改进的协同训练框架下压缩跟踪

郑超; 陈杰; 殷松峰; 杨星; 冯云松; 凌永顺

doi:10.11999/JEIT151001

改进的协同训练框架下压缩跟踪

doi: 10.11999/JEIT151001

1.
(电子工程学院脉冲功率激光技术国家重点实验室合肥 230037) ②(安徽建筑大学电子与信息工程学院合肥 230037)

基金项目:

安徽高校自然科学重大研究项目(KJ2015ZD14)，国家自然科学基金(61405248, 61503394)，安徽省自然科学基金(1408085 QF131, 1508085QF121)

计量
- 文章访问数: 1403
- HTML全文浏览量: 125
- PDF下载量: 401
- 被引次数: 0
出版历程
- 收稿日期: 2015-09-08
- 修回日期: 2016-01-11
- 刊出日期: 2016-07-19

Optimized Compressive Tracking in Co-training Framework

1.
(State Key Laboratory of Pulsed Power Laser Technology, Electronic Engineering Institute, Hefei 230037, China)
2.
(Electronics and Information Engineering Institute, Anhui Jianzhu University, Hefei 230037, China)

Funds:

Higher Education Institutes Natural Science Research Project of Anhui Province of China (KJ2015ZD14), The National Natural Science Foundation of China (61405248, 61503394), The Natural Science Foundation of Anhui Province (1408085QF131, 1508085QF121)

摘要

摘要: 针对基于传统协同训练框架的视觉跟踪算法在复杂环境下鲁棒性不足，该文提出一种改进的协同训练框架下压缩跟踪算法。首先，利用空间布局信息，基于能量熵最大化的在线特征选择技术提升压缩感知分类器的判别能力，分别在灰度空间和局部二值模式空间建立起基于结构压缩特征的两个独立分类器。然后，基于候选样本信任度分布熵的分类器联合机制实现互补性特征的自适应融合，增强跟踪结果的鲁棒性。最后，在级联的梯度直方图分类器辅助下，通过具备样本选择能力的新型协同训练准则完成联合外观模型的准确更新，解决了协同训练误差的积累问题。对大量具有挑战性的序列的对比实验结果验证了该算法相比于其它近似跟踪算法具有更优的性能。
- 视觉跟踪 /
- 协同训练 /
- 空间布局信息 /
- 压缩感知分类器 /
- 熵
Abstract: As visual tracking algorithms based on traditional co-training framework are characterized by poor robustness in complex environment, an optimized compressive tracking algorithm in a novel co-training criterion is proposed. Firstly, the spatial layout information and the online feature selection technique based on maximizing entropy energy are used to improve the discriminative capacity of compressive sense classifier, and two independent classifiers are constructed by structural compressive features selected from the gray intensity space and the local binary pattern space respectively. Secondly, on the basis of the classifiers collaborative strategy that is acquired by calculating the confidence score distribution entropy of the candidate samples, complementary features can be adaptive fused, which reinforces the robustness of tracking results. Thirdly, as assistant of the cascaded Histograms of Orientation Gradient (HOG) classifier, the collaborative appearance model is updated with accuracy by a novel co-training criterion with sample selecting ability, which solves the updating error of co-training accumulation problem. Comparative experiment results on extensive challenging sequences demonstrate that the proposed algorithm is of better performance than other similar tracking algorithms.
- Visual tracking /
- Co-training /
- Spatial layout information /
- Compressive sense classifier /
- Entropy

HTML全文

参考文献(23)

LI Xi, HU Weiming, SHEN Chunhua, et al. A survey of appearance models in visual object tracking[J]. ACM Transactions on Intelligent Systems and Technology, 2013, 4(4): 58. doi: 10.1145/2508037.2508039.

袁广林, 薛模根. 基于稀疏稠密结构表示与在线鲁棒字典学习的视觉跟踪[J]. 电子与信息学报, 2015, 37(3): 536-542. doi: 10.11999/JEIT140507.

YUAN Guanglin and XUE Mogen. Visual tracking based on sparse dense structure representation and online robust dictionary learning[J]. Journal of Electronics Information Technology, 2015, 37(3): 536-542. doi: 10.11999/JEIT140507.

HU Hongwei, MA Bo, and JIA Yunde. Multi-task l0 gradient minimization for visual tracking[J]. Neurocomputing, 2015, 54(1): 41-49. doi: 10.1016/j.neucom.2014.12.021.

HU Weiming, LI Wei, ZHANG Xiaoqin, et al. Single and multiple object tracking using a multi-feature joint sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(4): 816-833. doi: 10.1109/ TPAMI.2014.2353628.

YIN Yingjie, XU De, WANG Xingang, et al. Online state-based structured SVM combined with incremental PCA for robust visual tracking[J]. IEEE Transactions on Cybernetics, 2015, 45(9): 1988-2000. doi: 10.1109/TCYB. 2014.2363078.

KIM D H, KIM H K, LEE S J, et al. Kernel-based structural binary pattern tracking[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(8): 1288-1300. doi: 10.1109/TCSVT.2014.2305514.

陈思, 苏松志, 李绍滋, 等. 基于在线半监督 boosting 的协同训练目标跟踪算法[J]. 电子与信息学报, 2014, 36(4): 888-895. doi: 10.3724/SP.J.1146.2013.00826.

CHEN Si, SU Songzhi, LI Shaozi, et al. A novel co-training object tracking algorithm based on online semi-supervised boosting[J]. Journal of Electronics Information Technology, 2014, 36(4): 888-895. doi: 10.3724/SP.J.1146.2013.00826.

BLUM A and MITCHELL T. Combining labeled and unlabeled data with co-training[C]. Proceedings of ACM 11th Annual Conference on Computational Learning Theory, USA, 1998: 92-100.

TANG F, BRENNAN S, ZHAO Q, et al. Co-tracking using semi-supervised support vector machines[C]. IEEE International Conference on Computer Vision, Brazil, 2007: 1-8.

YU Q, DINH T B, and MEDIONI G. Online tracking and reacquisition using co-trained generative and discriminative trackers[C]. European Conference on Computer Vision, Springer, Berlin Heidelberg, 2008: 678-691.

LIU Rong, CHENG Jian, and LU Hanqing. A robust boosting tracker with minimum error bound in a co-training framework[C]. IEEE International Conference on Computer Vision, Japan, 2009: 1459-1466.

BABENKO B, YANG M H, and BELONGIE S. Visual tracking with online multiple instance learning[C]. IEEE Conference on Computer Vision and Pattern Recognition, USA, 2009: 983-990.

LU Huchuan, ZHOU Qiuhong, WANG Dong, et al. A co-training framework for visual tracking with multiple instance learning[C]. IEEE International Conference on Automatic Face Gesture Recognition and Workshops, Spain, 2011: 539-544.

ZHANG Kaihua, ZHANG Lei, and YANG M H. Fast compressive tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10): 2002-2015. doi: 10.1109/TPAMI.2014.2315808.

ZHU Jianzhang, MA Yue, QIN Qianqing, et al. Adaptive weighted real-time compressive tracking[J]. IET Computer Vision, 2014, 8(6): 740-752. doi: 10.1049/iet-cvi.2013.0255.

DALAL N and TRIGGS B. Histograms of oriented gradients for human detection[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, USA, 2005: 886-893.

HEIKKILA M and PIETIKAINEN M. A texture-based method for modeling the background and detecting moving objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4): 657-662. doi: 10.1109/ TPAMI.2006.68.

ZHOU Zhihua and LI Ming. Tri-training: exploiting unlabeled data using three classifiers[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(11): 1529-1541. doi: 10.1109/TKDE.2005.186.

WU Yi, LIM J, and YANG M H. Online object tracking: A benchmark[C]. IEEE Conference on Computer Vision and Pattern Recognition, USA, 2013: 2411-2418.

ZHANG Kaihua, ZHANG Lei, and YANG M H. Real-time object tracking via online discriminative feature selection [J]. IEEE Transactions on Image Processing, 2013, 22(12): 4664-4677. doi: 10.1109/TIP.2013.2277800.

ZHANG Kaihua and SONG Huihui. Real-time visual tracking via online weighted multiple instance learning[J]. Pattern Recognition, 2013, 46(1): 397-411. doi: 10.1016/ j.patcog.2012.07.013.

施引文献

资源附件(0)

访问统计