Shape-based Object Detection via Boundary Structure

We address the problem of object detection and segmentation using global holistic properties of object shape. Global shape representations are highly susceptible to clutter inevitably present in realistic images, and can be applied robustly only using a precise segmentation of the object. To this end, we propose a figure/ground segmentation method for extraction of image regions that resemble the global properties of a model boundary structure and are perceptually salient. Our shape representation, called the chordiogram, is based on geometric relationships of object boundary edges, while the perceptual saliency cues we use favor coherent regions distinct from the background. We formulate the segmentation problem as an integer quadratic program and use a semdefinite programming relaxation to solve it. Obtained solutions provide the segmentation of an object as well as a detection score used for object recognition. Our single-step approach achieves state-of-the-art performance on several object detection and segmentation benchmarks. Disciplines Computer Sciences Comments Shape-based Object Detection via Boundary Structure Segmentation, A. Toshev, B. Taskar, and K. Daniilidis, International Journal of Computer Vision (IJCV). An author may self-archive an author-created version of his/her article on his/her own website and or in his/her institutional repository. He/she may also deposit this version on his/her funder’s or funder’s designated repository at the funder’s request or as a result of a legal obligation, provided it is not made publicly available until 12 months after official publication. He/ she may not use the publisher's PDF version, which is posted on www.springerlink.com, for the purpose of self-archiving or deposit. The final publication is available at www.springerlink.com This journal article is available at ScholarlyCommons: https://repository.upenn.edu/cis_papers/544 Noname manuscript No. (will be inserted by the editor) Shape-based Object Detection via Boundary Structure Segmentation Alexander Toshev · Ben Taskar · Kostas Daniilidis Received: 03/02/2011 Abstract We address the problem of object detection and segmentation using global holistic properties of object shape. Global shape representations are highly susceptible to clutter inevitably present in realistic images, and can be applied robustly only using a precise segmentation of the object. To this end, we propose a figure/ground segmentation method for extraction of image regions that resemble the global properties of a model boundary structure and are perceptually salient. Our shape representation, called the chordiogram, is based on geometric relationships of object boundary edges, while the perceptual saliency cues we use favor coherent regions distinct from the background. We formulate the segmentation problem as an integer quadratic program and use a semidefinite programming relaxation to solve it. Obtained solutions provide the segmentation of an object as well as a detection score used for object recognition. Our single-step approach achieves state-of-the-art performance on several object detection and segmentation benchmarks.We address the problem of object detection and segmentation using global holistic properties of object shape. Global shape representations are highly susceptible to clutter inevitably present in realistic images, and can be applied robustly only using a precise segmentation of the object. To this end, we propose a figure/ground segmentation method for extraction of image regions that resemble the global properties of a model boundary structure and are perceptually salient. Our shape representation, called the chordiogram, is based on geometric relationships of object boundary edges, while the perceptual saliency cues we use favor coherent regions distinct from the background. We formulate the segmentation problem as an integer quadratic program and use a semidefinite programming relaxation to solve it. Obtained solutions provide the segmentation of an object as well as a detection score used for object recognition. Our single-step approach achieves state-of-the-art performance on several object detection and segmentation benchmarks.