Real-Time Quality Assessment of Videos from Body-Worn Cameras
Yuan-Yi Chang, Riccardo Mazzon, Andrea Cavallaro · 2018
Videos captured with body-worn cameras may be affected by distortions such as motion blur, overexposure and reduced contrast. Automated video quality assessment is therefore important prior to auto-tagging, event or object recognition, or automated editing. In this paper, we present M-BRISQUE, a spatial quality evaluator that combines, in realtime, the Michelson contrast with features from the Blind/Referenceless Image Spatial QUality Evaluator. To link the resulting quality score to human judgement, we train a Support Vector Regressor with Radial Basis Function kernel on the Computational and Subjective Image Quality database. We show an example of application of M-BRISQUE in automatic editing of multi-camera content using relative view quality, and validate its predictive performance with a subjective evaluation and two public datasets.