Partial Object Recognition for Improving Novelty Detection in Videos

One of the major issues in novelty detection for video and image analysis application is how to recognize objects that are not in full view. As the camera pans, tilts and zooms, image objects within a scene are never in full view and enter and exit image frames with time. These objects with partial view do not contain enough number of pixels that can generate robust color, texture and statistical features, and therefore result in classification samples that are often not representative of that class, e.g. outliers. From a data analysis point of view, it is impossible to known which samples are truly outliers because of partial view as opposed to outliers because of mistakes in object labeling. This can cause serious problems in novelty detection tasks using neural networks. In this paper we propose a novel methodology for automatically detecting image objects with partial view and discuss how to use this knowledge to improve novelty detection results.