Large-Scale Object Mining for Object Discovery from Unlabeled Video
This addresses the problem of identifying recurring object categories in raw automotive video streams for computer vision researchers, though it appears incremental as it builds on existing tracking and clustering methods.
The paper tackles object discovery from unlabeled driving videos by mining object tracks with a generic tracker, demonstrating feasibility in this challenging setting. It releases a dataset of over 360,000 object tracks from 10+ hours of video and evaluates feature representations and clustering strategies.
This paper addresses the problem of object discovery from unlabeled driving videos captured in a realistic automotive setting. Identifying recurring object categories in such raw video streams is a very challenging problem. Not only do object candidates first have to be localized in the input images, but many interesting object categories occur relatively infrequently. Object discovery will therefore have to deal with the difficulties of operating in the long tail of the object distribution. We demonstrate the feasibility of performing fully automatic object discovery in such a setting by mining object tracks using a generic object tracker. In order to facilitate further research in object discovery, we release a collection of more than 360,000 automatically mined object tracks from 10+ hours of video data (560,000 frames). We use this dataset to evaluate the suitability of different feature representations and clustering strategies for object discovery.