Visual Detection of Lintel-Occluded Doors from a Single Image

Abstract

Doors are important landmarks for indoor mobile robot navigation. Most existing algorithms for door detection use range sensors or work in limited environments because of restricted assumptions about color, pose, or lighting. We present a vision-based door detection algorithm that achieves robustness by utilizing a variety of features, including color, texture, and intensity edges. We introduce two novel geometric features that increase performance significantly: concavity and bottom-edge intensity profile. The features are combined using Adaboost to ensure optimal linear weighting. On a large database of images collected in a wide variety of conditions, the algorithm achieves more than 90% detection with a low false positive rate. Additional experiments demonstrate the suitability of the algorithm for real-time applications using a mobile robot equipped with an off-the-shelf camera and laptop.