Monocular vision and calculation of regular three-dimensional target pose based on Otsu and Haar-feature AdaBoost classifier

• Published in: International journal of agricultural and biological engineering 2020-09, Vol.13 (5), p.171-180
• Main Authors: Li, Yuanhong, Wang, Hongjun, Zhou, Weiliang, Xue, Zehao
• Format: Article
• Language: English
• Subjects: Algorithms; Automation; Cameras; Classifiers; Color; Coordinates; Efficiency; Error correction; Hough transformation; Image processing; Image segmentation; Learning algorithms; Machine learning; Machine vision; Mathematical analysis; Monocular vision; Production lines; Training; Vision systems
• ISSN: 1934-6344; 1934-6352
• DOI: 10.25165/j.ijabe.20201305.5013

Using machine vision to identify and sort scattered regular targets is an urgent problem to be solved in automated production lines. This study proposed a three-dimensional (3D) recognition method combining monocular vision and machine learning algorithms. According to the color characteristics of the targets, to convert the original color picture into YCbCr mode and use the 2D Otsu algorithm to perform gray level image segmentation on the Cb channel. Then the Haar-feature training was carried out. The comparison of feature training and Haar method for Hough transform showed that the recognized time of Haar-feature AdaBoost trainer reached 31.00 ms, while its false recognized rate was 3.91%. The strong classifier was formed by weight combination, and the Hough contour transformation algorithm was set to correct the normal vector between plane coordinate and camera coordinate system. The monocular vision system ensured that the field of camera view had not obstructed while the dots were being struck. It was measured and calculated angles between targets and the horizontal plane which coordinate points of the identified plane feature. The testing results were compared with the Otsu and AdaBoost trainer where the prediction and training set have an error of no more than 0.25 mm. Its correct rate can reach 95%. It shows that the Otsu and Haar-feature based on AdaBoost algorithm is feasible within a certain error ranges and meet the engineering requirements for solving the poses of automated regular three-dimensional targets.