Target detection automatic labeling method and device based on moving object detection

Abstract

The invention provides a target detection automatic labeling method and device based on moving object detection, and the method comprises the steps: employing a scene classifier to determine the scene category of a to-be-detected video, selecting at least one moving object detection algorithm having a corresponding relationship with the scene category, and enabling the to-be-detected video to comprise the same type of moving objects; detecting a moving object in a plurality of frames of pictures of the to-be-detected video through at least one moving object detection algorithm, and marking a target box for the detected moving object; tracking the moving object in the multi-frame picture by adopting a preset target tracking algorithm, and marking a target box for the tracked moving object; and removing the overlapped target frames on the moving object in the multi-frame picture by adopting a preset algorithm, and taking the remaining target frames as a final labeling result of the moving object. By adopting the automatic labeling method provided by the scheme of the invention, the labor cost of target detection labeling can be greatly saved, the efficiency is higher than that of a traditional pure manual labeling method, and the labor cost is effectively saved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for automatic labeling of target detection based on moving object detection. Background technique [0002] At present, object detection based on machine learning or deep learning is very popular and has become the main visual perception method in the field of autonomous driving. In the prior art, whether using machine learning or deep learning, the training of target detection models requires a large number of images and annotation operations, and manual annotation is mainly used for annotation. The labor cost of labeling is huge, so how to save the labor cost of target detection and labeling is the current problem. SUMMARY OF THE INVENTION [0003] In view of the above problems, the present invention is proposed to provide a method and apparatus for automatic target detection and labeling based on moving object detection, which overcomes t...

AI Technical Summary

Problems solved by technology

In the prior art, regardless of whether machine learning or deep learning is used, the training of the target detection model requires a large number of pictures and labeling operations, and manual labeling is mainly used for labeling. For pictures with small objects, the required The labor cost of labeling is huge, so how to save the labor cost of target detection and labeling is the current problem

Images