检索结果-内蒙古大学图书馆

A Bioinspired retinal neural network for accurately extracting small-target motion information in cluttered backgrounds

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Xiao Qiao, Hong Li, Hui Jiang, Zhihong School of Mechatronical Engineering Advanced Innovation Center for Intelligent Robots and Systems Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education Beijing Institute of Technology Beijing100081 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Beijing Key Laboratory of Research and Application for Robotic Intelligence of’Hand-Eye-Brain’ Interaction Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

—Robust and accurate detection of small moving targets in cluttered moving backgrounds is a significant and challenging problem for robotic visual systems to perform search and tracking tasks. Inspired by the neural circuitry of elementary motion vision in the mammalian retina, this paper proposes a bioinspired retinal neural network based on a new neurodynamics-based temporal filtering and multiform 2-D spatial Gabor filtering. This model can estimate motion direction accurately via only two perpendicular spatiotemporal filtering signals, and respond to small targets of different sizes and velocities through adjusting the dendrite field size of spatial filter. Meanwhile, an algorithm of directionally selective inhibition is proposed to suppress the target-like features in the moving background, which can reduce the influence of background motion effectively. Extensive synthetic and real-data experiments show that the proposed model works stably for small targets of a wider size and velocity range, and has better detection performance than other bioinspired models. Additionally, it can also extract the information of motion direction and motion energy accurately and rapidly. Copyright © 2021, The Authors. All rights reserved.

关键词： Ophthalmology

A Bioinspired approach-sensitive neural network for collision detection in cluttered and dynamic backgrounds

学校读者我要写书评

暂无评论

arXiv 2021年

—Rapid, accurate and robust detection of looming objects in cluttered moving backgrounds is a significant and challenging problem for robotic visual systems to perform collision detection and avoidance tasks. Inspired by the neural circuit of elementary motion vision in the mammalian retina, this paper proposes a bioinspired approach-sensitive neural network (ASNN) that contains three main contributions. Firstly, a direction-selective visual processing module is built based on the spatiotemporal energy framework, which can estimate motion direction accurately via only two mutually perpendicular spatiotemporal filtering channels. Secondly, a novel approach-sensitive neural network is modeled as a push-pull structure formed by ON and OFF pathways, which responds strongly to approaching motion while insensitivity to lateral motion. Finally, a method of directionally selective inhibition is introduced, which is able to suppress the translational backgrounds effectively. Extensive synthetic and real robotic experiments show that the proposed model is able to not only detect collision accurately and robustly in cluttered and dynamic backgrounds but also extract more collision information like position and direction, for guiding rapid decision making. © 2021, CC BY.

关键词： Mammals

An Island Remote Sensing Image Segmentation Algorithm Based on A Fusion Network with Attention Mechanism 3

学校读者我要写书评

暂无评论

An Island Remote Sensing Image Segmentation Algorithm Based ...

2020 3rd International Conference on Computer Information Science and Artificial Intelligence, CISAI 2020

作者： Chen, Tianyuan Wang, Hongfei Liu, Hao Wu, Peng Key Laboratory of Space Utilization Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing100094 China University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

With the increasing importance of islands in many fields, it has become the focus of research to obtain information from island remote sensing images efficiently by using image semantic segmentation algorithm. In recent years, deep learning methods based on convolutional neural network have been widely used in image segmentation. However, in view of the problems that remote sensing images contain richer ratio information and complex background interference, we propose an island remote sensing image segmentation algorithm based on a fusion network with attention mechanism, called AFU-Net. The network is built on the basis of FC_U-Net [1]. An attention mechanism is added to pre-weight the shallow features before deep-shallow layer feature fusion, in order to enhance the response capability of the target features, suppress the background interference and improve the segmentation accuracy of the network. The testing and comparative experiments on NWPU-RESISC45 dataset show that the quantitative metrics and visual effects of AFU-Net are greatly improved compared to FC_U-Net, and are also superior to other three state-of-the-art methods, U-Net, FCN, SegNet, which indicates the effectiveness of our method. © Published under licence by IOP Publishing Ltd.

关键词： Semantic Segmentation

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Jiaqi Huang, Zhizhong Lei, Yiming Shan, Hongming Wang, James Z. Wang, Fei-Yue Zhang, Junping The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China The Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China The College of Information Sciences and Technology The Pennsylvania State University University ParkPA16802 United States The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Institute of Systems Engineering Macau University of Science and Technology China Qingdao Academy of Intelligent Industries Qingdao266109 China

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://***/bridgeqiqi/DREAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

An Island Remote Sensing Image Segmentation Algorithm Based on FC_U-Net Network

学校读者我要写书评

暂无评论

An Island Remote Sensing Image Segmentation Algorithm Based ...

2020 International Conference on Computer Vision, Image and Deep Learning, CVIDL 2020

作者： Chen, Tianyuan Wang, Hongfei Liu, Hao Du, Junrong Wu, Peng Key Laboratory of Space Utilization Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing100094 China University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

ISBN: (数字)9781728194813

ISBN: (纸本)9781728194813

With the increasing importance of islands in many fields, it has become the focus of research to obtain information from island remote sensing images efficiently by using image semantic segmentation algorithm. In recent years, deep learning methods based on convolutional neural network have been widely used in image segmentation. However, for remote sensing images with rich details and different target scales, there are still some problems such as insufficient segmentation accuracy. To handle these problems, we propose an island remote sensing image segmentation algorithm based on FC_U-Net network. In this network, U-Net and FCN (Fully Convolutional Network) are improved respectively to form two new modules, and then the semantic features and detail features from the two modules are fused by a fusion module. The testing and comparative experiments on NWPU-RESISC45 dataset show that the quantitative metrics and visual effects of FC_U-Net are better than other three state-of-the-art methods, U-Net, FCN (Fully Convolutional Network), SegNet, which indicates the effectiveness of our method. © 2020 IEEE.

关键词： Semantic Segmentation

A Self-identifying Checkerboard-like Pattern for Camera Calibration

学校读者我要写书评

暂无评论

A Self-identifying Checkerboard-like Pattern for Camera Cali...

Chinese control Conference (CCC)

作者： Zhang Gao Mingzhu Zhu Junzhi Yu School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory for Turbulence and Complex Systems Peking University Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

This paper proposes a new type of planar pattern for camera calibration featuring its checkerboard-like structure and self-identity. White and black blocks are arranged by a novel method to ensure the uniqueness of each local pattern, and meanwhile maintain all checkerboard corners. The pattern is generated by combining identification units based on a random search strategy. Positions of local patterns can be acquired by searching the global pattern, achieving the benefit of self-identity. Because of the checkerboard-like structure, no burden is introduced in sampling compared to traditional calibrations. Experimental results show the effectiveness of the proposed calibration method. The conceived pattern is especially suitable for the calibration of multi-camera system with limited overlapping scope.

关键词： Calibration Feature extraction Cameras Search problems Visualization complex systems Electronic mail

A prototype-based generalized zero-shot learning framework for hand gesture recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wu, Jinting Zhang, Yujia Zhao, Xiaoguang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Hand gesture recognition plays a significant role in human-computer interaction for understanding various human gestures and their intent. However, most prior works can only recognize gestures of limited labeled classes and fail to adapt to new categories. The task of Generalized Zero-Shot Learning (GZSL) for hand gesture recognition aims to address the above issue by leveraging semantic representations and detecting both seen and unseen class samples. In this paper, we propose an end-to-end prototype-based GZSL framework for hand gesture recognition which consists of two branches. The first branch is a prototype-based detector that learns gesture representations and determines whether an input sample belongs to a seen or unseen category. The second branch is a zero-shot label predictor which takes the features of unseen classes as input and outputs predictions through a learned mapping mechanism between the feature and the semantic space. We further establish a hand gesture dataset that specifically targets this GZSL task, and comprehensive experiments on this dataset demonstrate the effectiveness of our proposed approach on recognizing both seen and unseen gestures. Copyright © 2020, The Authors. All rights reserved.

关键词： Palmprint recognition

Decision-Making in Driver-automation Shared control:A Review and Perspectives

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第5期7卷 1289-1307页

作者： Wenshuo Wang Xiaoxiang Na Dongpu Cao Jianwei Gong Junqiang Xi Yang Xing Fei-Yue Wang IEEE California PATH University of CaliforniaBerkeleyCA 94720 USA Department of Engineering University of CambridgeCambridge CB21PZU.K. Mechanical and Mechatronics Engineering University of WaterlooWaterloo N2L3G1Canada Department of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingapore 639798Singapore State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190and also with the Research Center for Military Computational Experiments and Parallel Systems TechnologyNational University of Defense TechnologyChangsha 410073China

Shared control schemes allow a human driver to work with an automated driving agent in driver-vehicle systems while retaining the driver’s abilities to *** human driver,as an essential agent in the driver-vehicle shared control systems,should be precisely modeled regarding their cognitive processes,control strategies,and decision-making *** interactive strategy design between drivers and automated driving agents brings an excellent challenge for human-centric driver assistance systems due to the inherent characteristics of *** open-ended questions arise,such as what proper role of human drivers should act in a shared control scheme?How to make an intelligent decision capable of balancing the benefits of agents in shared control systems?Due to the advent of these attentions and questions,it is desirable to present a survey on the decision making between human drivers and highly automated vehicles,to understand their architectures,human driver modeling,and interaction strategies under the driver-vehicle shared ***,we give a further discussion on the key future challenges and *** are likely to shape new potential research directions.

关键词： Automated vehicle decision-making human driver human-vehicle interaction shared control

Predicting Online News Authorship by an Authorship Embeddings Space Method

学校读者我要写书评

暂无评论

Predicting Online News Authorship by an Authorship Embedding...

IEEE International Conference on Big Data Analysis (ICBDA)

作者： Wanting Wen Qiudan Li Junfeng Li Xu Zhang Daniel Zeng The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China National Internet Emergency Center CNCERT/CC Beijing China

ISBN: (数字)9781728141114

ISBN: (纸本)9781728141121

In this paper, we study the problem of authorship identification in online news data. Most of the existing approaches predict authorship via feature engineering, which cannot focus on important attributes. We designed an authorship identification method named Authorship Embeddings Space model (AES) to predict the online news authorship between online news and authors. First, we propose an authorship space to represent the deep semantic relationship of news content. Second, we use an embedding learning method to perform the relationship between authors and news. Finally, we formulated an authorship prediction algorithm to identify the news authors based on the authorship embeddings. Experimental results on the online news dataset reveal that the AES model outperforms the baseline models.

关键词： Organizations Stock markets Training Semantics Writing Support vector machines