Doors are semantically meaningful objects crucial for indoor navigation and mapping. We have developed a technique that detects doors in a single image in near real time (approximately 5 fps) from a camera mounted on a mobile robot. Because the camera is mounted low to the ground, the top (lintel) of the door is often not visible. To solve the problem in a variety of environments, several standard and novel cues are employed. Any single cue is unable on its own to detect doors reliably, but these weak classifiers are combined using Adaboost to produce a strong classifier capable of reliable detection.
The basic algorithm is represented below. Vertical intensity edges are used to detect door candidates, which are then tested using the remaining cues.
Example images:
Videos:
Database of 440 door images: door_images.zip