Depth-Sensitive Mean-Shift Method for Head Tracking

详细信息    查看全文

• 关键词：Depth image ; Mean ; shift ; Tracking ; Kinect2.0
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9773
• 期：1
• 页码：753-764
• 全文大小：1,463 KB
• 参考文献：1.Zhang, C., Liu, J., Tian, Q.: Image classification by non-negative sparse coding, low-rank and sparse decomposition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1673–1680 (2011)
  2.Li, Y., Lou, J.: Mean shift tracking algorithm with hybrid target model. IEEE Trans. Comput. Eng. Appl. 46(16), 200–203 (2010)
  3.Yuan, Y., Fang, J.W., Wang, Q.: Robust superpixel tracking via depth fusion. IEEE Trans. Circ. Syst. video Technol. 24(1), 15–26 (2014)CrossRef
  4.Rendas, M., Moura, J.: Ambiguity in Radar and Sonar. IEEE Trans. Signal Process. 46(2), 294–305 (1998)CrossRef
  5.Shan, Y., Speich, J.E., Leang, K.: Low-cost IR reflective sensors for submicrolevel position measurement and control. IEEE/ASME Trans. Mechatron. 13(6), 700–709 (2008)CrossRef
  6.Bouzit, M., Burdea, G., Popescu, G., Boian, R.: The Rutgers Master II-new design force-feedback glove. IEEE/ASME Trans. Mechatron. 7(2), 256–263 (2002)CrossRef
  7.Journet, B., Bazin, G.: A low-cost laser range finder based on an FMCW-like method. IEEE Trans. Instrum. Meas. 49(4), 840–843 (2000)CrossRef
  8.Fukanaga, K., Hostetler, L.D.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory 21(1), 32–40 (1975)MathSciNet CrossRef MATH
  9.Cheng, Y.: Meanshift, mode seeking and clustering. IEEE Trans. Pattern Anal. Mach. Intell. 17(8), 790–799 (1995)CrossRef
  10.Comaniciu, D., Ramesh, V., Meer, P.: Real-Time tracking of non-rigid objects using Meanshift. In: Werner, B. (ed.) IEEE International Proceedings of the Computer Vision and Pattern Recognition, vol. 2, pp.142−149 (2000)
  11.Yilmaz, A., Shafique, K., Shah, M.: Target tracking in airborne forward looking infrared imagery. Int. J. Image Vis. Comput. 21(7), 623–635 (2003)CrossRef
  12.Bradski G.R.: Computer vision face tracking for use in a perceptual user interface. In: Sipple, R.S. (ed.) IEEE Workshop on Applications of Computer Vision, pp. 214−219 (1998)
  13.Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25(5), 564–575 (2003)
  14.Collins R.T.: Mean-shift blob tracking through scale space. In: Danielle, M. (ed.) IEEE International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 234−240. Victor Graphics, Baltimore (2003)
  15.Li, M., Yang, Y., Liu Y.X.: Robust 3D human tracking based on kinect. In: Proceedings of the 34th Chinese Control Conference, 28–30 July 2015. IEEE (2015)
  
• 作者单位：Ning Zhang (16)
  Yang Yang (16)
  Yun-Xia Liu (17)
  
  16. School of Information Science and Engineering, Shandong University, Jinan, 250100, China
  17. School of Control Science and Engineering, Shandong University, Jinan, 250014, China
  
• 丛书名：Intelligent Computing Methodologies
• ISBN：978-3-319-42297-8
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9773

文摘

Target tracking is one of the most basic application in computer vision and it has attracted wide concern in recent years. Until now, to our best knowledge, most research focused on the tracking research with 2D images, including the Tracking-Learning-Detection (TLD), particle filter, Mean-shift algorithm, etc. While with the advanced technology and lower cost of sensors, 3D information can be used for target tracking problems in many researches and the data can be obtained by laser scanner, Kinect sensor and etc. As a new type of data description, depth information can not only obtain the spatial position information of target but also can protect privacy and avoid the influence of illumination changes. In this paper, a depth-sensitive Mean-shift method for tracking is proposed, which use the depth information to estimate the range of people’s movement and improve the tracking efficiency and accuracy effectively. What’s more, it can adjust kernel bandwidth to adapt to the target size according to the distance between target and the depth camera. In the designed system, Kinect2.0 sensor is not only used to get the depth data and track the target but also can be mobilized by steering gear flexibly when tracking. Experimental results show that these improvements make Mean-shift algorithm more robust and accurate for handling illumination problems during tracking and it can achieve the purpose of real-time tracking.