Real-time monocular image-based path detection |
| |
| Authors: | Pablo De Cristóforis Matías A Nitsche Tomá? Krajník Marta Mejail |
| |
| Affiliation: | 1.Laboratory of Robotics and Embedded Systems, Computer Science Department, Faculty of Exact and Natural Sciences,University of Buenos Aires,Buenos Aires,Argentina;2.Intelligent and Mobile Robotics Group, Department of Cybernetics, Faculty of Electrical Engineering,Czech Technical University in Prague,Prague 2,Czech Republic |
| |
| Abstract: | In this work, we present a new real-time image-based monocular path detection method. It does not require camera calibration and works on semi-structured outdoor paths. The core of the method is based on segmenting images and classifying each super-pixel to infer a contour of navigable space. This method allows a mobile robot equipped with a monocular camera to follow different naturally delimited paths. The contour shape can be used to calculate the forward and steering speed of the robot. To achieve real-time computation necessary for on-board execution in mobile robots, the image segmentation is implemented on a low-power embedded GPU. The validity of our approach has been verified with an image dataset of various outdoor paths as well as with a real mobile robot. |
| |
| Keywords: | |
| 本文献已被 SpringerLink 等数据库收录！ |
|
