This Article 
 Bibliographic References 
 Add to: 
Detachable Object Detection: Segmentation and Depth Ordering from Short-Baseline Video
Oct. 2012 (vol. 34 no. 10)
pp. 1942-1951
Alper Ayvaci, University of California, Los Angeles
Stefano Soatto, University of California, Los Angeles
We describe an approach for segmenting a moving 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.
Index Terms:
Motion segmentation,Optimization,Image segmentation,Object recognition,Linear programming,Mathematical model,model selection.,Object detection,video segmentation,occlusion,layers,graph cuts,ordering constraints
Alper Ayvaci, Stefano Soatto, "Detachable Object Detection: Segmentation and Depth Ordering from Short-Baseline Video," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 10, pp. 1942-1951, Oct. 2012, doi:10.1109/TPAMI.2011.271
Usage of this product signifies your acceptance of the Terms of Use.