Title :
High resolution terrain map from multiple sensor data
Author :
Kweon, In ; Kanade, Takeo
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
Describes a terrain mapping 3D vision system to build a high resolution terrain map from multiple range images and a digital elevation model (DEM). To build a composite map of the environment from multiple sensor data, the terrain mapping system needs a representation of the terrain that must be appropriate for multiple sensor data. Building a composite terrain map also requires estimating motion between sensor views and merging these views into a composite map. The terrain representation described consists of a grid-based representation, called elevation map. The authors develop the locus method to build elevation maps from range images. The locus method uses a model of the sensor to interpolate at arbitrary resolution without making any assumptions on the terrain shape other than the continuity of the surface. They also present a pixel-based or iconic terrain matching algorithm to estimate the vehicle motion from a sequence of range images. This terrain matching method uses the locus method to solve correspondence and occlusion problems. Comprehensive test results using a long sequence of range images and a DEM for rugged outdoor terrain are given
Keywords :
computer vision; computerised pattern recognition; robots; 3D vision system; digital elevation model; grid-based representation; iconic terrain matching algorithm; locus method; motion estimation; multiple sensor data; occlusion problems; robot vision; terrain mapping; terrain representation; Digital elevation models; Image resolution; Machine vision; Merging; Motion estimation; Pixel; Sensor systems; Shape; Terrain mapping; Vehicles;
Conference_Titel :
Intelligent Robots and Systems '90. 'Towards a New Frontier of Applications', Proceedings. IROS '90. IEEE International Workshop on
Conference_Location :
Ibaraki
DOI :
10.1109/IROS.1990.262378