Speed up deep neural network based pedestrian detection by sharing features across multi-scale models

NEUROCOMPUTING

卷:185

Article

Jiang, Xiaoheng¹  Pang, Yanwei¹  Li, Xuelong²  Pan, Jing^1,3 

[1] Tianjin Univ, Sch Elect Informat Engn, Tianjin 300072, Peoples R China

[2] Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China

[3] Tianjin Univ Technol & Educ, Sch Elect Engn, Tianjin 300222, Peoples R China

关键词: Pedestrian detection;    Deep neural networks;    Convolutional neural networks;    Share features;   

DOI  :  10.1016/j.neucom.2015.12.042

来源: Elsevier

【 摘 要 】

Deep neural networks (DNNs) have now demonstrated state-of-the-art detection performance on pedestrian datasets. However, because of their high computational complexity, detection efficiency is still a frustrating problem even with the help of Graphics Processing Units (GPUs). To improve detection efficiency, this paper proposes to share features across a group of DNNs that correspond to pedestrian models of different sizes. By sharing features, the computational burden for extracting features from an image pyramid can be significantly reduced. Simultaneously, we can detect pedestrians of several different scales on one single layer of an image pyramid. Furthermore, the improvement of detection efficiency is achieved with negligible loss of detection accuracy. Experimental results demonstrate the robustness and efficiency of the proposed algorithm. (C) 2015 The Authors. Published by Elsevier B.V.

【 授权许可】

Free