Person Following of a Mobile Robot Using Kinect through Features Detection Based on SURF

Abstract:

Following a person is an important task for domestic service robots in applications in which human-robot interaction is a primary requirement. Two steps will be completed if the robot needs to achieves this task. It includes detecting the target person and following it. Thus, the robot needs applicable algorithm and specific sensor. In this paper features detection and following technology based on SURF (Speed Up Robust Features) algorithm is used for person following in domestic environments. The vision system of robot obtains very good features of the target person through the RGB camera of kinect (Kinect sensor device) using SURF algorithm. And the depth camera of kinect helps the robot obtain the accurate information about the position of the target person in the environment. It uses SURF algorithm to extract the features of the target person, and match them in following frames. The proposed method is programmed in high speed hardware system and using small zone person following method in order to meet the real time requirement. Experimental results are provided to demonstrate the effectiveness of the proposed approach.

• Periodical: Advanced Materials Research (Volumes 542-543)
• Pages: 779-784
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.542-543.779
• Online since: June 2012
• Authors: Wan Mi Chen, Sheng Guo
• Keywords: Feature Extraction, KINECT, Person Following, SURF

References

[1] N. Bellotto and H. Hu. Multisensor integration for human-robot interaction. The IEEE Journal of Intelligent Cybernetic Systems. (2005)

[2] T. Darrell, G. Gordon, M. Harville, and J. Woodfill. Integrated person tracking using stereo, color, and pattern detection. International Journal of Computer Vision. Vol.37(2) (2000), p.175–185

DOI: 10.1109/cvpr.1998.698667

[3] H. Kwon, Y. Yoon, J. B. Park, and A. C. Kak. Person tracking with a mobile robot using two uncalibrated independently moving cameras. In Proc. of IEEE Int. Conf. on Robotics and Automation (ICRA) (2005)

DOI: 10.1109/robot.2005.1570550

[4] Huiyu Zhou，Yuan Yuan，Chunmei Shi. Object tracking using SIFT features and mean shift [J]. Computer Vision and Image Understanding. Vol.113 (2009), pp.345-352

DOI: 10.1016/j.cviu.2008.08.006

[5] Ta, D N, Chen,W C, Gelfand, N, Pulli, K.SURFTrac: Efficient Tracking and Continuous Object Recognition using Local Feature Descriptors[C]. Computer Vision and Pattern Recognition(CVPR'09). (2009), pp.2937-2943

DOI: 10.1109/cvpr.2009.5206831

[6] Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool, SURF: Speeded Up Robust Features, Computer Vision and Image Understanding (CVIU). Vol. 110(3) (2008), pp.346-359

DOI: 10.1016/j.cviu.2007.09.014

[7] Xu Bo, Wang Junwen, Liu Guangjie and Dai Yuewei. Image Copy-move Forgery Detection Based on SURF. Multimedia Information Networking and Security (MINES), 2010 International Conference on. (2010) pp.889-890

DOI: 10.1109/mines.2010.189

[8] Bay H, Tuytelars T, Van Gool L. Speeded-Up Robust Features(SURF)[J]. Computer Vision and Image Understanding. Vol.110 (2008), pp.346-359

DOI: 10.1016/j.cviu.2007.09.014

[9] Shan An, Xin Ma, Rui Song and Yibin Li. Face Detection and Recognition with SURF for Human-Robot Interaction. Proceedings of IEEE International Conference on Automation and Logistics. (Shenyang, China August 2009)

DOI: 10.1109/ical.2009.5262624

[10] David G. Lowe. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision. Vol.60(2) (2004), pp.91-110

DOI: 10.1023/b:visi.0000029664.99615.94

[11] Mikolajczyk K, Schmid C. An affine invariant interest point detector[J]. Computer Vision-ECCV. Vol.2350 (2002), pp.128-142

DOI: 10.1007/3-540-47969-4_9