Multi-scale Detection Method for Dense Crowd Target Detection

Authors

Jianxin Zhou, 1. National University of Defense Technology, Changsha 410073, China;;
Jianjun Wu, 2. Hainan Armed Police Force, Hainan 570203, China;;
Junqiang Xue, 2. Hainan Armed Police Force, Hainan 570203, China;;
Lin Shuai, 1. National University of Defense Technology, Changsha 410073, China;;
Dang Gang, 1. National University of Defense Technology, Changsha 410073, China;;
Zhiquan Cheng, 3. Hunan Avatar Science Company, Changsha 410205, China;

Abstract

Abstract: A multi-scale algorithm was proposed to detect the targets flexibly. In coarse scale, an optimized DPM (Deformable Part Model) method was used to filter out sparse objectives that was represented by whole body. Then the whole scenario was cut into multiple finer regions and the Faster R-CNN (Region-based Convolutional Neural Network) method was trained and utilized to detect dense objects that was indicated by head in fine scale. These two detection results were incorporated via NMS (Non - Maximum Suppression) method, in order to supplement with each other and remove redundancy. The effectiveness of the proposed method has been proved comparing detect accuracy with DPM and R-CNN individually in the final experiment.

Recommended Citation

Zhou, Jianxin; Wu, Jianjun; Xue, Junqiang; Shuai, Lin; Gang, Dang; and Cheng, Zhiquan (2020) "Multi-scale Detection Method for Dense Crowd Target Detection," Journal of System Simulation: Vol. 28: Iss. 10, Article 30.
Available at: https://dc-china-simulation.researchcommons.org/journal/vol28/iss10/30

First Page

2503

Revised Date

2016-08-04

DOI Link

https://doi.org/

Last Page

2509

CLC

TP18

Recommended Citation

Zhou Jianxin, Wu Jianjun, Xue Junqiang, Lin Shuai, Dang Gang, Cheng Zhiquan. Multi-scale Detection Method for Dense Crowd Target Detection[J]. Journal of System Simulation, 2016, 28(10): 2503-2509.

Corresponding Author

Zhiquan Cheng,