposes a novel kNN-based supervised hashing method, which learns hash functions by directly maximizing the kNN accuracy of the Hamming-embedded training data. To make it scalable well to large problem, we propose a factorized neighborhood representation to parsimoniously model the neighborhood relationships inherent in training data. Considering that real-world data are often linearly inseparable, we further kernelize this basic model to improve its performance. As a result, the proposed method is able to learn accurate hashing functions with tolerable computation and storage cost. Experiments on four benchmarks demonstrate that our method outperforms the state-of-the-arts.

The traditional clustering approaches are limited for the unsupervised change detection of very high resolution images due to the multimodal distribution of change features. To overcome this difficulty, a sparse hierarchical clustering approach is proposed. Discriminative change features are generated by stacking bitemporal multiscale center-symmetric local binary pattern features. In order to explore the multimodal and hierarchical distribution of the change features, a tree-structured dictionary is learned from the pseudotraining set and the unlabeled data. The sparse reconstruction error, a more robust distance compared to the Euclidean distance, is used to determine the label of each change feature. Comparative experiments demonstrate the effectiveness of the proposed method.

Due to the complexity of very high resolution (VHR) images and the inaccurate correspondence, change feature extraction is the key difficulty of VHR image change detection. In this letter, change field is proposed to represent the complex changes between VHR images. Change field measures the complex changes based on the displacements and the compensated distance. Based on change field, a novel change detection approach is proposed, where the inter-class variability is improved and the changed class and the unchanged class can be separated effectively. Experiments demonstrate the effectiveness of the proposed approach.

The difficulty of Very High Resolution (VHR) image change detection is mainly due to the low separability between the changed and unchanged class. The traditional approaches usually address the problem by solving the feature extraction and classification separately, which cannot ensure that the classification algorithm makes the best use of the features. Considering this, we propose a novel approach that combines the feature extraction and the classification task by utilizing the sparse representation algorithm with discriminative dictionary. Experiments on real data sets show that our method achieves effective results.

Urban change detection of Very High Resolution (VHR) remote sensing images is challenging, due to the ill-posed nature of change detection problem, the inherent nature of VHR image, the complex morphology of urban scenes, etc. To address the above difficulties, a robust approach is proposed, which is based on discriminative local features, robust distance metric and novel multi-scale fusion strategy. By integrating these components synergistically, the proposed approach is superior to the traditional approaches in capturing semantic changes and removing the false changes. Comparative experiments demonstrate the effectiveness and advantages of the proposed approach.

In this letter, we propose a semisupervised context-sensitive technique for change detection in high-resolution multitemporal remote sensing images. This is achieved by analyzing the posterior probability of probabilistic Gaussian process (GP) classifier within a Markov random field (MRF) model. In particular, the method consists of two steps: 1) A semisupervised initialization exploits both labeled and unlabeled data based on a probabilistic GP classifier, and 2) an MRF regularization aims at refining the posterior probability by employing the spatial context information. In particular, both edge information and high-order potential are utilized in MRF energy function formulation. Experimental results obtained on real remote sensing multitemporal imagery data sets confirm the effectiveness of the proposed approach.

Although feature-based methods have been successfully developed in the past decades for the registration of optical images, the registration of optical and synthetic aperture radar (SAR) images is still a challenging problem in remote sensing. In this letter, an improved version of the scale-invariant feature transform is first proposed to obtain initial matching features from optical and SAR images. Then, the initial matching features are refined by exploring their spatial relationship. The refined feature matches are finally used for estimating registration parameters. Experimental results have shown the effectiveness of the proposed method.

A fast approach is proposed in this letter for large-size very high resolution image registration, which is accomplished based on coarse-to-fine strategy and blockwise scale-invariant feature transform (SIFT) matching. Coarse registration is implemented at low resolution level, which provides a geometric constraint. The constraint makes the blockwise SIFT matching possible and is helpful for getting more matched keypoints at the latter refined procedure. Refined registration is achieved by blockwise SIFT matching and global optimization on the whole matched keypoints based on iterative reweighted least squares. To improve the efficiency, blockwise SIFT matching is implemented in a parallel manner. Experiments demonstrate the effectiveness of the proposed approach.

A novel approach is presented for change detection of very high resolution images, which is accomplished by fast object-level change feature extraction and progressive change feature classification. Object-level change feature is helpful for improving the discriminability between the changed class and the unchanged class. Progressive change feature classification helps improve the accuracy and the degree of automation, which is implemented by dynamically adjusting the training samples and gradually tuning the separating hyperplane. Experiments demonstrate the effectiveness of the proposed approach.

This paper introduces a semi-supervised change detection method that exploits both labeled and unlabeled samples via Gaussian Process (GP). The proposed method is based on recent development in Gaussian Process classifier named NCNM [3]. NCNM is a probabilistic approach to learning a GP classifier in the presence of unlabeled data. It involves a novel transductive learning under a probabilistic framework. Experimental results obtained on two sets of multitemporal remote sensing images confirm the effectiveness of the proposed approach. It also proves that NCNM can compete seriously with the state-of-the-art support vector machines (SVM) classifier for remote sensing image change detection.

Usually changes in remote sensing images go along with the appearance or disappearance of some edges. In addition, pixels located along the edges are likely to weakly influenced by its neighborhood pixels, while pixels located far from the edges commonly have a tightly correlation among them. In this paper, we propose a novel change detection technique based on adaptive Markov Random Fields (MRFs) for high resolution satellite images with combined color and texture features. The technique is composed of two main steps: (1) the input images are marked with different region indexes by the combined color and edge features; (2) change maps are obtained under the MRF framework with alterable order of neighborhood and variable smooth weight coefficient controlled by the index map. The main contribution of this paper is that the spatial-contextual information included in the remote sensing imagery is correctly and adaptively exploited under an adaptive MRF framework. Experiments results obtained on a set of remote sensing imagery confirm the effectiveness of the proposed approach.

In this paper, we present an unsupervised change detection approach in temporal sets of SAR images. The change detection is represented as a task of energy minimization and the energy function is minimized using graph cuts. Neighboring pixels are taken into account in a priority sequence according to their distance from the center pixel, and the energy function is formed based on Markov Random Field (MRF) model. Graph cuts algorithm is employed for computing maximum a-posteriori (MAP) estimates of the MRF. Experiments results obtained on a SAR data set confirm the effectiveness of the proposed approach. The comparisons between graph cuts algorithm and iterated conditional modes (ICM) algorithm about the quality of change map and running time of energy minimization illustrate that graph cuts algorithm is a huge improvement over ICM.

A multilevel contextual approach is proposed in this paper for change detection of VHR images. By representing the change features in a hierarchical contextual manner, the changes are detected level-by-level. By taking advantages of SVMs, the ambiguity of changes is mitigated and the optimal changes are detected peculiar to the specific user. Compared to the traditional methods, the proposed approach is more accurate, more robust and faster. Experiments demonstrate the effectiveness and advantages of the proposed approach.

A multiscale approach is presented in this paper for urban change detection of VHR images. The proposed approach detects the changes at different scales by local-region-based approach, which consists of local region extraction, local region description and local region comparison. To combine the changes at different scales and improve the accuracy, multiscale fusion strategy is applied to local-region-based change detection. Experimental results obtained on Quickbird images confirm the effectiveness of the proposed approach.