Location and Recognition Fruit Trees Based on Binocular Stereo Vision
In order to improve pesticide utilization rate and reduce the environmental pollution caused by pesticide ground loss, this paper proposes to use binocular vision to recognize the contour and distance information of fruit trees. To improve the recognition accuracy and speed, focusing on the optimization of SIFT stereo matching algorithm. A method for matching the feature points of left and right images base on cosine distance and the vector modulus is proposed. On this basis, two stereo matching algorithms are compared, The accuracy of the Improved SIFT stereo matching algorithm is improved by 1.53%, With this method, the recognition time is almost unchanged, And the stability of depth measurement is analyzed. When the target distance sensor is 180 cm–220 cm, the standard deviation is 1.3592 cm, can meet the requirements of the work.
KeywordsImage recognition Binocular vision Stereo match Visual location
This research was financially supported by the National Key R&D Program of China (2016YFD0200604).
- 1.Li, L., Li, H., He, X., et al.: Development and experiment of automatic detection device for infrared. Trans. Chin. Soc. Agric. Eng. 28(12), 159–163 (2012)Google Scholar
- 2.Zhai, C., Zhao, C., Wang, X., et al.: Probing method of tree spray target profile. Trans. CSAE 26(12), 173–177 (2010)Google Scholar
- 6.Rao, H.: Study on crop spraying control based on machine vision. J. Nanjing Agric. Univ. 30(1), 120–123 (2007)Google Scholar
- 8.Cai, J., Sun, H., Li, Y.: Three dimensional information acquisition and reconstruction based on binocular stereo vision. Chin. J. Agric. Mach. 43(3), 152–156 (2012)Google Scholar
- 9.Doerr, Z., Lague, C.: Evaluating the ability to detect foreign objects in crops using range scanners mounted on agricultural vehicles. In: ASABE Annual International Meeting, Nevada, 21–24 June 2009Google Scholar
- 10.Zou, L., Li, Y.: A method of stereo vision matching based on Open CV. In: Proceedings of 2010 International Conference on Audio Language and Image Processing (ICALIP), pp. 185–190. IEEE, Piscataway (2010)Google Scholar
- 11.Spampinato, G., Lidholm, J., Ahlberg, C., et al.: An embedded stereo vision module for industrial vehicles automation. In: 2013 IEEE International Conference on Industrial Technology (ICIT), pp. 52–55. IEEE, Piscataway (2013)Google Scholar
- 12.Ganganath, N., Leung, H.: Mobile robot localization using odometry and Kinect sensor. In: 2010 IEEE International conference on Emerging Signal Processing Applications (ES-PA), NJ, USA, pp. 91–94 (2010)Google Scholar
- 13.Bradley, D., Heidrich, W.: Binocular camera calibration using rectification error. In: 2010 Canadian Conference on Computer and Robot Vision (CRV), pp. 183–190. IEEE (2010)Google Scholar
- 14.Shuai, Z.: Research on the Error Theory of Binocular Vision measurement system on Non-cooperative Targe. Changchun: Changchun Institute of Optics, fine Mechanics and Physics, Chinese Academy of Sciences (2014)Google Scholar
- 15.Ravari, A.R.N., Taghirad, H.D., Tamjidi, A.H.: Vision-based fuzzy navigation of mobile robots in grassland environments. In: Proceedings of International Conference on Advanced Intelligent Mechatronics.[S. I.]. IEEE/ASME Press (2009)Google Scholar