Dynamic Targets Detection for Robotic Applications Using Panoramic Camera Based on Optical Flow

Abstract:

Optical flow method is an important and valid method in the field of detection and tracking of moving objects for robot inspection system. Due to the traditional Horn-Schunck optical flow method and Lucas-Kanade optical flow method cannot meet the demands of real-time and accuracy simultaneously, an improved optical flow method based on Gaussian image pyramid is proposed. The layered structure of the images can be obtained by desampling of the original sequential images so that the motion with the high speed can be changed into continuous motion with lower speed. Then the optical flows of corner points of the lowest layer will be calculated by the LK method and be delivered to the upper layer and so on. Thus the estimated optical flow vectors of the original sequential images will be obtained. In this way, the requirement of accuracy and real time could be met for robotic moving obstacle recognition.

• Periodical: Applied Mechanics and Materials (Volume 376)
• Pages: 455-460
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.376.455
• Online since: August 2013
• Authors: Wei Zhu, Li Tian, Fang Di, Jian Li Li, Ke Jie Li
• Keywords: Dynamic Targets Detection, Gaussian Image Pyramid, Harris Corner Detection Algorithm, Optical Flow Method, Panoramic Annular Image, Robotic Obstacle Recognition

References

[1] Hu Yijing, Li Zhengfang, Theories and applications of motion analysis based on optical flow J. Computer Measurement & Control, v 15, n 2, pp.219-21, (2007).

[2] Shizhu Pan, Weiqun Shu, Real-time motion detection based on adaptive background J. Advances on Applied Computer and Applied Computational Science, pp.330-5, (2008).

[3] Anderson C, Burt P, Change detection and tracking using pyramid transform techniques C. Proceedings of the SPIE, v 579, pp.72-8 (1985).

[4] Barron J, Fleet D, Performance of optical flow techniques J. International Journal of Computer Vision, v 12, n 1, (1994).

[5] Horn Berthold K P, Schunck Brain G. Determining optical flow J. Artificial Intelligence, v 17, n 123, pp.185-203, (1981).

DOI: 10.1016/0004-3702(81)90024-2

[6] Shen shi, Zhang Xiaolong, Heng Wei, Improved Harris corner detection algorithm based on auto-adaptive threshold and pre-selection J. Journal of Data Acquisition & Processing. v 26, n 2, pp.209-213.

[7] Xiahou Yujiao, Gong Shengrong, Liu Chunping, Liu Chuang, Video object segmentation algorithm based on Gaussian distribution with LK optical flow method J. Microelectronics & Computer. v 26, n 6, pp.239-245.

[8] Chey, J., Grossberg, S. & Mingolla, E., Neural Dynamics of Motion Grouping: From Aperture Ambiguity to Object Speed and Direction, J. Journal of the Optical Society of America v 14, n 10, pp.2570-2594, (1997).

DOI: 10.1364/josaa.14.002570