Object detection based on DenseNet and RPN

Jing Li, Wenjie Chen, Yangyang Sun, Ye Li, Zhihong Peng

科研成果: 书/报告/会议事项章节会议稿件同行评审

6 引用 (Scopus)

摘要

Object detection algorithm based on depth model has achieved state-of-the-art results on various challenging benchmarks. However, the large amount of parameters of depth model means a large amount of calculation. This seriously limits the practical application of object detection algorithm, especially on embedded devices with limited computing power. We propose an object detection algorithm based on DenseNet and Region Proposal Network(RPN) and replace ROI Pooling with ROI Align. From the evaluation on PASCAL VOC and MS COCO we can see that the algorithm achieves object detection with fewer parameters while maintaining or improving accuracy. This is meaningful for the development of embedded in-depth learning. Finally, we explore the influence of different shared convolutional layers on object detection algorithm.

源语言英语
主期刊名Proceedings of the 38th Chinese Control Conference, CCC 2019
编辑Minyue Fu, Jian Sun
出版商IEEE Computer Society
8410-8415
页数6
ISBN(电子版)9789881563972
DOI
出版状态已出版 - 7月 2019
活动38th Chinese Control Conference, CCC 2019 - Guangzhou, 中国
期限: 27 7月 201930 7月 2019

出版系列

姓名Chinese Control Conference, CCC
2019-July
ISSN(印刷版)1934-1768
ISSN(电子版)2161-2927

会议

会议38th Chinese Control Conference, CCC 2019
国家/地区中国
Guangzhou
时期27/07/1930/07/19

指纹

探究 'Object detection based on DenseNet and RPN' 的科研主题。它们共同构成独一无二的指纹。

引用此