检索结果-内蒙古大学图书馆

Graph Learning Model for Saliency Detection in Thermal Pedestrian Videos

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zheng, Yu Zhou, Fugen Li, Lu Sun, Changming Bai, Xiangzhi Image Processing Center Beihang University Beijing102206 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100083 China CSIRO Data61 PO Box 76 EppingNSW1710 Australia

Thermal imaging is becoming popular recently due to its all-weather and all-time capability. However, video saliency detection, an active topic in computer vision, has not been well studied for thermal videos. In this paper, we propose an effective saliency detection method for thermal pedestrian videos. Different from graph-based saliency detection methods with fixed graph structures, we introduce a saliency-guided graph learning model (SGL), which integrates a multi-view graph and saliency to achieve joint graph learning and saliency diffusion. We also propose an efficient video saliency detection approach for thermal pedestrian videos with SGL. Specifically, a proposal-based objectness descriptor is first integrated with motion saliency to obtain initial foreground and background probabilities. Then, a multi-view spatiotemporal graph is built to extract comprehensive inter-frame and intra-frame connections. Finally, optimal saliency could be obtained by an iterative optimization process. Besides, a challenging thermal pedestrian video dataset with 67 sequences and 1462 frames in total is built to compensate for the insufficient scale and complexity of existing datasets. Extensive experiments on a public dataset and our newly built dataset demonstrate the superior performance of our method compared to 11 state-of-the-art (SOTA) video saliency detection methods. © 2022, The Authors. All rights reserved.

关键词： Infrared imaging

Ab initio spatial coupled-mode theory of Fano resonances in optical responses of multilayer interference resonators

学校读者我要写书评

暂无评论

Physical Review A 2022年第2期106卷 023507-023507页

作者： Dmitry V. Nesterenko Shinji Hayashi Victor Soifer Diffractive Optics Laboratory Image Processing Systems Institute – Branch of the Federal Scientific Research Centre “Crystallography and Photonics” of Russian Academy of Sciences Samara 443001 Russia Institute of Informatics and Cybernetics Samara National Research University Samara 443086 Russia Department of Electrical and Electronic Engineering Graduate School of Engineering Kobe University Kobe 657-8501 Japan Optics and Photonics Center Moroccan Foundation for Science Innovation and Research (MAScIR) University Mohammed VI Polytechnic Rabat 10100 Morocco

To reveal origins of resonance characteristics of multilayer interference structures, we developed an ab initio spatial coupled-mode theory using the approximations of general electromagnetic theory of wave propagation in stratified media. In contrast to the conventional coupled-mode theory, the coefficients of developed coupled-mode models, which describe the Fano resonance behavior of interference field enhancement, are given by analytical functions of structural and optical parameters of the resonance systems. The results of analytical modeling of low- and high-loss resonator systems supporting waveguide, Fabry-Pérot, symmetric, and antisymmetric plasmonic normal modes agree very well with electromagnetic numerical simulations. We demonstrate also that the conventional spatial phenomenological coupled-mode theory is accurate only for low-loss structures.

关键词： Geometrical & wave optics Interference & diffraction of light Light propagation, transmission & absorption Near-field optics Waveguides Multilayer thin films Thin films Ab initio calculations Electromagnetic wave theory Mode coupling theory Rigorous coupled-wave analysis Transfer matrix method

Remote sensing image change detection with transformers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Hao Qi, Zipeng Shi, Zhenwei Image Processing Center School of Astronautics Beihang University Beijing100191 China Beijing Key Laboratory of Digital Media Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems School of Astronautics Beihang University Beijing100191 China

Modern change detection (CD) has achieved remarkable success by the powerful discriminative ability of deep convolutions. However, high-resolution remote sensing CD remains challenging due to the complexity of objects in the scene. Objects with the same semantic concept may show distinct spectral characteristics at different times and spatial locations. Most recent CD pipelines using pure convolutions are still struggling to relate long-range concepts in space-time. Nonlocal self-attention approaches show promising performance via modeling dense relations among pixels, yet are computationally inefficient. Here, we propose a bitemporal image transformer (BIT) to efficiently and effectively model contexts within the spatial-temporal domain. Our intuition is that the high-level concepts of the change of interest can be represented by a few visual words, i.e., semantic tokens. To achieve this, we express the bitemporal image into a few tokens, and use a transformer encoder to model contexts in the compact tokenbased space-time. The learned context-rich tokens are then feedback to the pixel-space for refining the original features via a transformer decoder. We incorporate BIT in a deep feature differencing-based CD framework. Extensive experiments on three CD datasets demonstrate the effectiveness and efficiency of the proposed method. Notably, our BIT-based model significantly outperforms the purely convolutional baseline using only 3 times lower computational costs and model parameters. Based on a naive backbone (ResNet18) without sophisticated structures (e.g., FPN, UNet), our model surpasses several state-of-the-art CD methods, including better than four recent attention-based methods in terms of efficiency and accuracy. Our code is available at https://***/justchenhao/BIT CD. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Geographical knowledge-driven representation learning for remote sensing images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Wenyuan Chen, Keyan Chen, Hao Shi, Zhenwei Image Processing Center School of Astronautics Beihang University Beijing100191 China Beijing Key Laboratory of Digital Media Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems School of Astronautics Beihang University Beijing100191 China

The proliferation of remote sensing satellites has resulted in a massive amount of remote sensing images. However, due to human and material resource constraints, the vast majority of remote sensing images remain unlabeled. As a result, it cannot be applied to currently available deep learning methods. To fully utilize the remaining unlabeled images, we propose a Geographical Knowledge-driven Representation learning method for remote sensing images (GeoKR), improving network performance and reduce the demand for annotated data. The global land cover products and geographical location associated with each remote sensing image are regarded as geographical knowledge to provide supervision for representation learning and network pre-training. An efficient pre-training framework is proposed to eliminate the supervision noises caused by imaging times and resolutions difference between remote sensing images and geographical knowledge. A large scale pre-training dataset Levir-KR is constructed to support network pre-training. It contains 1,431,950 remote sensing images from Gaofen series satellites with various resolutions. Experimental results demonstrate that our proposed method outperforms imageNet pre-training and self-supervised representation learning methods and significantly reduces the burden of data annotation on downstream tasks such as scene classification, semantic segmentation, object detection, and cloud / snow detection. It demonstrates that our proposed method can be used as a novel paradigm for pre-training neural networks. Codes will be available on https://***/flyakon/ Geographical-Knowledge-driven-Representaion-Learning. Copyright © 2021, The Authors. All rights reserved.

关键词： Object detection

学校读者我要写书评

暂无评论

有向动态网络的自发恢复（英文）

Engineering 2024年第6期 208-214页

作者：刘雪明闫贤 H.Eugene Stanley School of Artificial Intelligence and Automation & The MOE Engineering Research Center of Autonomous Intelligent Unmanned Systems & the Key Laboratory of Image Processing Huazhong University of Science and Technology Center for Polymer Studies Department of Physics Boston University

Complex networked systems, which range from biological systems in the natural world to infrastructure systems in the human-made world, can exhibit spontaneous recovery after a failure; for example, a brain may spontaneously return to normal after a seizure, and traffic flow can become smooth again after a jam. Previous studies on the spontaneous recovery of dynamical networks have been limited to undirected networks. However, most real-world networks are directed. To fill this gap, we build a model in which nodes may alternately fail and recover, and we develop a theoretical tool to analyze the recovery properties of directed dynamical networks. We find that the tool can accurately predict the final fraction of active nodes, and the prediction accuracy decreases as the fraction of bidirectional links in the network increases, which emphasizes the importance of directionality in network dynamics. Due to different initial states, directed dynamical networks may show alternative stable states under the same control parameter, exhibiting hysteresis behavior. In addition, for networks with finite sizes, the fraction of active nodes may jump back and forth between high and low states, mimicking repetitive failure-recovery processes. These findings could help clarify the system recovery mechanism and enable better design of networked systems with high resilience.

关键词：

Online Attentive Kernel-Based Temporal Difference Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification

学校读者我要写书评

暂无评论

Seq-Masks: Bridging the gap between appearance and gait mode...

IEEE Visual Communications and image processing (VCIP)

作者： Zhigang Chang Zhao Yang Yongbiao Chen Qin Zhou Shibao Zheng Institute of Image Processing and Network Engineering Shanghai Jiao Tong University Shanghai China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781728173221

Video-based person re-identification (Re-ID) aims to match person images in video sequences captured by disjoint surveillance cameras. Traditional video-based person Re-ID methods focus on exploring appearance information, thus, vulnerable against illumination changes, scene noises, camera parameters, and especially clothes/carrying variations. Gait recognition provides an implicit biometric solution to alleviate the above headache. Nonetheless, it experiences severe performance degeneration as camera view varies. In an attempt to address these problems, in this paper, we propose a framework that utilizes the sequence masks (SeqMasks) in the video to integrate appearance information and gait modeling in a close fashion. Specifically, to sufficiently validate the effectiveness of our method, we build a novel dataset named MaskMARS based on MARS. Comprehensive experiments on our proposed large wild video Re-ID dataset MaskMARS evidenced our extraordinary performance and generalization capability. Validations on the gait recognition metric CASIA-B dataset further demonstrated the capability of our hybrid model. Our codes and dataset MaskMARS will be open-sourced as a strong baseline.

关键词： Measurement Mars image recognition Codes Visual communication Surveillance Video sequences

Seq-Masks: Bridging the gap between appearance and gait modeling for video-based person re-identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chang, Zhigang Yang, Zhao Chen, Yongbiao Zhou, Qin Zheng, Shibao Institute of Image Processing and Network Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China

关键词： Gait analysis

Pulsar candidate selection using ensemble networks for FAST drift-scan survey

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2019年第5期62卷 61-70页

作者： HongFeng Wang WeiWei Zhu Ping Guo Di Li SiBo Feng Qian Yin ChenChen Miao ZhenZhao Tao ZhiChen Pan Pei Wang Xin Zheng XiaoDan Deng ZhiJie Liu XiaoYao Xie XuHong Yu ShanPing You Hui Zhang FAST Collaboration Image Processing and Pattern Recognition Laboratory College of Information Science and TechnologyBeijing Normal UniversityBeijing 100875China CAS Key Laboratory of FAST Chinese Academy of SciencesBeijing 100101China School of Information Management Dezhou UniversityDezhou 253023China Image Processing and Pattern Recognition Laboratory School of Systems ScienceBeijing Normal UniversityBeijing 100875China University of Chinese Academy of Sciences Beijing 100049China Key Laboratory of Information and Computing Science Guizhou Province Guizhou Normal UniversityGuiyang 550001China School of Physics and Electronic Science Guizhou Normal UniversityGuiyang 550001China 不详

The Commensal Radio Astronomy Five-hundred-meter Aperture Spherical radio Telescope(FAST) Survey(CRAFTS) utilizes the novel drift-scan commensal survey mode of FAST and can generate billions of pulsar candidate signals. The human experts are not likely to thoroughly examine these signals, and various machine sorting methods are used to aid the classification of the FAST candidates. In this study, we propose a new ensemble classification system for pulsar candidates. This system denotes the further development of the pulsar image-based classification system(PICS), which was used in the Arecibo Telescope pulsar survey, and has been retrained and customized for the FAST drift-scan survey. In this study, we designed a residual network model comprising 15 layers to replace the convolutional neural networks(CNNs) in PICS. The results of this study demonstrate that the new model can sort >96% of real pulsars to belong the top 1% of all candidates and classify >1.6 million candidates per day using a dual-GPU and 24-core computer. This increased speed and efficiency can help to facilitate real-time or quasi-real-time processing of the pulsar-search data stream obtained from CRAFTS. In addition, we have published the labeled FAST data used in this study online, which can aid in the development of new deep learning techniques for performing pulsar searches.

关键词： pulsars neural networks data analysis