Research On The Omni-directional Visual Technology Of The AGV

Mobile robot and AGV(automated guided vehicle) are combined with varies of technologies, and the guidance is one of the most crucial technologies. With a very large field of view, omni-directional visual system has a special advantage in mobile robot and AGV. Nowadays, fisheye lens has been widely used in omni-directional visual systems, especially in tracking and navigation. However, the fisheye lens brings a kind of barrel distortion, which must lead to error in positioning if isn't accurately corrected.In this paper, a new approach is put forward to correct the distortion after an analysis on implementations of omni-directional image systems of mobile robot and AGV in and abroad: SVM(support vector machine) is trained using the real points as the import and the distorted points gathered by fisheye lens as the export, then makes a model for radial distance regression. Then the distortion can be real-timely corrected by means of table checking. The rectification process is finished on DSP TMS320DM642.Results using this method have verified that the degree of the rectification is sufficient and provides high speed response, which is required for accurate analysis of the image. The process speed of export image can reach 25 frames per second and is faster than using traditional method; besides, instead of PC, using hardware can simplify the structure and reduce the size.