Super pixels and structure constraint based image's multiple targets synchronous segmentation method

Abstract

The present invention discloses a super pixels and structure constraint based image's multiple targets synchronous segmentation method. The method is applied to a set of images with shared targets, and each of the images is allowed to have more than more shared target. With this method, the shared targets can be precisely segmented. Firstly, a pre-segmentation operation is performed to the inputted set of images to develop segmented images. Then, based on a target detection mechanism, all super pixels are classified as background ones and foreground ones. With it, foreground classifiers are developed. Based on results from the classifiers, models are established for foreground targets and precise segmentation is fulfilled to targets by an optimized algorithm utilizing forest model assumptions and beam constraints. Compared to current algorithms, the method of the invention adopts an optimized algorithm utilizing forest model assumptions and beam constraints, which provides increased segmentation accuracy and makes the method capable of dealing with various complex scenarios.

Description

technical field [0001] The invention relates to an image multi-object cooperative segmentation method based on superpixels and structural constraints, which is applicable to the fields of multi-object cooperative segmentation of pictures, object segmentation in sports pictures, picture classification and recognition, and the like. Background technique [0002] In the field of computer vision, image segmentation is a basic and classic problem, and its solution can play a very good auxiliary role in many other image processing problems such as target recognition and object classification. In practical applications, areas such as intelligent monitoring, medical diagnosis, robotics and intelligent machines, industrial automation and even military guidance are closely related to image segmentation. With the help of the Internet, people can easily obtain a large number of pictures containing the same object or objects of the same category, and how to automatically identify and seg...

AI Technical Summary

Problems solved by technology

[0003] 1) The existing methods mainly use the underlying features such as color and shape, while ignoring the high-level features based on superpixels that can be learned, as well as the structural constraints of objects in multi-target scenes;

[0004] 2) Most of the current mainstream algorithms are designed for single-object segmentation, and the effect of multi-object segmentation is often unsatisfactory, and there is no targeted optimization;

[0005] 3) The scalability of most methods is not ideal and cannot solve the processing of large databases

Images