NSSC OpenIR
基于卷积神经网络的候选区域优化算法
Alternative TitleRegion proposal optimization algorithm based on convolutional neural networks
王春哲; 安军社; 姜秀杰; 邢笑雪
Source Publication中国光学
2019
Volume12Issue:6Pages:1348-1361; AR:2095-1531(2019)12:6<1348:JYJJSJ>2.0.TX;2-#
ISSN2095-1531
Language中文
Keyword计算机视觉 目标检测 候选区域 卷积神经网络 显著性目标 computer vision object detection region proposals convolutional neural networks salient object
Abstract在目标检测中,通常使用候选区域提高目标的检测效率。为解决当前候选区域质量较低的问题,本文将卷积边缘特征、显著性及目标位置信息引入到候选区域算法中。首先,利用卷积神经网络将待检测图像生成更富有语义信息的边缘特征,并通过边缘点聚合及边缘组相似性策略,获取每个滑动窗口的边缘信息得分;其次,利用显著性目标的局部特征,统计每个滑动窗口中的目标显著性得分;第三,根据目标可能出现的位置,计算每个滑动窗口中的目标位置信息得分;最后,利用边缘信息、显著性及位置信息的分数确定候选区域。在PASCAL VOC 2007验证集上进行实验,给定10 000个候选区域,交并比取0.7时,所提算法的召回率为90.50%,较Edge Boxes算法提高了3%。每张图像的运行时间大约为0.76 s。结果表明,本文算法可快速产生较高质量的候选区域。
Other AbstractRegion proposals are usually used to efficiently detect objects in object detection. In order to solve the problem that the region proposals have low quality, the convolutional edge features, object saliency and position information of objects are introduced into the region proposals algorithm. Firstly, the edge features with semantically meaningful information are generated from the images to be detected using the convolutional neural networks, and the score of edge information for per sliding window is obtained through the strategy of edge clustering and the similarities between the edge groups. Then, the salient object scores of each sliding window are computed using the local features of salient objects. Thirdly,the scores of object position information are calculated according to the location where objects may occur. Finally, the region proposals are determined by three components including edge information scores, salient object scores and the object positions scores. The experimental results in PASCAL VOC 2007 validation set show that given just 10 000 region proposals, the object recall of the proposed algorithm is 90.50%,that is increased by 3% comparing with Edge Boxes with intersection over union threshold of 0.7. The run time of the proposed method is about 0.76 seconds for processing one image,and this demonstrates that our approach can yield a set of region proposals with higher quality at a fast speed.
Indexed ByCSCD
Citation statistics
Cited Times:1[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.nssc.ac.cn/handle/122/7450
Collection中国科学院国家空间科学中心
Affiliation1.王春哲, 中国科学院国家空间科学中心
2.中国科学院大学, 中国科学院复杂航天系统电子信息技术重点实验室
3.北京
4.北京 100190
5.100049, 中国.
6.安军社, 中国科学院国家空间科学中心, 中国科学院复杂航天系统电子信息技术重点实验室, 北京 100190, 中国.
7.姜秀杰, 中国科学院国家空间科学中心, 中国科学院复杂航天系统电子信息技术重点实验室, 北京 100190, 中国.
8.邢笑雪, 长春大学, 长春, 吉林 130022, 中国.
9.Wang Chunzhe, National Space Science Center,Chinese Academy of Sciences
10.University of Chinese Academy of Sciences, Key Laboratory of Electronics and Information Technology for Space Systems
11.Beijing
12.Beijing 100190
13.100049.
14.An Junshe, National Space Science Center,Chinese Academy of Sciences, Key Laboratory of Electronics and Information Technology for Space Systems, Beijing 100190, China.
15.Jiang Xiujie, National Space Science Center,Chinese Academy of Sciences, Key Laboratory of Electronics and Information Technology for Space Systems, Beijing 100190, China.
16.Xing Xiaoxue, Changchun University, Changchun, Jilin 130022, China.
17.wangchunzhe163@sina.com
18.anjunshe@nssc.ac.cn
Recommended Citation
GB/T 7714
王春哲,安军社,姜秀杰,等. 基于卷积神经网络的候选区域优化算法[J]. 中国光学,2019,12(6):1348-1361; AR:2095-1531(2019)12:6<1348:JYJJSJ>2.0.TX;2-#.
APA 王春哲,安军社,姜秀杰,&邢笑雪.(2019).基于卷积神经网络的候选区域优化算法.中国光学,12(6),1348-1361; AR:2095-1531(2019)12:6<1348:JYJJSJ>2.0.TX;2-#.
MLA 王春哲,et al."基于卷积神经网络的候选区域优化算法".中国光学 12.6(2019):1348-1361; AR:2095-1531(2019)12:6<1348:JYJJSJ>2.0.TX;2-#.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王春哲]'s Articles
[安军社]'s Articles
[姜秀杰]'s Articles
Baidu academic
Similar articles in Baidu academic
[王春哲]'s Articles
[安军社]'s Articles
[姜秀杰]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王春哲]'s Articles
[安军社]'s Articles
[姜秀杰]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.