Combination of Planes and Image Edges for a Visual Odometer for Weakly Textured Structured Environments

Camera trajectory estimation has generated a lot of interest during the last decades, especially for robotic positioning. It is well-known that outdoors positioning mainly relies on GPS, whereas one of the main used methods in indoor positioning is visual odometry. As it is well known, visual odometers get typically in trouble when the environment is weakly textured. Facing this situation, this paper develops and tests a novel visual odometer that combines image edges and planar information to estimate the trajectory of an RGB-D camera in environments that lack texture. We also present a plane matching method based on a graph matching technique. To conclude, a comparison of the proposed odometer for two well-known datasets and other visual odometers and SLAM systems is reported. The comparison shows our method as more accurate as for the estimation of the position in indoor places where visual features are poor, while similar values are obtained for other indoor environments.