Vehicle type discrimination method based on deep learning

The invention provides a vehicle type discrimination method based on deep learning, and the method comprises the steps: constructing an artificial neural network model of a yolo frame, and randomly initializing a weight coefficient; collecting vehicle photos from the internet and captured in the current application environment, wherein the vehicle photos comprise vehicle photos under the conditions of blocking, dim light and the front face of a vehicle; marking the vehicle, and inputting the vehicle photos into an artificial neural network model; perofrming training by using an artificial neural network model and a vehicle picture; stopping training to obtain a weight file suitable for the current application environment; and inputting a picture needing to be identified into the artificialneural network model, judging the vehicle type and returning a result. According to the vehicle type distinguishing method, the adopted vehicle photos comprise the shielded sample, the dark light sample and the vehicle photo