Share Email Print
cover

Proceedings Paper • new

Receptive field enrichment network for pedestrian detection
Author(s): Pengfei Luo; Zengfu Wang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The current advanced pedestrian detection methods adopt feature maps with different resolutions to cover multiscale pedestrians. Despite multi-scale feature pyramid can alleviate the problems caused by scale variation, each layer used for detection has merely a fixed receptive field, which results in the defects related to pedestrians with wide range of scale and aspect ratio variation. In this paper, we propose the Receptive Field Enrichment Network (RFENet), an endto- end framework for fast and accurate pedestrian detection. Two blocks are introduced in this framework, a receptive field enrichment module (RFEM) and a hierarchy aggregation module (HAM). The former is designed to diversify receptive fields of features, so as to better adapt to pedestrians with different scales and aspect ratios. The latter is further applied to enhance the entire feature hierarchy by merging spatial information and high-level semantics from different layers simultaneously. To evaluate the effectiveness of our method, extensive experiments are conducted on CityPersons and Caltech datasets. The results show that our proposed RFENet achieves comparable performance with state-of-the-art methods.

Paper Details

Date Published: 27 November 2019
PDF: 8 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113211K (27 November 2019); doi: 10.1117/12.2548620
Show Author Affiliations
Pengfei Luo, Univ. of Science and Technology of China (China)
Zengfu Wang, Univ. of Science and Technology of China (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top