Vehicle detection method used for traffic monitoring

Abstract

The invention provides a vehicle detection method used for traffic monitoring. The vehicle detection method comprises the steps that S1, firstly a collected traffic monitoring image is split into upper and lower parts, the vehicle of the upper half of image is away from a monitoring camera and the vehicle is in the small and blurred state, the vehicle of the image is cut and vehicle type information is marked so as to form a first training sample set; and the vehicle of the lower half of image is near the monitoring camera, the vehicle is in the large and clear state, and the vehicle type information and position information are directly marked in the lower half of image so as to form a second training sample set; S2, a convolutional neural network is constructed and trained; S3, a YOLO neural network is constructed and trained; and S4, the result is outputted by combining the convolutional neural network and the YOLO neural network, and the vehicle in the complete traffic monitoring image is detected. The disadvantages of low detection speed of the detection convolutional neural network and low recall rate of the YOLO neural network can be simultaneously overcome so as to rapidly and accurately detect the vehicle in traffic monitoring.

Description

technical field [0001] The invention belongs to the field of vehicle image detection, and in particular relates to a vehicle detection method for traffic monitoring. Background technique [0002] In recent years, with the increase of vehicles, the congestion of traffic roads has become more and more serious. Therefore, the traffic department's technical demand for real-time detection of the number of vehicles on each road is becoming more and more intense. The traditional manual detection method consumes manpower and lacks accuracy. And the current mainstream vehicle detection method based on machine vision only has good performance in static pictures, but the performance in dynamic video cannot meet the technical requirements. [0003] The existing vehicle detection methods mainly include the following types: [0004] 1. HOG feature detection: HOG detection method feature is a feature description used for vehicle detection in computer vision and image processing. It form...

AI Technical Summary

Problems solved by technology

However, affected by the detection rate, accuracy rate and recall rate, the existing methods still have many technical difficulties in video

Images