Image Composition for Object Pop-out
We propose a new data-driven framework for novel object detection and segmentation, or "object pop-out". Traditionally, this task is approached via background subtraction, which requires continuous observation from a stationary camera. Instead, we consider this an image matching problem. We detect novel objects in the scene using an unordered, sparse database of previously captured images of the same general environment. The problem is formulated in a new image composition framework: 1) given an input image, we find a small set of similar matching images; 2) each of the matches is aligned with the input by proposing a set of homography transformations; 3) regions from different transformed matches are stitched together into a single composite image that best matches the input; 4) the difference between the input and the composite is used to "pop-out" new or changed objects.
ReferencesH. Kang, A. A. Efros, M. Hebert, and T. Kanade, Image Composition for Object Pop-out IEEE Computer Society International Conference on Computer Vision (ICCV) Workshop on 3D Representation for Recognition (3dRR-09), September, 2009.
Videos[DataAcquisition, MOV, 8MB], [Methodology, MOV, 8MB]
|Pixelwise precision and recall curve.||Detection hit/miss precision-recall curve|
This research is supported by:
- NSF Grant EEEC-0540865;