Issue No. 09 - Sept. (2012 vol. 34)
Yi Yang , Dept. of Comput. Sci., Univ. of California at Irvine, Irvine, CA, USA
S. Hallman , Dept. of Comput. Sci., Univ. of California at Irvine, Irvine, CA, USA
D. Ramanan , Dept. of Comput. Sci., Univ. of California at Irvine, Irvine, CA, USA
C. C. Fowlkes , Dept. of Comput. Sci., Univ. of California at Irvine, Irvine, CA, USA
We formulate a layered model for object detection and image segmentation. We describe a generative probabilistic model that composites the output of a bank of object detectors in order to define shape masks and explain the appearance, depth ordering, and labels of all pixels in an image. Notably, our system estimates both class labels and object instance labels. Building on previous benchmark criteria for object detection and image segmentation, we define a novel score that evaluates both class and instance segmentation. We evaluate our system on the PASCAL 2009 and 2010 segmentation challenge data sets and show good test results with state-of-the-art performance in several categories, including segmenting humans.
probability, image segmentation, object detection, human segmentation, layered object models, image segmentation, object detection, generative probabilistic model, object detectors, shape masks, appearance, depth ordering, image pixel labelling, class label estimation, object instance label estimation, class segmentation, instance segmentation, PASCAL 2009 segmentation challenge data sets, PASCAL 2010 segmentation challenge data sets, Shape, Image segmentation, Image color analysis, Detectors, Object detection, Mathematical model, Computational modeling, segmentation benchmark., Image segmentation, multiclass object detection, layered model, 2.1D model
D. Ramanan, S. Hallman, Yi Yang and C. C. Fowlkes, "Layered Object Models for Image Segmentation," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1731-1743, 2012.