CASIA OpenIR  > 模式识别国家重点实验室  > 先进数据分析与学习
Objectness estimation using edges
Hongzhen Wang; Zikun Liu; Lingfeng Wang; Lubin Weng; Chunhong Pan
Conference NameIEEE International Conference on Image Processing
Conference Date2015-9
Conference PlaceQuébec City, Canada
AbstractGenerating object proposals before object detection has become a common way. In this paper, we present a novel method to measure the objectness of bounding boxes using edges. The contours play an important role in object localization and detection. The number of edges that are close to the boundary of a box has strong relationship with the likelihood of the box covering an object. In our method, we adopt a two-step scheme to generate object proposals. In the first step, we count the number of contours close to the box, where we use the proposed “Tile Algorithm” to wipe off the inner edges of a box. In the second step we re-rank the object proposals with a linear SVM classifier across all aspect-ratios for calibration. Experiments on the VOC2007 dataset show that we achieve 96.47% object detection rate with 1000 proposals.
Document Type会议论文
Recommended Citation
GB/T 7714
Hongzhen Wang,Zikun Liu,Lingfeng Wang,et al. Objectness estimation using edges[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
Objectness estimatio(2509KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hongzhen Wang]'s Articles
[Zikun Liu]'s Articles
[Lingfeng Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hongzhen Wang]'s Articles
[Zikun Liu]'s Articles
[Lingfeng Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hongzhen Wang]'s Articles
[Zikun Liu]'s Articles
[Lingfeng Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Objectness estimation using edges.pdf
Format: Adobe PDF
All comments (0)
No comment.

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