.png){kind=icon}
.png){kind=icon}
Return
Abnormal crowd motion detection using double sparse representation
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2016.09.138.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The sparse representation method is widely used in the area of abnormal crowd motion detection to accurately represent the crowd motions with high dimension features. To overcome its lack of training samples and achieve more accurate detection, a double sparse representation method with a dynamic dictionary updating process is proposed. The proposed method utilizes two sparse representation classifiers that each gives a separate judgment for every test sample. Fuzzy integral is also employed to detect any abnormality in a sample. The results of experiments conducted on various datasets show that the proposed method achieves higher accuracy than state-of-the-art methods in local and global abnormal events detection. (C) 2017 Elsevier B.V. All rights reserved.
Keywords:
Abnormal event
Crowd analysis
Sparse representation
Dictionary updating
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.