A New Quality Model For Object Detection Using Compressed Videos

In distributed sensing systems that use compressed videos for video analysis tasks, the lossy compression of videos can damage the accuracy of object detection, which is an essential step for various vision applications. This paper aims at constructing a new quality model to predict the performance of object detection. To achieve this goal, a distorted video database is constructed by applying object detection algorithms on a variety of videos that are compressed with different levels of distortion. Based on the database, a parametric quality prediction model is built using features that can be easily obtained during the encoding process. Experimental results show that the model can achieve high accuracy in predicting the performance of object detection. The model introduces low computation cost and can be easily integrated in video encoders for rate-quality optimization.