Search

Synthetic aperture radar (SAR) image intelligence interpretation is always a challenging task due to its special imaging mechanism. This article focuses on the aircraft detection and recognition in large-scale SAR images. The objects in large-size SAR images are usually sparsely distributed and tend to be highly concentrated in certain areas. Therefore, the detection and classification in SAR images are affected easily by the imaging environment, leading to ineffective and instability. It suffers from time-consuming, high false-alarm rate, and low recognition rate. To alleviate these problems, a joint probability detector integrated with scattering attention (SA) is designed for aircraft detection and classification. Based on the fact that all aircraft are parked in the airport area, an airport detection method with mixed strategy is proposed to obtain the valid region (airport), narrowing down the scope of detection area, increasing the detection efficiency, as well as suppressing a lot of false alarms outside the airport. Considering that it is easy to generate false alarms within the airport on account of clutter scattering interference, a two-stage detector is introduced to improve the accuracy by replacing a stronger region proposal network and optimizing a lower bound to a joint probabilistic objective over two stages. Furthermore, the classification encoder module incorporates SA into a convolution neural network to leverage the distribution relation among strong scattered points to enhance the classification performance. Finally, extensive experiments on the Zhong Ke Xing Tu (ZKXT) and GaoFen-3 datasets verify the effectiveness and superiority of the proposed approach, and surpass runner up by 5.3% with the mF1 indicator. On a large GaoFen3 image (16 550 × 11 945 pixels), the proposed method improves the detection speed by 187.52%, without sacrificing the accuracy.

With the rapid development and widespread deployment of radar technology, the interpretation of the vast amount of synthetic aperture radar (SAR) imagery obtained daily has emerged as a hot topic. The complexity of the electromagnetic scattering mechanisms contained within radar images makes SAR image interpretation a challenging task. Current methodologies for SAR image interpretation primarily involve feature extraction-based techniques, categorized into image-domain and frequency-domain algorithms. However, these methods are faced with issues, such as rough segmentation in images, high-computational complexity, and poor robustness, presenting significant challenges in the field. In this article, a novel framework for SAR image interpretation is proposed, leveraging reinforcement learning (RL) for the extraction of electromagnetic scattering features and the inversion of parameters. Within this framework, a nonsparse reward function, combined with curriculum learning, is introduced as the supervisory information. It enables more efficient policy updates through a structured two-stage training approach. In addition, an algorithm that integrates a four-neighbor breadth-first search (BFS) with the watershed segmentation process is proposed, aiming to enhance the accuracy of scattering center analysis in SAR imagery. The attribute scattering center model (ASCM) is utilized as a prototype for conducting algorithmic research and experimentation. Experimental results on both simulation data and measured data have indicated that the proposed method significantly improves efficiency while ensuring accuracy, demonstrating its capability to extract parameters from measured data in most scenarios.

Amidst the landscape of contemporary remote-sensing (RS) technology, the endeavor to detect and recognize aircraft within RS images (RSIs) assumes pivotal strategic and practical significance. The complex nature of fine-grained aircraft recognition is a result of the intricate interplay between aircraft and their background environments, alongside category imbalance, which collectively leads to the emergence of a long-tail distribution within the dataset. However, experts proficient in RSI interpretation can effectively address these challenges through the application of prior knowledge. This article introduces the aircraft reasoning network (ARNet), a framework tailored for aircraft detection and fine-grained recognition in RSIs, building upon prior knowledge employed in expert interpretation. Specifically, the knowledge reasoning module (KRM) introduces a knowledge graph (KG) that incorporates both common and expert knowledge into the end-to-end network. Additionally, the network encompasses a spatial context module (SCM) and an airport facility relationship module (AFRM). These components facilitate highly accurate detection and recognition of fine-grained aircraft in diverse environmental contexts by employing adaptive prior knowledge reasoning and optimizing target spatial location. Furthermore, an independent aircraft component discrimination module (ACDM) distinguishes aircraft based on their predominant component features, contributing to improved classification performance in both the few-shot and easily confused categories. Moreover, this article introduces the AR-RSI dataset, a compilation of RSIs capturing fine-grained aircraft targets from diverse locations. The effectiveness and superiority of ARNet are exemplified by AR-RSI, achieving a minimum of 3.7% higher mean average precision (mAP) than the mainstream aircraft detection framework.

Superpixel analysis is showing great potential for high-resolution synthetic aperture radar (SAR) image change detection (CD), as it uses a larger detection granularity and enhances computational efficiency. However, some deficiencies still exist. It is difficult for previous methods to extract the complete change regions from cluttered backgrounds. Meanwhile, the local spatial correlation and structure consistency are not well represented. To address the above problems and achieve better separation of changed and unchanged superpixels in complicated scenarios, we design a novel unsupervised CD framework from the perspective of low-rank matrix decomposition (LRMD) theory. The entire framework is carried out in two stages. First, the $\ell _{1}$ -norm sparsity constraint LRMD model is constructed to decompose change features into a low-rank component associated with background and a sparse component representing changed regions. Then, the local spatial correlation and structure consistency constraint are explicitly modeled by introducing a Laplacian regularization term. The unified model smooths the local similarity superpixels and enlarges the distance between changed regions and the background in the feature subspace. In this stage, the saliency difference image (DI) is generated to indicate the change probabilities of each superpixel. Furthermore, a classification refining (CR) module is designed to learn the projection from the change feature matrix to the saliency DI, which can further fine-tune such obscure regions and boost the binary classification. Extensive experiments on five challenging datasets from the TerraSAR-X sensor demonstrate the effectiveness and superiority of the proposed method.

This paper describes our solution for the protein homology prediction task in KDD Cup 2004 competition. This task is modeled as a supervised learning problem with multiple performance metrics. Several key characteristics make the problem both novel and challenging, including the concept of data blocks and the presence of large-scale and imbalanced training data. These features make a naive application of the traditional classification algorithms infeasible. Our approach focuses on making full use of the abundant information within the blocks, and developing a new technique for reducing and balancing training data to make the support vector machine applicable to this kind of large-scale and imbalanced learning tasks.

Multimodal image fusion has recently garnered increasing interest in the field of remote sensing. By leveraging the complementary information in different modalities, the fused results may be more favorable in characterizing objects of interest, thereby increasing the chance of a more comprehensive and accurate perception of the scene. Unfortunately, most existing fusion methods tend to extract modality-specific features independently without considering intermodal alignment and complementarity, leading to a suboptimal fusion process. To address this issue, we propose a novel interactive generative adversarial network (IG-GAN), for the task of multimodal image fusion. IG-GAN comprises guided dual streams tailored for enhanced learning of details and content, as well as cross-modal consistency. Specifically, a details-guided interactive running-in module (GIR1) and a content-guided interactive running-in module (GIR2) are developed, with the stronger modality serving as guidance for detail richness or content integrity, and the weaker one assisting. To fully integrate multigranularity features from dual-modality, a hierarchical fusion and reconstruction branch is established. Specifically, a shallow interactive fusion (SIF) module followed by a multilevel interactive fusion (MIF) module is designed to aggregate multilevel local and long-range features. Concerning feature decoding and fused image generation, a high-level interactive fusion and reconstruction module (HRM) is further developed. In addition, to empower the fusion network to generate fused images with complete content, sharp edges, and high fidelity without supervision, a loss function facilitating the mutual game between the generator and two discriminators is also formulated. Comparative experiments with 14 state-of-the-art methods are conducted on three datasets. Qualitative and quantitative results indicate that IG-GAN exhibits obvious superiority in terms of both visual effect and quantitative metrics. Moreover, experiments on two RGB-IR object detection datasets are also conducted, which demonstrate that IG-GAN can enhance the accuracy of object detection by integrating complementary information from different modalities. The code will be available at https://github.com/flower6top.

The heat transfer characteristics of feedthrough flange under high alternating current excitation were investigated by three-dimensional finite element model. The correlations between the heat transfer behaviors and system parameters including applied current, ceramic thickness and working time were discussed comprehensively. A remarkable absorbed power beyond 100 W in flange would be produced by the electromagnetic field from wires. Under natural cooling condition, there is an obvious temperature rise about 40°C in the flange center after 10 min of current excitation. Three types of water cooling solutions acting on flange surface, e.g. line type, circle type and S type solutions, were proposed to reduce the flange temperature under high alternating current and long working time condition. By the S type water cooling mode, the best cooling effect can be achieved that the maximum temperature rise is about 20°C and the average temperature rise is less than 5°C.

This study introduces an innovative approach to hyperspectral imaging (HSI) classification by integrating convolution, recurrence, and self-attention mechanisms in a 3-D configuration. We address several challenges such as the 1) disruption of spectral continuity by traditional dimensionality reduction methods like PCA, 2) the overlooking of band-to-band continuous features in existing spatial-only 2-D multiscanning strategy, and 3) the limitations in model design by simply cascading recurrent neural networks (RNNs) with transformers for HSI analysis. Our solution involves three core components: 1) subband grouping with group-wise convolution for refined dimension reduction; 2) a novel cubed 3-D-multiscanning technique enabling thorough multidirectional analysis in both spectral and spatial domains; and 3) the development of a Cubic-Net framework with a specially designed segmented recurrent transformer (SRT). This SRT is tailored to effectively utilize spectral continuity along with spatial contextual features, overcoming common sequential data analysis challenges seen in RNNs and transformers. Furthermore, our feature fusion strategy successively integrates “short-term” and “long-term” SRT features, thereby enhancing the model’s ability to process both spectral and spatial features effectively. Experimental results from three public HSI datasets indicate our method’s improved performance over existing baselines and state-of-the-art methods. This research offers a new perspective on 3-D sequential HSI classification.

A supervised image decomposition algorithm is proposed in this study for human heart rate measurement under low-light environments. First, the comparative human face image pairs under different light intensities are captured, and special image capturing and matching algorithms are designed in this procedure. Then, a multilayer image decomposition network is constructed and trained to obtain the correlation of the images under different lighting intensities. Specifically, a loss function, including illumination loss, illumination smoothness loss, and interframe loss, is designed for network optimization. A heart rate measurement algorithm runs at last for the calculation of heart rate. Verification experiments under different human-camera distances and light intensities confirm the effectiveness of the proposed method. Specifically, the proposed method can be used for stale and effective human heart rate measurement when the human–camera distance is within 0.8 m and the light intensity is higher than 400 lux.

Benefiting from deep learning, defocus blur detection (DBD) has made prominent progress. Existing DBD methods generally study multiscale and multilevel features to improve performance. In this article, from a different perspective, we explore to generate confrontational images to attack DBD network. Based on the observation that defocus area and focus region in an image can provide mutual feature reference to help improve the quality of the confrontational image, we propose a novel mutual-referenced attack framework. Firstly, we design a divide-and-conquer perturbation image generation model, where the focus region attack image and defocus area attack image are generated respectively. Then, we integrate mutual-referenced feature transfer (MRFT) models to improve attack performance. Comprehensive experiments are provided to verify the effectiveness of our method. Moreover, related applications of our study are presented, e.g., sample augmentation to improve DBD and paired sample generation to boost defocus deblurring.

Remote sensing datasets pose long-tailed data distribution, and such unbalanced datasets will reduce the performance of existing remote sensing object classification models. Existing methods mainly rely on resampling datasets, modifying loss functions, data augmentation, and transfer learning to cope with such challenges. Unlike these, our study takes a novel perspective and focuses on mitigating the long-tailed distribution problem by generating a large number of tail-class images with consistency and diversity. Specifically, this article introduces a novel text-guided tail-class generation network (TGN). TGN comprises two main components: knowledge mutual distillation network (KMDN) and class-consistent diverse tail-class generation network (CDTG). KMDN resolves the isolation issue of the head and tail knowledge by facilitating mutual learning of feature representations between the head and tail data, thereby improving the feature extraction capability of the tail model. CDTG focuses on generating class-consistency diverse tail-class images that uses tail-class features extracted by KMDN. Especially, the class consistency is guaranteed by contrastive language-image pre-trainings (CLIP’s) powerful text-image alignment capability. These generated images are then added back into the original dataset to alleviate the long-tailed distribution, thereby improving the tail-class accuracy. Extensive experiments on the widely used DIOR, FGSC-23 and DOTA datasets demonstrate that the proposed method outperforms state-of-the-art methods. Dataset and code are publicly available at https://github.com/XinR-Tang/TGN.

In this work, a novel semi-supervised twin neural network (semiTNN)-based post-equalizer (PE) is proposed and developed for high-speed 4-level pulse amplitude modulation (PAM4) underwater wireless optical communication (UWOC). Furthermore, semiTNN is enabled by a dual-drop strategy and interleaved consistency regularization (ICR), thereby only requiring a small amount of labeled PAM4 symbols as references to be well-trained. The experimental results over a 14-m/4-Gbps underwater link reveal that the proposed semiTNN PE paired with ICR, with only 5% labeled data, can achieve nearly the same bit error rate (BER) performance as the one trained by a fully-supervised learning process, resulting in 0.8-dB and 4.9-dB sensitivity improvements comparing with the traditional Volterra nonlinear equalizer (VNE) and linear feedforward equalizer (FFE) at a specific BER of 1 × 10−3, respectively. When the transmission distance is further extended to 56 m, the semiTNN PE with 10% labeled data can reach a data rate up to 4.26 Gbps under the hard-decision forward error correction (HD-FEC) threshold, which is 90 Mbps and 150 Mbps larger than that of VNE and FFE, respectively. Moreover, even facing bias-current fluctuations, turbulence, and bubbles, the UWOC systems supported by the semiTNN can still maintain a satisfying BER performance to some extent. This is the first time to utilize the proposed semiTNN PE combined with an ICR-based loss function for high-speed UWOC, and it can be highly beneficial to the practical deployment of NN-based PEs in the future.