Search Results

Autonomous ground vehicles can use a variety of techniques to navigate the environment and deduce their motion and location from sensory inputs. Visual Odometry can provide a means for an autonomous vehicle to gain orientation and position information from camera images recording frames as the vehicle moves. This is especially useful when global positioning system (GPS) information is unavailable, or wheel encoder measurements are unreliable. Feature-based visual odometry algorithms extract corner points from image frames, thus detecting patterns of feature point movement over time. From this information, it is possible to estimate the camera, i.e., the vehicle’s motion. Visual odometry has its own set of challenges, such as detecting an insufficient number of points, poor camera setup, and fast passing objects interrupting the scene. This paper investigates the effects of various disturbances on visual odometry.

To reliably implement driver-assist features and ultimately self-driving cars, autonomous driving systems will likely rely on a variety of sensor types including GPS, RADAR, LASER range finders, and cameras. Cameras are an essential sensory component because they lend themselves to the task of identifying object types that a self-driving vehicle is likely to encounter such as pedestrians, cyclists, animals, other cars, or objects on the road. In this paper, we present a feature-based visual odometry algorithm based on a stereo-camera to perform localization relative to the surrounding environment for purposes of navigation and hazard avoidance. Using a stereo-camera enhances the accuracy with respect to monocular visual odometry. The algorithm relies on tracking a local map consisting of sparse 3D map points. By tracking this map across frames, the algorithm makes use of the full history of detected features which reduces the drift in the estimated motion trajectory.