Target Recognition Method Based on Quality Evaluation

Abstract

The invention provides a target identification method based on quality evaluation. The target identification method based on quality evaluation includes the steps: constructing a target identificationmodel which includes a quality evaluation network, a feature extraction network, and a feature aggregation network, wherein the target identification model is used for extracting the target feature from a video so as to characterize the overall structural information and local information of the target; training the target identification model, and adjusting the parameters of the quality evaluation network and the feature extraction network during the training process so as to enable the target identification model to output the target feature according with the preset demand; and performingtarget identification on the video through the trained target identification model. Therefore, the target identification method based on quality evaluation solves the target identification problem caused by changeable appearance and irregular image quality in a video sequence, and adds the interframe correlation information in quality evaluation so as to obtain more effective target information toenable characterization of the target to be more accurate, thus improving the identification accuracy.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for object recognition based on quality evaluation. Background technique [0002] The rise of a series of applications such as face recognition and behavior analysis shows that object recognition is playing an increasingly important role in real life. In object recognition tasks, it is often necessary to recognize the same object from cameras of different angles and scenes. In the case of cross-camera, the appearance of the target is often quite different, which poses a great challenge to the robustness of the recognition algorithm. In recent years, although the existing recognition algorithms have achieved good results in the experimental environment, these recognition algorithms are not satisfactory in the real uncontrollable scene. This is because the quality of the data collected in the experimental environment is often better. In the deliberate sh...

AI Technical Summary

Problems solved by technology

However, it regards video frames as separate individuals and ignores the connection between video frames, which limits the performance of target recognition.

Images