Abstract: In order to reduce the probability of traffic accident caused by night driving, and to provide initiative safety system for the vehicle in poor visibility environment, according to the basic requirements of the auxiliary driving system, based on infrared sensor technology, design a nighttime pedestrian auxiliary model. The model captures the original data source through infrared sensors, and obtains its ROIs through gray statistical technique, matches and detects the data source based on the building multi-scale probability template, and improves the detection rate and missing rate effectively by multi-frame checksum integrated processing technology. Experiments show that compared to the common method, the probability template’s matching accuracy improves a lot, In addition, this model can also be used under suburbs and the cities, so it has a good practicability.

Key words: Multi-frame check