10 April 2018 Small-size pedestrian detection in large scene based on fast R-CNN
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106150J (2018) https://doi.org/10.1117/12.2305889
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
Pedestrian detection is a canonical sub-problem of object detection with high demand during recent years. Although recent deep learning object detectors such as Fast/Faster R-CNN have shown excellent performance for general object detection, they have limited success for small size pedestrian detection in large-view scene. We study that the insufficient resolution of feature maps lead to the unsatisfactory accuracy when handling small instances. In this paper, we investigate issues involving Fast R-CNN for pedestrian detection. Driven by the observations, we propose a very simple but effective baseline for pedestrian detection based on Fast R-CNN, employing the DPM detector to generate proposals for accuracy, and training a fast R-CNN style network to jointly optimize small size pedestrian detection with skip connection concatenating feature from different layers to solving coarseness of feature maps. And the accuracy is improved in our research for small size pedestrian detection in the real large scene.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shengke Wang, Shengke Wang, Na Yang, Na Yang, Lianghua Duan, Lianghua Duan, Lu Liu, Lu Liu, Junyu Dong, Junyu Dong, "Small-size pedestrian detection in large scene based on fast R-CNN", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106150J (10 April 2018); doi: 10.1117/12.2305889; https://doi.org/10.1117/12.2305889
PROCEEDINGS
5 PAGES


SHARE
Back to Top