Title :
Research on Localization of Apples Based on Binocular Stereo Vision Marked by Cancroids Matching
Author :
Jian, Li ; Shujuan, Cui ; Chengyan, Zhang ; Haifeng, Chen
Author_Institution :
Shaanxi Univ. of Sci. & Technol., Xi´´an, China
fDate :
July 31 2012-Aug. 2 2012
Abstract :
In order to enhance the localization accuracy of apple-picking robots´ vision system, a method based on binocular stereo vision technology marked by cancroids matching was proposed. Key problems such as camera calibration, characteristics extraction and 3D coordinate´s calculation were analyzed. The distances between apples and cameras were measured with the proposed method under different circumstances. Experimental results showed that the average relative error was about 3.54% with the help of matched cancroids when the working distance ranged between 300-1000mm. This can meet the needs of vision system of apple picking robot in most picking environments.
Keywords :
agricultural products; calibration; cameras; feature extraction; robot vision; service robots; stereo image processing; 3D coordinate calculation; apple-picking robot vision system; apples localization; binocular stereo vision technology; camera calibration; cancroids matching; characteristics extraction; localization accuracy; Calibration; Cameras; Error analysis; Robot kinematics; Robot vision systems; Stereo vision; 3D Localization; Binocular Vision; Cancroids Recognition; Stereo Matching;
Conference_Titel :
Digital Manufacturing and Automation (ICDMA), 2012 Third International Conference on
Conference_Location :
GuiLin
Print_ISBN :
978-1-4673-2217-1
DOI :
10.1109/ICDMA.2012.161