Share Email Print
cover

Proceedings Paper

Special faster-RCNN for multi-objects detection
Author(s): Libin Hu D.V.M.; Changzhi Wei II; Xinghai Yang II; Teng Wang II
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

A series of neural networks called RCNN are playing a vital role in objects detection, as the most perfect one, Faster RCNN achieved an end-to-end object detection and made the detection times comparatively low but with high accuracy. In this work, we propose the following two changes to the original Faster RCNN model for multi-object detection: The first, we give 1800 ROI(Regions of Interest) comes from RPN to the RCNN network as input instead of 300, all the 1800 ROI are used to training the softmax classification and Bounding-box regression. The second, we traverse all xml files of every training image to get the number of marked objects and calculate the value of IOU for every marked objects, then we set a dynamic loss function to evaluation and optimization the Faster RCNN model by the two values of an image.

Paper Details

Date Published: 26 July 2018
PDF: 10 pages
Proc. SPIE 10828, Third International Workshop on Pattern Recognition, 108280W (26 July 2018); doi: 10.1117/12.2501773
Show Author Affiliations
Libin Hu D.V.M., Univ. of Jinan (China)
Changzhi Wei II, Univ. of Jinan (China)
Xinghai Yang II, Univ. of Jinan (China)
Teng Wang II, Univ. of Jinan (China)


Published in SPIE Proceedings Vol. 10828:
Third International Workshop on Pattern Recognition
Xudong Jiang; Zhenxiang Chen; Guojian Chen, Editor(s)

© SPIE. Terms of Use
Back to Top