Share Email Print
cover

Proceedings Paper • new

Feature-fused SSD: fast detection for small objects
Author(s): Guimei Cao; Xuemei Xie; Wenzhe Yang; Quan Liao; Guangming Shi; Jinjian Wu
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Small objects detection is a challenging task in computer vision due to its limited resolution and information. In order to solve this problem, the majority of existing methods sacrifice speed for improvement in accuracy. In this paper, we aim to detect small objects at a fast speed, using the best object detector Single Shot Multibox Detector (SSD) with respect to accuracy-vs-speed trade-off as base architecture. We propose a multi-level feature fusion method for introducing contextual information in SSD, in order to improve the accuracy for small objects. In detailed fusion operation, we design two feature fusion modules, concatenation module and element-sum module, different in the way of adding contextual information. Experimental results show that these two fusion modules obtain higher mAP on PASCAL VOC2007 than baseline SSD by 1.6 and 1.7 points respectively, especially with 2-3 points improvement on some small objects categories. The testing speed of them is 43 and 40 FPS respectively, superior to the state of the art Deconvolutional single shot detector (DSSD) by 29.4 and 26.4 FPS.

Paper Details

Date Published: 10 April 2018
PDF: 8 pages
Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106151E (10 April 2018); doi: 10.1117/12.2304811
Show Author Affiliations
Guimei Cao, Xidian Univ. (China)
Xuemei Xie, Xidian Univ. (China)
Wenzhe Yang, Xidian Univ. (China)
Quan Liao, Xidian Univ. (China)
Guangming Shi, Xidian Univ. (China)
Jinjian Wu, Xidian Univ. (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