Share Email Print
cover

Proceedings Paper

Small-size pedestrian detection in large scene based on fast R-CNN
Author(s): Shengke Wang; Na Yang; Lianghua Duan; Lu Liu; Junyu Dong
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 10 April 2018
PDF: 5 pages
Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106150J (10 April 2018); doi: 10.1117/12.2305889
Show Author Affiliations
Shengke Wang, Ocean Univ. of China (China)
Na Yang, Ocean Univ. of China (China)
Lianghua Duan, Ocean Univ. of China (China)
Lu Liu, Ocean Univ. of China (China)
Junyu Dong, Ocean Univ. of China (China)


Published in SPIE Proceedings Vol. 10615:
Ninth International Conference on Graphic and Image Processing (ICGIP 2017)
Hui Yu; Junyu Dong, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray