Cross-camera video concentration method based on pedestrian re-identification

Abstract

The invention belongs to the technical field of video processing, and specifically relates to a cross-camera video concentration method based on pedestrian re-identification. The specific steps are asfollows: (1) using multiple segments of obtained videos shot by different cameras as input, and finally outputting multiple segments of concentrated videos; and (2) based on the multiple segments ofconcentrated videos obtained in a video concentration phase, in view of a specific target object, firstly searching for specific locations of the target object appearing in different videos in the concentrated videos according to a corresponding matching measurement method, and extracting concentrated video segments containing the target object to obtain the description of a coherent motion trajectory of the target object in the multiple videos. By adoption of the method of the invention, a lot of manpower can not only be saved, and the identification accuracy of the target object is also improved to some extent. The method proposed by the invention has an important value for practical application.

Description

technical field [0001] The invention belongs to the technical field of video processing, and in particular relates to a cross-camera video concentration method based on pedestrian re-identification. Background technique [0002] Since entering the digital age in the last century, tens of thousands of surveillance cameras have been deployed at transportation hubs such as railway stations, airports, and urban traffic intersections, and are working 24 hours a day. The number of surveillance videos has grown explosively. trend. In addition, surveillance video plays an increasingly important role in practical applications such as intelligent security, traffic management, and criminal investigation. Therefore, surveillance videos that are concise and contain rich information are of great value for storing or viewing surveillance videos. [0003] However, a large number of lengthy surveillance videos have high requirements for video storage. In reality, many videos will be deleted...

AI Technical Summary

Problems solved by technology

The method based on feature representation represents pedestrians by extracting robust discriminative features, and matches the target object according to the features in different videos. The computational complexity of this method is relatively simple, but the effect is not ideal.

The distance metric learning method calculates the image distance of corresponding objects between videos by learning a discriminative distance metric function, so that the distance between images of the same object is smaller than the distance between images of different objects. Although this type of method improves the recognition accuracy, but Often requires a complex learning process

Images