| 题名: | A novel multi-view object recognition in complex background |
| 作者: | Chang, Yongxin1,2,3; Yu, Huapeng1,2,3; Xu, Zhiyong1; Fu, Chengyu1; Gao, Chunming2
|
| 出版日期: | 2015
|
| 会议名称: | Proceedings of SPIE: 20th International Symposium on High Power Systems and Applications 2014, HPLS and A 2014
|
| 会议日期: | 2015
|
| 学科分类: | Algorithms - Computer vision - High power lasers
|
| DOI: | 10.1117/12.2065292
|
| 通讯作者: | Chang, Yongxin
|
| 中文摘要: | Recognizing objects from arbitrary aspects is always a highly challenging problem in computer vision, and most existing algorithms mainly focus on a specific viewpoint research. Hence, in this paper we present a novel recognizing framework based on hierarchical representation, part-based method and learning in order to recognize objects from different viewpoints. The learning evaluates the model"™s mistakes and feeds it back the detector to avid the same mistakes in the future. The principal idea is to extract intrinsic viewpoint invariant features from the unseen poses of object, and then to take advantage of these shared appearance features to support recognition combining with the improved multiple view model. Compared with other recognition models, the proposed approach can efficiently tackle multi-view problem and promote the recognition versatility of our system. For an quantitative valuation The novel algorithm has been tested on several benchmark datasets such as Caltech 101 and PASCAL VOC 2010. The experimental results validate that our approach can recognize objects more precisely and the performance outperforms others single view recognition methods. © 2015 SPIE. |
| 英文摘要: | Recognizing objects from arbitrary aspects is always a highly challenging problem in computer vision, and most existing algorithms mainly focus on a specific viewpoint research. Hence, in this paper we present a novel recognizing framework based on hierarchical representation, part-based method and learning in order to recognize objects from different viewpoints. The learning evaluates the model"™s mistakes and feeds it back the detector to avid the same mistakes in the future. The principal idea is to extract intrinsic viewpoint invariant features from the unseen poses of object, and then to take advantage of these shared appearance features to support recognition combining with the improved multiple view model. Compared with other recognition models, the proposed approach can efficiently tackle multi-view problem and promote the recognition versatility of our system. For an quantitative valuation The novel algorithm has been tested on several benchmark datasets such as Caltech 101 and PASCAL VOC 2010. The experimental results validate that our approach can recognize objects more precisely and the performance outperforms others single view recognition methods. © 2015 SPIE. |
| 收录类别: | Ei
|
| 语种: | 英语
|
| 卷号: | 9255
|
| ISSN号: | 0277-786X
|
| 文章类型: | 会议论文
|
| 页码: | 92553K
|
| Citation statistics: |
|
| 内容类型: | 会议论文
|
| URI标识: | http://ir.ioe.ac.cn/handle/181551/7439
|
| Appears in Collections: | 光电工程总体研究室（一室）_会议论文
|
| File Name/ File Size |
Content Type |
Version |
Access |
License |
|
|---|
| 2015-2051.pdf（621KB） | 会议论文 | -- | 限制开放 | | View
联系获取全文 |
|
|
作者单位: | 1. Institute of Optics and Electronics, Key Laboratory of Beam Control, Chinese Academy of Sciences, Chengdu, China
2. School of Optoelectronic Information, University of Electronic Science and Technology of China, Chengdu, China
3. University of Chinese Academy of Sciences, Beijing, China
|
| Recommended Citation: | |
Chang, Yongxin,Yu, Huapeng,Xu, Zhiyong,et al. A novel multi-view object recognition in complex background[C]. 见:Proceedings of SPIE: 20th International Symposium on High Power Systems and Applications 2014, HPLS and A 2014. 2015.
|
|
|
