Video image quality analysis for enhancing tracker performance

Object tracking in video data is fundamental to many practical applications, including gesture recognition, activity analysis, physical security, and surveillance. A fundamental assumption is that the quality of the video stream is adequate to support the analysis. In practice, however, the video quality can vary widely due to lighting and weather, camera placement, and data compression. These factors affect the performance of object tracking algorithms. We present a method for automated analysis of the video quality which can be used to adjust the object tracker appropriately. This paper extends earlier research, presenting a model for quantifying the quality of motion imagery in the context of automated exploitation. We present a method for predicting the tracker performance and demonstrate the results on a range of video clips. The model rests on a suite of image metrics computed in real-time from the video. We will describe the metrics and the formulation of the quality estimation model. Results from a recent experiment will quantify the empirical performance of the model. We conclude with a discussion of methods for enhancing tracker performance based on the real-time video quality analysis.