A real-time panoramic vision system for autonomous navigation

作者: Amarnath Banerjee , Sumantra Dasgupta

DOI: 10.5555/1161734.1162052

关键词: Sensory cuePanoramaComputer graphics (images)Machine visionMatching (graph theory)Image stitchingArtificial intelligenceComputer visionMobile robot navigationComputer science

摘要: The paper discusses a panoramic vision system for autonomous navigation purposes. It describes method integrating data in real-time from multiple camera sources. views adjacent cameras are visualized together as panorama of the scene using modified correlation based stitching algorithm. A separate operator is presented with particular slice matching user's viewing direction. Additionally, simulated environment created where can choose to augment video by simultaneously an artificial 3D view scene. Potential applications this include enhancing quality and range visual cues, under hostile circumstances direct not possible or desirable.

参考文章(2)
David A. Forsyth, Jean Ponce, Computer Vision: A Modern Approach ,(2002)
R. Szeliski, Video mosaics for virtual environments IEEE Computer Graphics and Applications. ,vol. 16, pp. 22- 30 ,(1996) , 10.1109/38.486677