Fields, J., Salgian, G., Samarasekera, S., & Kumar, R., (Sept. 27 2009-Oct. 4 2009). “Monocular structure from motion for near to long ranges,” Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on, vol., no., pp.1702,1709.
This paper describes a sensing system for estimating range and detecting the shape of objects from a few meters to a few kilometers away. Such distances are too large for current active methods (e.g. LADAR) or fixed baseline stereo. A sensing system consisting of a single camera mounted on a ground vehicle equipped with a precision inertial navigation system (INS) is used. The vehicle travel is used to synthesize baselines of different lengths. The system uses visual odometry (VO) techniques to refine the camera orientation information derived from the INS and camera-to-vehicle calibration. Range information is obtained through motion stereo analysis of rectified image pairs and the use of multiple baselines in each range image. In addition, range images are combined as the vehicle travel creates new views. Results are compared with ground truth in open terrain with ranges up to several km.