KMS Chongqing Institute of Green and Intelligent Technology, CAS
| A hybrid real-time visual tracking using compressive RGB-D features | |
Zhao, Mengyuan1; Luo, Heng2; Tafti, Ahmad P.3; Lin, Yuanchang4; He, Guotian4
| |
| 2015 | |
| 摘要 | The online multi-instance learning tracking (MIL) algorithm is known for its ability of alleviating tracking drift by training classifiers with positive and negative bag. However, the increased computational complexity results in time consuming due to the lack of consideration of sampling importance when collecting training samples. Additionally, the MIL method, as a 2D feature-based tracking algorithm, performs unsteadily when the object changes poses or rotates seriously. In this paper, a histogram-based feature similarity measurement is employed as a weighting strategy to select positive samples. Benefited from profitable depth information, the tracking algorithm we proposed achieves higher tracking performance. For computational efficiency, a compressive sensing method is adopted to extract features and reduce dimensionality. Experimental results demonstrate that our algorithm is better in robustness, accuracy, efficiency than three state-of-the-art methods on challenging video sequences. © Springer International Publishing Switzerland 2015. |
| 语种 | 英语 |
| DOI | 10.1007/978-3-319-27857-5_51 |
| 会议(录)名称 | 11th International Symposium on Advances in Visual Computing, ISVC 2015
 |
| 页码 | 561-573 |
| 收录类别 | SCI |
| 会议地点 | Las Vegas, NV, United states |
| 会议日期 | December 14, 2015 - December 16, 2015 |
