Automatic identification and autonomous sorting of cylindrical parts in cluttered scene based on monocular vision 3D reconstruction

Abstract

Purpose This paper aims to propose an identification method based on monocular vision for cylindrical parts in cluttered scene, which solves the issue that iterative closest point (ICP) algorithm fails to obtain global optimal solution, as the deviation from scene point cloud to target CAD model is huge in nature. Design/methodology/approach The images of the parts are captured at three locations by a camera amounted on a robotic end effector to reconstruct initial scene point cloud. Color signatures of histogram of orientations (C-SHOT) local feature descriptors are extracted from the model and scene point cloud. Random sample consensus (RANSAC) algorithm is used to perform the first initial matching of point sets. Then, the second initial matching is conducted by proposed remote closest point (RCP) algorithm to make the model get close to the scene point cloud. Levenberg Marquardt (LM)-ICP is used to complete fine registration to obtain accurate pose estimation. Findings The experimental results in bolt-cluttered scene demonstrate that the accuracy of pose estimation obtained by the proposed method is higher than that obtained by two other methods. The position error is less than 0.92 mm and the orientation error is less than 0.86°. The average recognition rate is 96.67 per cent and the identification time of the single bolt does not exceed 3.5 s. Practical implications The presented approach can be applied or integrated into automatic sorting production lines in the factories. Originality/value The proposed method improves the efficiency and accuracy of the identification and classification of cylindrical parts using a robotic arm.

A signed pulse-train-based image processor-array for parallel kernel convolution in vision sensors

“…The evaluation results show the effectiveness of the approach in the processing of many essential and important machine vision steps such as sharpening, edge detections and Laplacian filter. The proposed hardware is suitable to be used in smart vision sensors for real time, high-speed and parallel image processing scenarios such as product line quality control (Kumar and Ratnam, 2015;Wei et al, 2019) and robot navigation (Li and Zhong, 2016;Singh and Nagla, 2019).…”

Automatic loading method for robot guided by 3D vision for scattered and stacked shoe soles

“…Guo et al [11] proposed a state-of-the-art pregrasping planning method based on point cloud processing and used the SAC-IA ICP algorithm to match the Kinect-based online target point cloud obtained from the three-dimensional reconstruction with an offline template based on a laser scanner to estimate the 6D pose of the fruit. Wei et al [12] extracted the color features of the local feature descriptor of the direction histogram (C-SHOT) from the model and the scene point cloud. The random sample consensus (RANSAC) algorithm is used to perform the first initial matching of the point set.…”