Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video

Details Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video

2011-09-22

arxiv.org/abs/1109.4683v1

Computer Science

Computer Vision and Pattern Recognition

Scientific paper

We describe an approach for segmenting an image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appearance and motion statistics into a cost functional, that is seeded with occluded regions and minimized efficiently by solving a linear programming problem. Where a short observation time is insufficient to determine whether the object is detachable, the results of the minimization can be used to seed a more costly optimization based on a longer sequence of video data. The result is an entirely unsupervised scheme to detect and segment an arbitrary and unknown number of objects. We test our scheme to highlight the potential, as well as limitations, of our approach.

Affiliated with

Also associated with

No associations

Rating

Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-262048