Industrial part intelligent identification and sorting system based on computer vision

Abstract

The invention provides an industrial part intelligent identification and sorting system based on computer vision. An image collector collects a two-dimensional color image and a depth information image and outputs the two-dimensional color image and the depth information image to a master control system terminal, the master control system terminal extracts the size and position information of a target in a production environment as classification features and inputs the classification features to a locally trained instance segmentation model HTC for target identification and positioning so asto obtain the position information of the target, the path planning of a mechanical arm is completed, and the posture of a mechanical clamp is determined according to the shape and size of the target;and the task of the mechanical arm and the mechanical clamp is interrupted or changed in real time according to the interaction information received in real time from the mechanical arm host and themechanical clamp host. According to the invention, the use of the industrial robot is simplified, the operation difficulty of a user is reduced, and meanwhile, the working efficiency of cooperative sorting between robots is improved.

Description

technical field [0001] The invention relates to a robot sorting technology, in particular to the industrial parts robot sorting technology based on computer vision instance segmentation. Background technique [0002] In the traditional robot sorting environment, the motion control of the robot generally adopts the method of teaching or offline programming. Most of the existing parts processing and production environments have strict requirements on the initial and final posture of the robot and the placement of the workpiece. In the actual part manufacturing and processing production line, there are some problems such as asymmetric part structure, uneven mass distribution, and overlapping and shadows caused by random placement of parts on the conveyor belt. These factors will bring interference and errors to part detection, identification and grasping , will eventually cause the robot to fail to grab the workpiece. [0003] Based on the above industrial background, the exi...

AI Technical Summary

Problems solved by technology

However, its sorting speed is slow, the efficiency is low, the action is fixed, and it cannot adapt to the changing working environment

Such as sorting of randomly placed or overlapping parts, once the position and shape of the parts change slightly, the robot will fail to grasp, thus affecting production efficiency

Images