Moving Car Detection and Model Recognition based on Deep Learning
Yongbin Gao, Hyo Jong Lee · Advanced science and technology letters · 2015
Vehicle analysis is an import task in many intelligent applications, such as automatic toll collection and driver assistance systems. Among these applications, moving car detection and model recognition are a challenging task due to the close appearance between car models. In this paper, we propose a framework to detect moving cars and its model based on deep learning. We first detect the moving car using frame difference; the resultant binary image is used to detect the frontal view of a car by a symmetry filter. The detected frontal view is used to identify a car based on deep learning with three layers of restricted Boltzmann machines (RBMs). Experiment results show that our proposed framework achieves favorable recognition accuracy.