? 指向性边缘框:基于内法向特征的一般物体检测
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (4) :701-713    DOI: 10.1007/s11390-017-1752-9
Special Issue on Deep Learning << Previous Articles | Next Articles >>
指向性边缘框:基于内法向特征的一般物体检测
Xiang Bai1, Senior Member, IEEE, Zheng Zhang1, Hong-Yang Wang1, Wei Shen2,*
1 School of Electronic Information and Communications, Huazhong University of Science and Technology Wuhan 430074, China;
2 Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University, Shanghai 200444, China
Directional Edge Boxes: Exploiting Inner Normal Direction Cues for Effective Object Proposal Generation
Xiang Bai1, Senior Member, IEEE, Zheng Zhang1, Hong-Yang Wang1, Wei Shen2,*
1 School of Electronic Information and Communications, Huazhong University of Science and Technology Wuhan 430074, China;
2 Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University, Shanghai 200444, China

摘要
参考文献
相关文章
Download: [PDF 6893KB]  
摘要 边缘是一种定位物体候选框的重要特征。最近在这个问题上的进展大多数是通过定义基于边缘特征的有效物体置性度来推动。在本文中,我们提出一种新的叫做指向性边缘的表示。所谓指向性边缘,是指该边缘上每个点给予了一个指向物体中心的方法。该方向通过卷积神经网络学习得到。基于指向性边缘,我们提出两种新的物体置性度用于对物体候选框排序。在PASCAL VOC 2007测试数据集上,产生1000个候选框,我们的方法可以分别取得97.1%和81.9%召回率,在IoU阈值为分别为0.5和0.7的情况下。该实验结果表明,我们的方法性能优于当前最好的方法。
关键词物体候选框   指向性边缘   卷积神经网络     
Abstract: Edges are important cues for localizing object proposals. The recent progresses to this problem are mostly driven by defining effective objectness measures based on edge cues. In this paper, we develop a new representation named directional edges on which each edge pixel is assigned with a direction toward object center, through learning a direction prediction model with convolutional neural networks in a holistic manner. Based on directional edges, two new objectness measures are designed for ranking object proposals. Experiments show that the proposed method achieves 97.1% object recall at an overlap threshold of 0.5 and 81.9% object recall at an overlap threshold of 0.7 at 1 000 proposals on the PASCAL VOC 2007 test dataset, which is superior to the state-of-the-art methods.
Keywordsobject proposal   directional edge   convolutional neural network     
Received 2016-12-16;
本文基金:

This work was supported in part by the National Natural Science Foundation of China under Grant Nos. 61573160 and 61672336, and in part by the "Chen Guang" Project supported by Shanghai Municipal Education Commission and Shanghai Education Development Foundation of China under Grant No. 15CG43.

通讯作者: Wei Shen     Email: wei.shen@t.shu.edu.cn
About author: Xiang Bai received his B.S., M.S., and Ph.D. degrees from Huazhong University of Science and Technology (HUST), Wuhan, in 2003, 2005, and 2009, respectively, all in electronics and information engineering. He is currently a professor with the School of Electronic Information and Communications, HUST, Wuhan, where he is also the vice director of the National Center of Anti-Counterfeiting Technology of China. His research interests include object recognition, shape analysis, scene text recognition, and intelligent systems. He serves as an associate editor for Pattern Recognition, Pattern Recognition Letters, Neuro Computing, and Frontiers of Computer Science.
引用本文:   
Xiang Bai, Zheng Zhang, Hong-Yang Wang, Wei Shen.指向性边缘框:基于内法向特征的一般物体检测[J]  Journal of Computer Science and Technology , 2017,V32(4): 701-713
Xiang Bai, Zheng Zhang, Hong-Yang Wang, Wei Shen.Directional Edge Boxes: Exploiting Inner Normal Direction Cues for Effective Object Proposal Generation[J]  Journal of Computer Science and Technology, 2017,V32(4): 701-713
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1752-9
Copyright 2010 by Journal of Computer Science and Technology