Machine vision-aware quality metrics for compressed image and video assessment
This addresses the need for efficient video processing in applications like surveillance and autonomous vehicles, representing an incremental improvement in quality assessment.
The paper tackled the problem of optimizing video compression for machine vision tasks like detection and recognition, introducing novel quality metrics that correlate better with machine-vision results than existing metrics.
A main goal in developing video-compression algorithms is to enhance human-perceived visual quality while maintaining file size. But modern video-analysis efforts such as detection and recognition, which are integral to video surveillance and autonomous vehicles, involve so much data that they necessitate machine-vision processing with minimal human intervention. In such cases, the video codec must be optimized for machine vision. This paper explores the effects of compression on detection and recognition algorithms (objects, faces, and license plates) and introduces novel full-reference image/video-quality metrics for each task, tailored to machine vision. Experimental results indicate our proposed metrics correlate better with the machine-vision results for the respective tasks than do existing image/video-quality metrics.