Method and system for retrieving specified object based on multi-feature fusion

Abstract

The invention provides a method and a system for retrieving a specified object based on multi-feature fusion. The method comprises the following steps of: acquiring an image to be retrieved; carrying out a template matching between the image to be retrieved and a sample image containing the specified object based on color to determine degree of color similarity, and processing the next step if the degree of color similarity exceeds a set threshold; making a comparison on minor features between the image to be retrieved and the sample image and determining degree of similarity of the minor features, wherein the minor features include at least one of texture feature and shape feature; and finally, making a comprehensive judgment and acquiring a comprehensive degree of similarity between a retrieval object in the image to be retrieved and the specified object. The result can also be obtained by extracting minor features from a matching area of the image to be retrieved and making a comparison between the extracted minor features and minor features of the sample image containing the specified object. By a cascaded approach, a similar region between the sample image and the image to be retrieved from coarse to fine can be gradually and accurately determined, the effect of fast, efficient and accurate retrieval is achieved, and manpower and material resources are saved.

Description

technical field [0001] The invention relates to the technical field of image processing and information retrieval, in particular to a method and system for specifying target retrieval based on multi-feature fusion. Background technique [0002] With the construction of large-scale security monitoring systems such as "Safe City" and "Smart City", the amount of surveillance video data is increasing. How to quickly and accurately retrieve the required images and videos from the massive image and video data has become an increasingly important task. Important issues. [0003] For example, with the rapid development of national road traffic construction and the popularization of motor vehicles, criminal and public security cases related to roads and motor vehicles have increased year by year, especially hit-and-run cases, theft of motor vehicles, and vehicle smuggling via the intercity road network etc. are becoming more and more rampant, which not only poses a great threat to s...

AI Technical Summary

Problems solved by technology

[0011] In order to overcome the problems existing in the existing multi-feature fusion retrieval methods such as slow speed, accumulation of unfavorable factors of each feature, and high false detection rate, the present invention provides a designated target retrieval method and system based on multi-feature fusion, through cascaded The method makes full use of the advantages of each feature, gradually determines the retrieval target from coarse to fine, and can gradually and accurately determine the similar area in the specified target sample image and the image to be retrieved, instead of a direct comparison between the two images, to achieve Fast and efficient and accurate retrieval effect, saving manpower and material resources

Images