Share Email Print
cover

Proceedings Paper • new

Fast pedestrian detection using scale-aware pooling
Author(s): Xinchuan Fu; Jie Wu; Shihai Shao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The standard pipeline in pedestrian detection is sliding a pedestrian model on an image feature pyramid to detect pedestrians of different scales. In this pipeline, feature pyramid construction is time consuming and becomes the bottleneck for fast detection. Recently, a method called multiresolution filtered channels (MRFC) was proposed which only used single scale feature maps to achieve fast detection. However, as MRFC use gridwise sampling in the feature extraction process, the receptive field correspondence in different scales is weak. This shortcoming limits its accuracy. In this paper, we proposed a method which also uses single scale feature maps. The main difference between MRFC and our method lies in feature extraction. As opposed to using gridwise sampling, we use scale-aware pooling, which makes a better receptive field correspondence. Experiment on Caltech dataset shows our detector achieves fast detecting speed at the same time with high accuracy.

Paper Details

Date Published: 9 August 2018
PDF: 7 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108061M (9 August 2018); doi: 10.1117/12.2503002
Show Author Affiliations
Xinchuan Fu, Univ. of Electronic Science and Technology of China (China)
Jie Wu, East China Normal Univ. (China)
Shihai Shao, Univ. of Electronic Science and Technology of China (China)


Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)

© SPIE. Terms of Use
Back to Top