多示例深度学习目标跟踪

程帅; 孙俊喜; 曹永刚; 刘广文; 韩广良

doi:10.11999/JEIT150319

多示例深度学习目标跟踪

doi: 10.11999/JEIT150319

1.
(长春理工大学电子信息工程学院长春 130022) ②(东北师范大学计算机科学与信息技术学院长春 130117) ③(中国科学院长春光学精密机械与物理研究所长春 130000)

基金项目:

国家自然科学基金(61172111)和吉林省科技厅项目(20090512, 20100312)

计量
- 文章访问数: 2306
- HTML全文浏览量: 176
- PDF下载量: 1781
- 被引次数: 0
出版历程
- 收稿日期: 2015-03-17
- 修回日期: 2015-07-27
- 刊出日期: 2015-12-19

Target Tracking Based on Multiple Instance Deep Learning

1.
(School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun 130022, China)
2.
(School of Computer Science and Information Technology, Northeast Normal University, Changchun 130117, China)

Funds:

The National Natural Science Foundation of China (61172111)

摘要

摘要: 为解决多示例跟踪算法中外观模型和运动模型不足导致跟踪精度不高的问题，该文提出多示例深度学习目标跟踪算法。针对原始多示例跟踪算法中采用Haar-like特征不能有效表达图像信息的缺点，利用深度去噪自编码器提取示例图像的有效特征，实现图像信息的本质表达，易于分类器正确分类，提高跟踪精度。针对多示例学习跟踪算法中选取弱特征向量不能更换，难以反映目标自身和外界条件变化的缺点，在选择弱分类器过程中，实时替换判别力最弱的特征以适应目标外观的变化。针对原始多示例跟踪算法中运动模型中仅假设帧间物体运动不会超过某个范围，不能有效反映目标的运动状态的缺点，引入粒子滤波算法对目标进行预测，提高跟踪的准确性。在复杂环境下不同图片序列实验结果表明，与多示例跟踪算法及其他跟踪算法相比，该文算法具有更高跟踪精确度和更好的鲁棒性。
- 目标跟踪 /
- 多示例学习 /
- 深度学习 /
- 弱特征更换 /
- 粒子滤波
Abstract: To overcome the problem that the deficiency of the appearance model and the motion model often leads to low precision in original Multiple Instance Learning (MIL), a target tracking algorithm is proposed based on multiple instance deep learning. In original MIL algorithm, the image is not represented effectively by Haar-like feature. To improve the tracking precision, a stacked denoising autoencoder is used to learn image features and express the image representations obtained effectively. Selected feature vector could not be replaced in the original MIL algorithm, which has difficulty reflecting the changes of the target and the background．Thus, some weakest discriminative feature vector is replaced with new randomly generated feature vector when weak classifiers are selected. It introduces new information to the target model and adapts to the dynamic changes of the target. Aiming at the deficiency of using motion model where the location of the target is likely to appear within a radius in original MIL algorithm, the particle filter estimates objects location to increase the tracking precision. Compared with the original MIL algorithm and other state-of-the-art trackers in the complex environment, the experiments on variant image sequences show that the proposed algorithm raise the tracking accuracy and the robustness.
- Target tracking /
- Multiple instance learning /
- Deep learning /
- Weak classifier replacement /
- Particle filter

HTML全文

参考文献(27)

Wu Y, Lim J, and Yang M H. Online object tracking: a benchmark[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2013: 2411-2418.

Ross D A, Lim J, Lin R S, et al.. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77(3): 125-141.

Zhang K, Zhang L, and Yang M H. Fast compressive tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10): 2002-2015.

Zhong W, Lu H C, and Yang M H. Robust object tracking via sparse collaborative appearance model[J]. IEEE Transactions on Image Processing, 2014, 23(5): 2356-2368.

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.

Chen S, Su S Z, Li S Z, 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.

Zhang K, Zhang L, Liu Q, et al.. Fast tracking via dense spatio-temporal context learning[C]. Proceedings of European Conference on Computer Vision, Zurich, Switzerland, 2014: 127-141.

Kalal Z, Mikolajczyk K, and Matas J. Tracking- learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422.

Babenko B, Yang M H, and Belongie S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1619-1632.

Zhang K H and Song H H. Real-time visual tracking via online weighted multiple instance learning[J]. Pattern Recognition, 2013, 46(1): 397-411.

陈东成, 朱明, 高文, 等. 在线加权多示例学习实时目标跟踪[J]. 光学精密工程, 2014, 22(6): 1661-1667.

Chen D C, Zhu M, Gao W, et al.. Real-time object tracking via online weighted multiple instance learning[J]. Optics and Precision Engineer, 2014, 22(6): 1661-1667.

宁纪锋, 赵耀博, 石武祯. 多通道Haar-like特征多示例学习目标跟踪[J]. 中国图象图形学报, 2014, 19(7): 1038-1045.

Ning J F, Zhao Y B, and Shi W Z. Multiple instance learning based object tracking with multi-channel haar-like feature[J]. Journal of Image and Graphics, 2014, 19(7): 1038-1045.

郑胤, 陈权崎, 章毓晋. 深度学习及其在目标和行为识别中的新进展[J]. 中国图像图形学报, 2014, 19(2): 175-184.

Zheng Y, Chen Q, and Zhang Y. Deep learning and its new progress in object and behavior recognition[J]. Journal of Image and Graphics, 2014, 19(2): 175-184.

Vincent P, Larochellel H, Lajoie I, et al.. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11: 3371-3408.

程帅, 曹永刚, 孙俊喜, 等. 基于增强群跟踪器和深度学习的目标跟踪[J]. 电子与信息学报, 2015, 37(7): 1646-1653.

Cheng S, Cao Y G, Sun J X, et al.. Target tracking based on enhanced flock of tracker and deep learning[J]. Journal of Electronics Information Technology, 2015, 37(7): 1646-1653.

Hinton G E and Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.

Rob H and Alan F. Discriminatively trained particle filters for complex multi-object tracking[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 240-247.

李天成, 孙树栋. 采用双重采样的移动机器人Monte Carlo定位方法[J]. 自动化学报, 2010, 36(9): 1279-1286.

Li T C and Sun S D. Double-resampling based monte carlo localization for mobile robot[J]. Acta Automatica Sinica, 2010, 36(9): 1279-1286.

Torralba A, Fergus R, and Freeman W T. 80 million tiny images: a large data set for nonparametric object and scene recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(11): 1958-1970.

Olshausen B and Field D. Sparse coding with an overcomplete basis set: a strategy employed by V1[J]. Vision Research, 1997, 37(23): 3311-3326.

Dinh T B, Vo N, and Medion G. Context tracker: exploring supporters and distracters in unconstrained environments[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2011: 1177-1184.

Zhang T, Ghanem B, Liu S, et al.. Robust visual tracking via multi-task sparse learning[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 2042-2049.

施引文献

资源附件(0)

访问统计