ABSTRACT
Crowd density estimation, is much valuable in intelligent crowd monitoring. The traditional approach based on static texture analysis of single frame, is not adept to complex background, and the rule based statistic approaches are short of robustness for background noise. In this paper, a crowd density estimation approach fusing statistic features and texture analysis was proposed. After extracting foreground objects with frame difference, we learn SVM classifiers with GLCM and statistical features. The experiment results show the superiority of the proposed method and it can be applied in a complex environment.
- Davies A C, Yin J H, Velastin S A, et al. Crowd Monitoring Using Image Processing{J}. IEEE Elect ronics and Commu2 nication Engineering Journal, 1995, 7 (1): 37--47Google Scholar
- Valle J D, Oliveira L E S. People counting in low density video sequences{C}//LNCS 4872: PSIVT 2007, 2007: 737--748. Google ScholarDigital Library
- Li Chen, Ji Tao. People counting using iterative mean- shift fitting with symmetry measure{C}//International Conference on Information and Communication Security, 2007: 890--895.Google Scholar
- Bozzoli M. A statistical method for people counting in crowded environments{C}//14th International Conference on Image Analysis and Processing (ICIAP 2007), 2007: 1110--1115. Google ScholarDigital Library
- Ma Ruihua, Li Liyuan. On pixel count based crowd density estimation for visual surveillance{C}//Proceedings of the 2004 IEEE Conference on Cybernetics and Intelligent Systems, 2004:170--173.Google Scholar
- Marana A N, Cavenaghi M A. Real-time crowd density estimation using images{C}//International Symposium on Visual Computing (ISVC 2005), 2005: 355--362. Google ScholarDigital Library
- A.B. Chan, Privacy Preserving Crowd Monitoring: Counting People with-out People Models or Tracking. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR2008), 2008.Google ScholarCross Ref
Index Terms
- Multiple features fusion for crowd density estimation
Recommendations
Abnormal crowd density estimation in aerial images based on the deep and handcrafted features fusion
Highlights- Abnormal crowd density estimation in aerial images.
- The fusion of the deep and ...
AbstractAbnormal crowd analysis has always been an interesting research area since it ensures people’s safety and prevents crowd disasters in large scale events. In particular, crowd density estimation in aerial images has the advantage of ...
Towards crowd density-aware video surveillance applications
Crowd density analysis is a crucial component in visual surveillance mainly for security monitoring. This paper proposes a novel approach for crowd density measure, in which local information at pixel level substitutes a global crowd level or a number ...
Crowd counting using statistical features based on curvelet frame change detection
Automatic counting for moving crowds in digital images is an important application in computer artificial intelligence, especially for safety and management purposes. This paper presents a new method to estimate the size of a crowd. The new algorithm ...
Comments