In recent years, the application of autonomous aerial vehicle (AAV) devices in military, industrial, and civilian sectors has become increasingly widespread. Consequently, research on multi-AAV formation cooperative control strategies has garnered significant attention. However, current multiagent reinforcement learning algorithms often struggle with unguided exploration, making it challenging for agents to develop efficient action strategies for complex collaborative tasks. To address this issue, this article introduces a multicritic deep deterministic policy gradient (MCDDPG) algorithm. This algorithm designs a multicritic (MC) structure based on the DDPG algorithm. This structure guides AAVs using physical models for tracking and obstacle avoidance, while deep learning models are employed to facilitate cooperative coordination among AAVs. Furthermore, to address the weight allocation issue among different Critic modules in the MC structure, a dynamic difficulty priority weight optimization algorithm is implemented. This enhances the algorithm’s collaborative capabilities. To validate the collaborative planning capability of the proposed algorithm, a simulation scenario involving multicoupled tasks is designed in the multiagent particle environment (MPE). In this scenario, the MCDDPG algorithm demonstrates the fastest convergence speed and the optimal collaborative strategy, outperforming other state-of-the-art multiagent deep reinforcement learning (MADRL) algorithms currently in use.

Combining synthetic aperture radar (SAR) and optical images for geomorphic feature extraction offers a promising solution. However, the significant difference in data distribution between the two modalities poses a challenge for the fusion mechanism to achieve efficient segmentation. This letter presents a fusion modulation network based on state space model (SSM) (FMamba), designed for multimodal semantic segmentation tasks. The network can effectively fuse the complementary features of the two modalities to enhance the semantic features of the target regions. Specifically, FMamba integrates a dynamic fusion modulation module (DFMM) based on SSM at the encoding stage. This module dynamically fuses and modulates features from two different modalities to facilitate cross-modal feature extraction and semantic alignment. In the decoding phase, the final segmentation map is generated by progressively decoding and reconstructing the multiscale fusion features. Experimental results on the WHU-OPT-SAR and DFC2025 datasets demonstrate the superior semantic segmentation performance of the proposed method.

Abnormal behavior detection in surveillance video, as one of the essential functions in the intelligent surveillance system, plays a vital role in anti-terrorism, maintaining stability, and ensuring social security. Aiming at the problem of extremely imbalance between normal behavior data and abnormal behavior data, the probabilistic memory model-based network is designed to learn from the distribution of normal behaviors and guide the detection of abnormal behavior. An auto-encoding model is employed as the backbone network, and the gap between the predicted future frame and the real frame is used to measure the degree of abnormality. An autoregressive conditional probability estimation model and a normal distribution memory model are employed as auxiliary modules, to achieve the prediction of normal frames. When extracting temporal and spatial features in the backbone network, the causal three-dimensional convolution and time-dimension shared fully connected layers are used to avoid future information leakage and ensure the timing of information. In addition, from the perspective of probability entropy and behavioral modality diversity, autoregressive probability model is proposed to fit the distribution of input normal frame, so the network converges to the low entropy state of the normal behavior distribution. The memory module stores the feature of normal behavior in historical data, and injects the current input data. The memory vector and the encoding vector are concatenated along the time dimension and input to the decoder, realizing normal frame prediction. Using public datasets, ablation and comparison experiments show that the proposed algorithm has significant advantages in anomaly detection.

Personal belongings information (e.g., backpacks and reticules) and attribute descriptions (e.g., gender and age) provide critical discriminative cues for person re-identification (Re-ID) tasks. However, existing Re-ID algorithms leveraging additional semantic models often fail to accurately recognize personal belongings and suffer from noisy attribute predictions derived from global or local features, as they inadequately exploit attribute correlations. To address these challenges, we propose a novel person re-identification network, ReID-FSAI, which fuses personal belongings information and attribute descriptions from isolated semantic regions. ReID-FSAI integrates personal belongings areas identified through feature clustering with semantic parsing results from an auxiliary semantic model. By treating the generated semantic regions as body labels, our network refines global features into precise semantic features and accurately predicts attribute information from these regions. Furthermore, ReID-FSAI employs a reweighting model to enhance the confidence in specific attributes, improving attribute prediction accuracy. By combining predictions of attributes and personal belongings with global features, our approach significantly improves the representation ability of pedestrians. Experimental evaluations on the Market-1501 and DukeMTMC-reID datasets demonstrate that ReID-FSAI achieves superior performance in both person re-ID and attribute prediction, surpassing state-of-the-art methods.

Due to the intensity differences and speckle noise, automatic optical-synthetic aperture radar (SAR) image matching is still a challenging task. This letter addresses this problem by proposing a novel descriptor (MaskMIND) with three different modes using modality independent neighborhood information. This descriptor aims to sample and active relative structural information to improve accuracy and precision. In addition, the gradient maps are calculated respectively in pretreatment to eliminate noise. Then the corresponding metric, which takes into account the increasing positional uncertainty with distance, is defined using the sum of squared differences (SSD) accelerated by fast Fourier transform (FFT). Our methods are effective because of its relativeness and abstractness. The experimental results in five optical-SAR image pairs show that our methods have great performance and potentialities. Compared with CFOG, which is the state-of-the-art method, the accuracy of our sMaskMIND-grids is improved by 12% on average.

Due to the severe speckle noise and complex local deformation in synthetic aperture radar (SAR) images, robust pixelwise registration with high accuracy is an important problem but is far from being resolved. The core of this problem is how to establish a precise deformation field that maps every pixel to its corresponding pixel with high accuracy. To address this problem, a novel SAR dense-matching algorithm, which includes high-accuracy landmark generation and a precise deformation field parameter estimation, is proposed in this article. First, a strategy for generating enough well-distributed landmarks is proposed by designing patch matching of improved scale-invariant feature transform features based on phase correlation and the gradient method. Furthermore, a multiscale coherent point drift (MCPD), powered by iterative residual map minimization, is designed to reliably match landmarks and estimate precise field parameters. Both simulated deformed SAR images and real SAR images are utilized to evaluate the performance of the proposed method, and the experimental results demonstrate that the proposed method provides better registration performance than previous methods in terms of both accuracy and robustness.

In this paper, we present a multiclass data classifier, denoted by optimal conformal transformation kernel (OCTK), based on learning a specific kernel model, the CTK, and utilize it in two types of image recognition tasks, namely, face recognition and object categorization. We show that the learned CTK can lead to a desirable spatial geometry change in mapping data from the input space to the feature space, so that the local spatial geometry of the heterogeneous regions is magnified to favor a more refined distinguishing, while that of the homogeneous regions is compressed to neglect or suppress the intraclass variations. This nature of the learned CTK is of great benefit in image recognition, since in image recognition we always have to face a challenge that the images to be classified are with a large intraclass diversity and interclass similarity. Experiments on face recognition and object categorization show that the proposed OCTK classifier achieves the best or second best recognition result compared with that of the state-of-the-art classifiers, no matter what kind of feature or feature representation is used. In computational efficiency, the OCTK classifier can perform significantly faster than the linear support vector machine classifier (linear LIBSVM) can.

For remote sensing applications, automatic image registration is an essential part for further image processing such as image fusion, change detection and so on. In this paper, we propose an effective and fast automatic image registration based on both global and local method. In the first stage, we extract SIFT features and make the affine transformation with RANSAC, a robust outlier removal method. After the image globally registered, uniform spacing control points are selected in the common area. Through template matching, control points are refined and more local to the image. At last thin-plate spline, a nonrigid image registration transformation function is applied to achieve local matching. The experiment results indicate that this method not only distinctive and robust in overall registration but also significantly improve matching performance in local area1.

The generalized renewal process (GRP) has been widely used for modeling repairable systems under general repairs. Unfortunately, most of the related work does not provide closed-form solutions for predicting the reliability metrics of such systems, such as the expected number of failures, and the expected failure intensity, at a future point in time. A technical approach reported in literature is to conduct simulations to predict the reliability metrics of interest; however, simulations can be time-consuming. To reduce computational efforts for failure prediction, we propose an analytical approach that does not rely on simulations. Our idea is to predict the system's mean residual life based on its virtual age after each repair. The predicted mean residual life is then used to determine the expected time to the next failure. To illustrate this approach, we use a log-linear failure intensity function, and provide a detailed procedure for obtaining the maximum likelihood estimates (MLE) of the model parameters. A numerical study shows that this simple yet effective approach can provide failure predictions as accurate as the simulation alternative. We then demonstrate how the proposed approach can evaluate different maintenance strategies more efficiently compared to using simulations.

A novel land-cover classification framework for HR SAR images which combines low-level features and category context is presented in this paper. We use patch-based features for low-level information extraction, including average intensity, texture within a patch and the super texture we proposed to model the texture similarity of neighboring patches. To represent the local category context of SAR images, we propose the label layout filter. This work resolves local ambiguities of low-level features from a category context perspective. The framework demonstrates good performance in both accuracy and visual appearance for HR SAR scene interpretation.

In this paper, we improve the traditional bag-of-words-based image representation method in two aspects: preserving the semantics in vocabulary generation and incorporating spatial relations in image representation. Based on that, we present a novel context-aware information modeling method for high resolution synthetic aperture radar image scene interpretation. We compare the proposed method with traditional ones in scene interpretation on TerraSAR-X data sets.

In this paper, an unsupervised change detection method based on space contextual information and EM algorithm is proposed. In the algorithm, each pixel of the difference image is represented by a characteristic quantity constructed from the difference image values considering the space contextual information. EM algorithm is used to achieve the parameter estimation of each class pixels. Bayesian inference is then employed to perform the final change detection results. Experimental results obtained on multi-temporal optical images acquired by Landsat 5 TM confirm the effectiveness of the proposed approach.

This paper proposes a robust and fast matching method based on Normalized Cross Correlation (NCC) for Synthetic Aperture Radar (SAR) image matching. NCC is a robust algorithm in SAR image matching. Two main drawbacks of the NCC algorithm are the flatness of the similarity measure maxima, due to the self-similarity of the images, and the high computational complexity [1]. To tackle these two problems, we adopt the block partitioning strategy, texture feature analysis, and the Fast Fourier Transformation (FFT) algorithm and Integral Images to improve the performance of the conventional NCC algorithm. In the block partitioning strategy, we divide the template and the corresponding sub-window in the examined image into some sub-blocks, and there are several sub-blocks in the template, then we use texture features to increase the weight of sub-blocks which contain more terrain information in the template during the matching process, in this way we improve the flatness of the similarity measure maxima greatly. After that we use the FFT algorithm and Integral Images to speed up the proposed method, with the actual situation of our experiment we adopt the FFT and Integral Images based on the block partitioning strategy, thus we significantly reduce the number of computations required to carry out template matching based on the conventional NCC. Experimental results show that the proposed algorithm is more robust and faster than the conventional NCC algorithm.

In this paper, we propose a coarse-to-fine framework design and implementation for oil tank detection in optical satellite imagery. The framework is mainly composed of two operations: 1) from the whole scene imagery, extraction of patches with oil tanks based on the probabilistic latent semantic analysis model; 2) in the relatively small size patches, detection of the oil tanks with Hough transform and template matching. Experiments show that the framework provides a promising solution for oil tank detection in optical satellite imagery.

A novel segmentation algorithm for Synthetic Aperture Radar (SAR) images is presented in this paper to improve performance. First, we design a model of wavelet coefficients based on the relativities of the coefficients at different scales to sup press noise. Furthermore, we employ a weight-variant graph cuts-based approach to extract objects from complex back ground. Finally, we compare our proposed algorithms with several segmentation measures on synthetic and real SAR images and the experimental results demonstrate that the pro posed strategies have better performances in speckle suppression and image segmentation compared with other methods.

Wavelet image denoising has been well acknowledged as an important method of denoising in image processing. This paper describers a new method for the suppression of noise in image by fusing the wavelet denoising technique with support vector regression (SVR). Based on the least squares support vector machine (LS-SVM), a new denoising operators used in the wavelet domain are obtained. Simulated noise images are used to evaluate the denoising performance of the proposed algorithm along with the other wavelet-based denoising algorithm. Experimental results show that the proposed denoising method outperforms standard wavelet denoising techniques in terms of the signal-to-noise ratio and the prevented edge information in most cases. It also achieves better performance than the median filter.