Layered Object Detection for Image Segmentation

Yi Yang, Sam Hallman, Deva Ramanan and Charless Fowlkes

Introduction

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. 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.

Publications

Yi Yang, Sam Hallman, Deva Ramanan, Charless Fowlkes. Layered Object Detection for Multi-Class Segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, USA, 2010.

Yi Yang, Sam Hallman, Deva Ramanan, Charless Fowlkes. Layered Object Models for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2012.

Examplar Results

Input Images Instance Segmentation Class Segmentation Input Images Instance Segmentation Class Segmentation

Related Links