Method for registering target contour point cloud based on monocular depth sensor and mechanical arm

Abstract

The invention discloses a method for registering a target contour point cloud based on a monocular depth sensor and a mechanical arm. The monocular depth sensor (2) is loaded on the end of a robot arm(1). A host computer (3) controls the robot arm to accurately move a sampling position, controls the monocular depth camera to capture the target contour point cloud and preprocesses the target contour point cloud, and marks the current point cloud as a source point cloud S. The rotation angle values of each axis of the current robot arm (1) are obtained through a control cabinet (4). The robot arm (1) is modeled according to the kinematics theory, and the base coordinate system-based posture of the monocular depth sensor at the current sampling point is calculated. An improved iterative nearest point algorithm is used to complete precise registration of the point cloud in the S and D views, and the registered point cloud is marked as the source point cloud S. Steps S4 and S5 are repeatedly executed, and the point cloud under the next view is again registered until the model of the target contour point cloud is complete, and the registration then terminates.

Description

technical field [0001] The invention relates to the field of robot technology and computer vision, in particular to a method for registering target contour point clouds based on a monocular depth sensor and a mechanical arm. Background technique [0002] The 3D point cloud model is an important part of computer vision, and it is a hot issue to be studied and solved in the interaction between intelligent robots and unknown environments. The monocular depth vision system generally uses infrared rays to emit to the target, and calculates the depth information by receiving the returned light waves. There are time-of-flight methods, structured light methods, etc. When the robot arm recognizes the target object or locates the contour of the target object, it needs to obtain all the contour information of the target under different viewing angles, so it is necessary to register the point clouds collected under different viewing angles. In larger cases, the point cloud registration...

AI Technical Summary

Problems solved by technology

When the robot arm recognizes the target object or locates the contour of the target object, it needs to obtain all the contour information of the target under different viewing angles, so it is necessary to register the point clouds collected under different viewing angles. In larger cases, the point cloud registration can be completed quickly and efficiently, and the target contour can be accurately positioned at the same time

However, the continuous acquisition of the depth sensor, the calculation of the step-by-step matching criterion is complex, and the requirements for the hardware platform are relatively high.

Images