Moving workpiece target unsupervised segmentation method suitable for high-dynamic light condition

Abstract

The invention relates to a moving workpiece target unsupervised segmentation method suitable for a high-dynamic light condition, which belongs to the technical field of digital image processing. Single frame superposition is carried out on acquired continuous frames of video images, and subtraction with a background image is carried out; then, an LDOF optical flow method is used for acquiring a video foreground moving target optical flow field, and according to the optical flow field, a foreground moving target boundary is acquired; and a mixed Gaussian model and a position model are built for the foreground and the background of the video image. Through the above processing, segmentation on the video foreground target is finally realized. In view of the defect that the segmentation precision of a moving target quick segmentation method in an unrestricted scene is likely influenced by a light condition, an image pre-processing method of adopting single frame superposition to make the feature information of the foreground moving target to be more outstanding is put forward, influences on the segmentation precision of the method by the light condition can be effectively reduced and the video segmentation precision is improved.

Description

technical field [0001] The invention relates to an unsupervised segmentation method for a moving workpiece target suitable for high dynamic lighting conditions, and belongs to the technical field of digital image processing. Background technique [0002] The dynamic target segmentation technology is a key technology in the industrial robot vision system. Its basic idea is to extract the foreground moving workpiece target from the video image acquired by the robot vision system, and obtain its edge contour target shape and motion information. The problem of moving object detection and segmentation has always occupied an extremely important position in the fields of machine vision technology and pattern recognition. The segmentation of moving objects is developed on the basis of static image processing technology, and its development is late, and it is a difficult point. The research on the segmentation of moving objects has always been a very challenging direction. With the ...

AI Technical Summary

Problems solved by technology

[0004] The invention provides an unsupervised segmentation method for moving workpiece targets suitable for high dynamic lighting conditions. The method proposes a single-frame superposition method for the shortcoming that the segmentation accuracy of the fast segmentation method for moving targets in unrestricted scenes is easily affected by lighting conditions. The image preprocessing method that highlights the feature information of the foreground moving target effectively reduces the impact of lighting conditions on the segmentation accuracy of the method and improves the accuracy of video segmentation

Images