Learning generic human body models
AMDO'10 Proceedings of the 6th international conference on Articulated motion and deformable objects
Recovering Occlusion Boundaries from an Image
International Journal of Computer Vision
Arbitrary body segmentation in static images
Pattern Recognition
Using structural patches tiling to guide human head-shoulder segmentation
Proceedings of the 20th ACM international conference on Multimedia
Improving HOG with image segmentation: application to human detection
ACIVS'12 Proceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems
A robust stereo prior for human segmentation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Object class detection: A survey
ACM Computing Surveys (CSUR)
| Hi-index | 0.14 |
We present a probabilistic method for segmenting instances of a particular object category within an image. Our approach overcomes the deficiencies of previous segmentation techniques based on traditional grid conditional random fields (CRF), namely that 1) they require the user to provide seed pixels for the foreground and the background and 2) they provide a poor prior for specific shapes due to the small neighborhood size of grid CRF. Specifically, we automatically obtain the pose of the object in a given image instead of relying on manual interaction. Furthermore, we employ a probabilistic model which includes shape potentials for the object to incorporate top-down information that is global across the image, in addition to the grid clique potentials which provide the bottom-up information used in previous approaches. The shape potentials are provided by the pose of the object obtained using an object category model. We represent articulated object categories using a novel layered pictorial structures model. Nonarticulated object categories are modeled using a set of exemplars. These object category models have the advantage that they can handle large intraclass shape, appearance, and spatial variation. We develop an efficient method, OBJCUT, to obtain segmentations using our probabilistic framework. Novel aspects of this method include: 1) efficient algorithms for sampling the object category models of our choice and 2) the observation that a sampling-based approximation of the expected log-likelihood of the model can be increased by a single graph cut. Results are presented on several articulated (e.g., animals) and nonarticulated (e.g., fruits) object categories. We provide a favorable comparison of our method with the state of the art in object category specific image segmentation, specifically the methods of Leibe and Schiele and Schoenemann and Cremers.