NeuroAED: Towards Efficient Abnormal Event Detection in Visual Surveillance With Neuromorphic Vision Sensor
文献类型:期刊论文
作者 | Chen, Guang2,3,4; Liu, Peigen2; Liu, Zhengfa2; Tang, Huajin5; Hong, Lin1; Dong, Jinhu2; Conradt, Jorg6; Knoll, Alois3 |
刊名 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY |
出版日期 | 2021 |
卷号 | 16页码:923-936 |
ISSN号 | 1556-6013 |
关键词 | Neuromorphics Vision sensors Event detection Cameras Feature extraction Legged locomotion Signal processing algorithms Abnormal event detection video surveillance optical flow event based descriptors neuromorphic vision sensor |
DOI | 10.1109/TIFS.2020.3023791 |
通讯作者 | Chen, Guang(tj_autodrive@hotmail.com) |
英文摘要 | Abnormal event detection is an important task in research and industrial applications, which has received considerable attention in recent years. Existing methods usually rely on standard frame-based cameras to record the data and process them with computer vision technologies. In contrast, this paper presents a novel neuromorphic vision based abnormal event detection system. Compared to the frame-based camera, neuromorphic vision sensors, such as Dynamic Vision Sensor (DVS), do not acquire full images at a fixed frame rate but rather have independent pixels that output intensity changes (called events) asynchronously at the time they occur. Thus, it avoids the design of the encryption scheme. Since events are triggered by moving edges on the scene, DVS is a natural motion detector for the abnormal objects and automatically filters out any temporally-redundant information. Based on this unique output, we first propose a highly efficient method based on the event density to select activated event cuboids and locate the foreground. We design a novel event-based multiscale spatio-temporal descriptor to extract features from the activated event cuboids for the abnormal event detection. Additionally, we build the NeuroAED dataset, the first public dataset dedicated to abnormal event detection with neuromorphic vision sensor. The NeuroAED dataset consists of four sub-datasets: Walking, Campus, Square, and Stair dataset. Experiments are conducted based on these datasets and demonstrate the high efficiency and accuracy of our method. |
WOS关键词 | ANOMALY DETECTION ; LOCALIZATION ; RECOGNITION ; SYSTEM |
资助项目 | National Natural Science Foundation of China[61906138] ; State Key Laboratory of Management and Control for Complex Systems Open Project[20190109] ; Shanghai Automotive Industry Sci-Tech Development Program[1838] ; European Union's Horizon 2020 Framework Programme for Research and Innovation (Human Brain Project SGA3)[945539] ; Shanghai AI Innovation Development Program 2018 |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000576264500017 |
资助机构 | National Natural Science Foundation of China ; State Key Laboratory of Management and Control for Complex Systems Open Project ; Shanghai Automotive Industry Sci-Tech Development Program ; European Union's Horizon 2020 Framework Programme for Research and Innovation (Human Brain Project SGA3) ; Shanghai AI Innovation Development Program 2018 |
源URL | [http://ir.ia.ac.cn/handle/173211/42096] |
专题 | 国家专用集成电路设计工程技术研究中心_前瞻芯片研制与测试团队 |
通讯作者 | Chen, Guang |
作者单位 | 1.Shandong Univ Sci & Technol, Coll Transportat, Qingdao 266510, Peoples R China 2.Tongji Univ, Dept Automot Engn, Shanghai 200092, Peoples R China 3.Tech Univ Munich, Chair Robot Artificial Intelligence & Real Time S, D-80333 Munich, Germany 4.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China 5.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou 310027, Peoples R China 6.KTH Royal Inst Technol, S-11428 Stockholm, Sweden |
推荐引用方式 GB/T 7714 | Chen, Guang,Liu, Peigen,Liu, Zhengfa,et al. NeuroAED: Towards Efficient Abnormal Event Detection in Visual Surveillance With Neuromorphic Vision Sensor[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2021,16:923-936. |
APA | Chen, Guang.,Liu, Peigen.,Liu, Zhengfa.,Tang, Huajin.,Hong, Lin.,...&Knoll, Alois.(2021).NeuroAED: Towards Efficient Abnormal Event Detection in Visual Surveillance With Neuromorphic Vision Sensor.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,16,923-936. |
MLA | Chen, Guang,et al."NeuroAED: Towards Efficient Abnormal Event Detection in Visual Surveillance With Neuromorphic Vision Sensor".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 16(2021):923-936. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。