Layered Object Models for Image Segmentation
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 datasets and show good test results with state of the art performance in several categories including segmenting humans.
Text ReferenceYi Yang, Sam Hallman, Deva Ramanan, and Charless Fowlkes. Layered object models for image segmentation. IEEE TPAMI, 2011.
author = "Yang, Yi and Hallman, Sam and Ramanan, Deva and Fowlkes, Charless",
title = "Layered Object Models for Image Segmentation",
journal = "IEEE TPAMI",
year = "2011",
tag = "grouping"