自适应多尺度颜色特征目标跟踪算法研究

为了解决尺度变化对目标跟踪的影响, 本文在颜色特征跟踪算法的基础下提出了一种多尺度目标跟踪算法。该算法通过训练位置和尺度两个相关滤波器以实现自适应尺度跟踪。首先通过最小二乘分类器学习获得位置相关滤波器, 采用主成分分析法对颜色特征进行降维, 计算响应的最大值作为下一帧目标中心位置; 接着根据设定的尺度因子在中心位置周围形成多个大小不一的矩形区域, 并计算每个区域的颜色特征; 学习每个区域的颜色特征, 获得尺度相关滤波器, 并采用正交三角分解对尺度相关滤波器进行降维; 然后根据响应的最大值确定跟踪目标的尺寸; 最后对目标的位置和尺寸进行更新。通过对13组挑战性的视频序列进行测试, 结果表明, 本算法不仅对目标尺度变化具有一定的适应性, 而且对光照变化、快速运动、运动模糊等复杂情况下, 均具有鲁棒性, 多项性能指标均优于目前跟踪性能先进的算法。

Abstract

In order to solve the influence of scale change on target tracking, a multi-scale target tracking algorithm was proposed based on the color feature tracking algorithm. The algorithm realized adaptive scale tracking by training position and scale correlation filters. Firstly, the target center position of next frame was obtained by computing the maximum of the response, where the position correlation filter was learned by the least squares classifier and the dimensionality reduction for color features was analyzed by principal component analysis. The scale correlation filter was obtained by color characteristics at 33 rectangular areas which was set by the scale factor around the central location and reduced dimensions by orthogonal triangle decomposition. Finally, the location and size of the target were updated by the maximum of the response. By testing 13 challenging video sequences, the results show that the algorithm has adaptability to the changes in the target scale and its robustness along with many other performance indicators are both better than the most state-of-the-art methods in illumination variation, fast motion, motion blur and other complex situations.

参考文献

[1] RAZAVI S F, SAJEDI H, SHIRI M E. Integration of colour and uniform interlaced derivative patterns for object tracking [J]. IET Image Processing, 2016, 10(5): 381-390.

[2] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.

[3] 胡良梅, 段琳琳, 张旭东, 等．融合颜色信息与深度信息的运动目标检测方法[J]．电子与信息学报, 2014, 36(9): 2047-2052．

HU L M, DUAN L L, ZHANG X D, et al. Moving object detection based on the fusion of color and depth information [J]. Journal of Electronics & Information Technology, 2014, 36(9): 2047-2052. (in Chinese)

[4] WANG S, CLARK R, WEN H K, et al. DeepVO: Towards end-to-end visual odometry with deep recurrent convolutional neural networks [C]//2017 IEEE International Conference on Robotics and Automation. Singapore: IEEE, 2017: 2043-2050.

[5] 刘林涛, 董雪莹, 刘俊, 等．基于时空上下文和随机森林的人眼跟踪定位算法研究[J]．液晶与显示, 2018, 33(5): 443-449．

LIU L T, DONG X Y, LIU J,et al. Human eye locating and tracking using space-time context and random forest [J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(5): 443-449. (in Chinese)

[6] AMMIRATO P, POIRSON P, PARK E,et al. A dataset for developing and benchmarking active vision [J]. arXiv preprint arXiv: 1702.08272, 2017.

[7] 龙思源, 张葆, 宋策, 等．基于改进的加速鲁棒特征的目标识别[J]. 中国光学, 2017, 10(6): 719-725.

LONG S Y, ZHANG B, SONG C, et al. Object detection based on improved speeded-up robust features [J]. Chinese Optics, 2017, 10(6): 719-725. (in Chinese)

[8] KHAN F S, VAN DE WEIJER J, VANRELL M. Modulating shape features by color attention for object recognition [J]. International Journal of Computer Vision, 2012, 98(1): 49-64.

[9] KHAN F S, ANWER R M, VAN DE WEIJER J,et al. Color attributes for object detection [C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE, 2012: 3306-3313.

[10] DANELLJAN M, KHAN F S, FELSBERG M,et al. Adaptive color attributes for real-time visual tracking [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014: 1090-1097.

[11] COSTANTE G, MANCINI M, VALIGI P,et al. Exploring representation learning with CNNs for frame-to-frame ego-motion estimation [J]. IEEE Robotics and Automation Letters, 2016, 1(1): 18-25.

[12] NING J, ZHANG L, ZHANG D,et al. Scale and orientation adaptive mean shift tracking [J]. IET Computer Vision, 2012, 6(1): 52-61.

[13] VOJIR T, NOSKOVA J, MATAS J. Robust scale-adaptive mean-shift for tracking [J]. Pattern Recognition Letters, 2014, 49: 250-258.

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

[15] 王民, 石新源, 王稚慧．基于Vibe和时空上下文的运动手势跟踪算法[J]．液晶与显示, 2018, 33(1): 92-98．

WANG M, SHI X Y, WANG Z H.Moving gesture tracking algorithm based on vibe and space-time context [J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(1): 92-98. (in Chinese)

[16] MOJSILOVI A. A computational model for color naming and describing color composition of images [J]. IEEE Transactions on Image Processing, 2005, 14(5): 690-699.

[17] VAN DE WEIJER J, SCHMID C, VERBEEK J, et al. Learning color names for real-world applications [J]. IEEE Transactions on Image Processing, 2009, 18(7): 1512-1523.

[18] CLARK R, WANG S, WEN H K, et al. VINet: Visual-inertial odometry as a sequence-to-sequence learning problem [C]//Thirty-First AAAI Conference on Artificial Intelligence. San Francisco, California: AAAI, 2017.

[19] COMANICIU D, MEER P, RAMESH V. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.

[20] CHATFIELD K, SIMONYAN K, VEDALDI A, et al. Return of the devil in the details: Delving deep into convolutional nets [EB/OL]. arXiv preprint arXiv: 1405.3531, 2014.

[21] ORON S, BAR-HILLEL A, LEVI D, et al. Locally orderless tracking [C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE, 2012: 1940-1947.

[22] VAN DE WEIJER J, SCHMID C, VERBEEK J. Learning color names from real-world images [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, Minnesota, USA: IEEE, 2007: 1-8.

[23] CLARK R, WANG S, MARKHAM A, et al. VidLoc: 6-dof video-clip relocalization [EB/OL]. arXiv preprint arXiv: 1702.06521, 2017.

[24] COMANICIU D, RAMESH V, MEER P. Real-time tracking of non-rigid objects using mean shift [C]//IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, SC, USA: IEEE, 2000: 142-149.

[25] JADERBERG M, SIMONYAN K, ZISSERMAN A, et al. Spatial transformer networks [EB/OL]. arXiv: 1506.02025, 2015.

[26] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 770-778.

李晓云, 何秋生, 张卫峰, 梁慧慧, 陈伟. 自适应多尺度颜色特征目标跟踪算法研究[J]. 液晶与显示, 2019, 34(3): 291. LI Xiao-yun, HE Qiu-sheng, ZHANG Wei-feng, LIANG Hui-hui, CHEN Wei. Adaptive multi-scale color feature target tracking algorithm[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(3): 291.

自适应多尺度颜色特征目标跟踪算法研究

关于本站 Cookie 的使用提示

全站搜索

自适应多尺度颜色特征目标跟踪算法研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索