Neuromorphic visual information processing for vulnerable road user detection and driver monitoring

Abstract

Considering the number of fatalities and serious injuries of road users, the safety enhancement has begun to gain more attention, in particular the innovation and application of Advanced Driver Assistance System Technologies. We have proposed that the neuromorphic visual processing algorithm based on the biological vision system is an effective approach for making detection of human figures from a moving vehicle, with the focus on either the driver or other vulnerable road users, such as the pedestrians or cyclists on the road. The effectiveness of proposed neuromorphic networks of visual processing is evaluated for the vulnerable road user detection technology via the 99% (day time) and 88% (night time) of successful detection rate. The post enhancement with deep networks showed that further applications could be sought from incorporating neuromorphic visual processing into Driver State Monitoring for the purpose of enhancing vulnerable road users' safety. The early implementation demonstrated the advantages of fast and robust neuromorphic vision with either the small embedded system or the portable computer based emulator, and the orientation processing of 30 frames per second with the neuromorphic ASIC and FPGA.