Real-time object recognition on image sequences with the adaptable time delay neural network algorithm - applications for autonomous vehicles

Within the framework of the vision-based "Intelligent Stop&Go" driver assis tance system for both the motorway and the inner city environment, we prese nt a system for segmentation-free detection of overtaking vehicles and esti mation of ego-position on motorways as well as a system for the recognition of pedestrians in the inner city traffic scenario. Both systems are runnin g in real-time in the test vehicle UTA of the DaimlerChrysler computer visi on lab, relying on the adaptable time delay neural network (ATDNN) algorith m. For object recognition, this neural network processes complete image seq uences at a time instead of single images, as it is the case in most conven tional neural algorithms. The results are promising in that using the ATDNN algorithm, we are able to perform the described recognition tasks in a lar ge variety of real-world scenarios in a computationally highly efficient an d rather robust and reliable manner. (C) 2001 Elsevier Science Ltd All righ ts reserved.