Semantic shape similarity-based contour tracking evaluation
文献类型：期刊论文
| 作者 | Zhang, Xiaoqin1; Luo, Wenhan2; Zhao, Li3; Li, Wei2 ; Hu, Weiming2
|
| 刊名 | OPTICAL ENGINEERING
 |
| 出版日期 | 2011-10-01 |
| 卷号 | 50期号:10 |
| 关键词 | evaluation measures contour tracking shape context pyramid match kernels |
| 英文摘要 | One major problem of contour-based tracking is how to evaluate the accuracy of tracking results due to nonrigid and deformative properties of contours. We propose a shape context-based evaluation measure that considers the semantic shape similarity between the tracked contour and ground-truth contour. In addition, a pyramid match kernel is introduced for shape histogram matching, which can effectively deal with the contours with different scales. Experimental results demonstrate, compared to two start-of-art evaluation measures, our measure effectively captures the local shape information and thus is more consistent with human vision. (C) 2011 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/1.3633334] |
| WOS标题词 | Science & Technology ; Physical Sciences |
| 类目[WOS] | Optics |
| 研究领域[WOS] | Optics |
| 关键词[WOS] | VISUAL TRACKING ; OBJECTS ; MODELS ; SETS |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000296559700035 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/3255]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_视频内容安全团队 |
| 作者单位 | 1.Wenzhou Univ, Inst Intelligent Syst & Decis, Wenzhou 325035, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Wenzhou Univ, Coll Phys & Elect Informat Engn, Wenzhou 325035, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Xiaoqin,Luo, Wenhan,Zhao, Li,et al. Semantic shape similarity-based contour tracking evaluation[J]. OPTICAL ENGINEERING,2011,50(10). |
| APA | Zhang, Xiaoqin,Luo, Wenhan,Zhao, Li,Li, Wei,&Hu, Weiming.(2011).Semantic shape similarity-based contour tracking evaluation.OPTICAL ENGINEERING,50(10). |
| MLA | Zhang, Xiaoqin,et al."Semantic shape similarity-based contour tracking evaluation".OPTICAL ENGINEERING 50.10(2011). |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。