Image Processing Based on Three-Dimensional Stereo Vision

Abstract:

Three-dimensional stereo vision technology has the capability of overcoming drawbacks influencing by light, posture and occluder. A novel image processing method is proposed based on three-dimensional stereoscopic vision, which optimizes model on the basis of camera binocular vision and in improvement of adding constraints to traditional model, moreover ensures accuracy of later location and recognition. To verify validity of the proposed method, firstly marking experiments are conducted to achieve fruit location, with the result of average error rate of 0.65%; and then centroid feature experiments are achieved with error from 5.77mm to 68.15mm and reference error rate from 1.44% to 5.68%, average error rate of 3.76% while the distance changes from 300mm to 1200mm. All these data of experiments demonstrate that proposed method meets the requirements of three-dimensional imageprocessing.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 5017-5020
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.5017
• Online since: May 2014
• Authors: Ting Ting Wang*
• Keywords: Binocular Stereoscopic Vision, Location, Recognition, Three-Dimensional Image

References

[1] Satoshi Yamamoto, Ken Kobayashi, Yasushi Kohno. Evaluation of a strawberry-harvesting robot in a field test [J]. Biosystems Engineering, 2010, 15(2): 160-171.

DOI: 10.1016/j.biosystemseng.2009.09.011

[2] Bulanon D M, Kataoka T, Okamoto H, et al. Determining the 3-d location of the apple fruit during harvest[C]. Proceedings of Automation Technology for Off-Road Equipment. Japan: Kyoto, 2004: 91- 97.

DOI: 10.13031/2013.17822

[3] Zheng Xiaodong, Zhao WenJie, Liu Muhua. Tomatoes recognition and location from nature background based on binocular stereo vision [J]. Computing Engineering, 2004, 30(22): 171-173.

[4] Jiang Huanyi, Peng Yongshi, Shen Chuan. Recognizing and locating ripe tomatoes based on binocular stereovision technology [J]. Transactions of The Chinese Society of Agricultural Engineering, 2008, 24(8): 279-283.

[5] Li Jian, Zhang Chengyan, Cui Shujuan. Positioning Technology of Apple-Picking Robot Based on OpenCV[C]. Third International Conference on Digital Manufacturing & Automation, Guilin, China, 2012: 618-621.

DOI: 10.1109/icdma.2012.146