Detecting automobiles on real street environment for Advanced Driver Assistance Systems by its projected shadow

Advanced Driver Assistance Systems (ADAS) are becoming of major relevance for driver assistance. Collision Warning Systems (CWS) are part of ADAS. It is well known that driver distraction on his/her driving is a major cause of traffic accidents, and giving the environment variability while driving is a challenging area of research. This work shows that by reducing the search space to critical areas, segmenting vehicle´s shadow, and using vehicle´s properties, it is possible to successfully detect automobiles in real urban environments. By using parameterized windowing and transforming a vehicle´s shadow to a higher level of information, and vehicle´s properties, the detection is simplified. The algorithm parameterizes image resolution, thus allowing for different camera resolutions that surely will continue to improve. This work uses the fact that a vehicle has a shadow on the road´s pavement; together with the alarm zones give enough information for an ADAS to decide on actions for driver assistance. On a test set of 20 test images of real urban environments this work has results that show 100% correct automobile detection on real outdoor environments.