- Y. LeCun, Y. Bengio, G. Hinton
- Nature, vol. 521, pp. 436-444, May 2015.
In this paper, we proposed a real-time vehicle detection using deep learning scheme to reduce false-positive rate. In addition, we implemented our algorithm in an embedded system to confirm the real time. Experimental results show that the precision rate is increased by applying the model generated through deep learning to the vehicle validation phase. The average processing time of our vehicle detection modules is about 15frame per seconds.