Object Recognition for Autonomous Vehicle

An Autonomous Vehicle is capable of fulfilling the transportation instead of the traditional car. As an autonomous vehicle, it have to detect its environment and navigate without human's involvement. A vision-based vehicle recognition system working in road environments has three main roles: Road detection, Traffic sign recognition, and Obstacles detection. Traffic signs are designed with different colors and shapes to be easily recognized by human drivers mainly from natural environments and some obstacles (i.e. other cars and pedestrians) also have obvious features.
We are reserching about vision based object recognition using the best use of some features allowing the vehicles to keep track of their position even when conditions change or when they enter uncharted environments and also participating in autonomous vehicle competitions.