Special issue on car navigation and vehicle systems

From the early experiments on self-driving vehicles half a century ago to the modern Google driverless cars, significant progress has been made in the understanding of traffic scenes and extracting of information that the autonomous cars need. In addition to guidance and improved comfort, advanced navigation systems also provide enhanced driver assistance to maintain a safe speed, keep a safe distance, drive within the lane, avoid overtaking in critical situations, safely pass intersections, avoid collisions with vulnerable road users, and as a last resort, reduce the severity of an accident if it still occurs. Yet, automatic detection of such objects and events comes with many challenges. Complex backgrounds, low-visibility weather conditions, cast shadows, strong headlights, direct sunlight during dusk and dawn, uneven street illumination, occlusion caused by other vehicles, great variation of traffic sign pictograms are just some of the issues that make these tasks difficult. This special issue brings together several contributions toward achieving visual intelligence in autonomous navigation. In their selection, we have tried to select both scientifically and practically strong, covering a broad scope of relevant topics. The first paper, “Event Classification for Vehicle Navigation System by Regional Optical Flow Analysis” examines the optical flow observed by a camera, mounted in a car and looking forward. The difficulty of course is that the camera