Moving object segmentation method based on optical flow field clustering

Abstract

The invention discloses a moving object segmentation method based on optical flow field clustering. The method is characterized in that optical flow fields of an image sequence are clustered to effectively detect and segment single or multiple moving object(s) in a complex image background. An object area is segmented by utilizing moving internal epipolar constraint and C-mean value cluster algorithm to obtain a segmentation image; a detailed target area is obtained from the segmentation image by utilizing a Canny edge operator, and an edge image is obtained; and the segmentation image is merged with the edge image according to the flow velocity in the optical flow field, and complete single or multiple moving objects is / are detected. Thus, the moving object can be reliably segmented and detected under the condition that a camera moves.

Description

technical field [0001] The present invention is related to computer graphics and image understanding. In the case of camera movement, the background of the image sequence is very complex, which brings challenges to the detection and segmentation of the target. The present invention relates to a solution to the complex background conditions. A segmentation method for moving objects, using optical flow field clustering to achieve reliable detection of single and multiple objects. Background technique [0002] Moving object detection has always been a very important research content in the fields of machine vision, image understanding and computer graphics. Under the condition of camera movement, especially when the scene is very complex, it is difficult to detect a complete moving target only by a single detection algorithm. For the case of multiple moving objects, the detection of moving objects becomes more complicated. [0003] The previous method [1] (see Thompson ...

AI Technical Summary

Problems solved by technology

Under the condition of camera movement, especially when the scene is very complex, it is difficult to detect a complete moving target only by a single detection algorithm

For the case of multiple moving objects, the detection of moving objects becomes more complicated.

[0003] The previous method [1] (see Thompson W. B, Pong T. C. Detecting moving object. Int. J. Comp. Vision, 1990, 4: 39~57) was determined by using the optical flow direction of the moving object and the inner epipolar line constraint of the movement However, in a more complex natural background, it is difficult to obtain a complete moving target only by using the inner epipolar line constraints.

[0004] The previous method [2] (see Sasa G., Loncaric S. Spatio temporal image segmentation using optical flow and clustering algorithm. First Int'l workshop on image and signal processing and analysis, Pula, Croatia: 2000, 63~68) proposed A method of object segmentation using optical flow field motion information is proposed, but it is only applied to the case of simple background and static camera.

[0005] The previous method [3] (see Adiv G.. Determining three Dimensional motion and structure from optical flow generated by several moving objects. IEEE Trans, 1985, PAMI-7(4):384-401) by using the six parameters to complete the segmentation of the optical flow field of multiple moving objects, but the calculation cost of this segmentation is quite large.

Images