Welcome to Francis Academic Press

International Journal of Frontiers in Medicine, 2020, 2(2); doi: 10.25236/IJFM.2020.020210.

Research on object recognition and manipulator grasping strategy based on binocular vision

Author(s)

Haiyan Sheng1,2,a,*, Shimin Wei1,b, Yu Yang1,c and Xiuli Yu1,d

Corresponding Author:
Haiyan Sheng
Affiliation(s)

1College of Automation, Beijing University of Posts and Telecommunications, Beijing, China
2Century College, Beijing University of Posts and Telecommunications, Beijing, China
*Corresponding author e-mail: ashenghaiyan@ccbupt.cn, bwsmly@bupt.edu.cn, cyuyang@bupt.edu.cn, dyxl@bupt.edu.cn

Abstract

Machine vision has been successfully applied in a series of challenging environments, but at the same time, it has encountered problems[1]. In order to solve this problem, this paper presents an object recognition and manipulator grabbing strategies based on binocular vision. Our method first uses the feature point matching algorithm based on binocular vision to recognize the target, then through the detection of the target object in the image, through the extraction and recognition of the target point, the pose estimation and location of the grab point, determines which grab strategy to operate.

Keywords

binocular vision, robotic arm, feature point matching, object recognition, grab strategy

Cite This Paper

Haiyan Sheng, Shimin Wei, Yu Yang and Xiuli Yu. Research on object recognition and manipulator grasping strategy based on binocular vision. International Journal of Frontiers in Medicine (2020), Vol. 2, Issue 2: 87-92. https://doi.org/10.25236/IJFM.2020.020210.

References

[1] Wang Xinghua. Research on binocular vision recognition and location technology based on embedded system [D]. Harbin: Harbin University of technology, 2016.
[2] Lin Y, Sun Y. Robot grasp planning based on demonstrated grasp strategies[J]. International Journal of Robotics Research,2015, 34(1): 26-42.
[3] Li Shengli. Research on workpiece recognition and positioning technology based on binocular stereo vision [D]. Harbin: Harbin University of technology, 2016.
[4] Cao Zhile, Yan Zhonghong, Wang Hong.Summay of binocular stereo vision matching technologu [J]. Journal of Chongqing University of Technology: Natural Science,2015,29(2).
[5] Zhang Guangjun.Visual measurement[M].Beijing: Science Press,2008.
[6] Jiang ang. Research and implementation of stereo matching algorithm in binocular vision [D]. Tianjin University of technology, 2016.
[7] Chen Bin. Research and implementation of real-time binocular stereo matching algorithm [D]. Wuhan University of science and technology, 2014.
[8] David A.Forsyth, Jean Ponce. Computer Vision: A Modern Approach, Second Edition[M]. Beijing: Electronic Industry Press,2017.7.
[9] Lin T Y, Dollár P, Girshick R, et al. Feature Pyramid Networks for Object Detection[J]. 2016.
[10] WANG Linyu, JIANG Qiangwei, LI Shuang. Research on Fusion Matching Object Recognition and Location Based on Binocular Image Multifeature Point Fusion[J].Radio Engineering,2018,48(8):628-633.
[11] Shuhuailin. PID neural network and its control system [M]. National Defense Industry Press, 2006.
[12] Kang J, Meng W, Abraham A,et al. An adaptive PID neural network for complex nonlinear system control[J]. Neurocomputing, 2014, 135(8):79-85.