Visual Features Extraction Based Egomotion Calculation from a Infrared Time-of-Flight Camera

Autor:	Diego Viejo, Miguel Cazorla, José Tomás García García
Rok vydání:	2011
Předmět:	Time-of-flight camera Neural gas Stereo cameras Infrared Computer science business.industry 3D reconstruction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Robotics Computer vision Artificial intelligence business
Zdroj:	Advances in Computational Intelligence ISBN: 9783642214974 IWANN (2)
DOI:	10.1007/978-3-642-21498-1_2
Popis:	3D data have been used for robotics tasks in the last years. These data provide valuable information about the robot environment. Traditionally, stereo cameras has been used to obtain 3D data, but these kind of cameras do not provide information in the lack of texture. There is a new camera, SR4000, which uses infrared light in order to get richer information. In this paper we first analyze this camera. Then, we detail an efficient ICP-like method to build complete 3D models combining Growing Neural Gas (GNG) and visual features. First, we adapt the GNG to the 3D cloud points. Then, we propose the calculation of visual features and its registration to the elements of the GNG. Finally, we use correspondences between frames, an ICP-like method to calculate egomotion. Results of mapping from the egomotion are shown.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::6c7cb638a9a46702da8630d9819445bc https://doi.org/10.1007/978-3-642-21498-1_2 Zobrazit plný text záznamu