A Fast and Robust People Counting Method in Video Surveillance

2007 ◽  
Author(s):  
Enwei Zhang ◽  
Feng Chen
Keyword(s):  
Video Surveillance ◽  
Counting Method ◽  
People Counting

scholarly journals A Soft-YoloV4 for High-Performance Head Detection and Counting

Mathematics ◽  
2021 ◽  
Vol 9 (23) ◽  
pp. 3096
Author(s):  
Zhen Zhang ◽  
Shihao Xia ◽  
Yuxing Cai ◽  
Cuimei Yang ◽  
Shaoning Zeng
Keyword(s):  
High Performance ◽  
Detection Rate ◽  
Detection Method ◽  
State Of The Art ◽  
Counting Method ◽  
People Counting ◽  
Detection Model ◽  
Detection And Counting ◽  
Head Detection ◽  
Ap Value

Blockage of pedestrians will cause inaccurate people counting, and people’s heads are easily blocked by each other in crowded occasions. To reduce missed detections as much as possible and improve the capability of the detection model, this paper proposes a new people counting method, named Soft-YoloV4, by attenuating the score of adjacent detection frames to prevent the occurrence of missed detection. The proposed Soft-YoloV4 improves the accuracy of people counting and reduces the incorrect elimination of the detection frames when heads are blocked by each other. Compared with the state-of-the-art YoloV4, the AP value of the proposed head detection method is increased from 88.52 to 90.54%. The Soft-YoloV4 model has much higher robustness and a lower missed detection rate for head detection, and therefore it dramatically improves the accuracy of people counting.

People Counting Based on the Analysis of the Mass

2014 ◽  
Vol 945-949 ◽  
pp. 1875-1879
Author(s):  
Tao Li ◽  
Dong Mei Li ◽  
Ren Jie Huang ◽  
Xue Zhu Zhao
Keyword(s):  
Support Vector Machine ◽  
Video Surveillance ◽  
Support Vector ◽  
Svm Classifier ◽  
The Novel ◽  
People Counting ◽  
The People ◽  
Objects Tracking ◽  
Counting Model ◽  
Novel Algorithm

In order to improve the accuracy of people counting in video surveillance, the method for people counting based on the analysis of the mass is proposed. The novel algorithm of objects tracking is designed to aim at people counting, and the people counting model is obtained by training a support vector machine (SVM) classifier with the input of the feature of mass. The experimental results show that the accuracy of counting is over 93%.

People Counting Based on the Moving Feature of the Mass

2014 ◽  
Vol 989-994 ◽  
pp. 2540-2542
Author(s):  
Peng Zhe Qiao ◽  
Tao Li ◽  
Tao Xiang ◽  
Xi Zhi Zhang
Keyword(s):  
Support Vector Machine ◽  
Energy Density ◽  
Optical Flow ◽  
Video Surveillance ◽  
Support Vector ◽  
Svm Classifier ◽  
People Counting ◽  
The People ◽  
Flow Algorithm ◽  
Counting Model

In order to improve the accuracy of people counting in video surveillance, the method for people counting based on the moving feature of the mass is proposed. We obtain the orientation and energy density of mass through the optical flow algorithm, and get the information about the size of mass to design the feature of mass. The people counting model is obtained by training a support vector machine (SVM) classifier with the moving feature and shape feature of mass. The experimental results confirm that our approach improves the accuracy of people counting.

Sign in / Sign up

Export Citation Format

Share Document