Comparison of Keypoint Detection Methods for Indoor and Outdoor Scene Recognition

Urszula Libal, Łukasz Łoziuk
2018 Journal of Automation, Mobile Robotics & Intelligent Systems  
We describe an experimental study, based on several million video scenes, of seven keypoint detec on algorithms: BRISK, FAST, GFTT, HARRIS, MSER, ORB and STAR. It was observed that the probability distribu ons of selected keypoints are dras cally different between indoor and outdoor environments for all algorithms analyzed. This paper presents a simple method for dis nguishing between indoor and outdoor environments in a video sequence. The proposed method is based on the central loca on of
more » ... oints in video frames. This has lead to a universally effec ve indoor/outdoor environment recogni on method, and may prove to be a crucial step in the design of robo c control algorithms based on computer vision, especially for autonomous mobile robots.
doi:10.14313/jamris_4-2017/32 fatcat:k4rlnyiemvctvdkpskc4aec2xy