Real-time vehicle flow detecting and tracking method based on aerial photography data

Abstract

The invention provides a real-time vehicle flow detecting and tracking method based on aerial photography data. The method comprises the following steps that 1, a pre-training model of a YOLO networkis trained on the basis of a pre-training part of weak supervised learning by using a weak supervised learning mode; and 2, the pre-training model of the YOLO network is improved on the basis of a real-time vehicle flow detecting part of aerial photography data by adopting a full convolutional neural network and a multi-target box detection method with prior information to obtain a YOLO detectingnetwork. The method has the advantages that improvement is achieved on the basis of a YOLO algorithm, the full convolutional neural network and the multi-target box detection method with the prior information are adopted, training is conducted by effectively utilizing the multi-view and multi-resolution image characteristics of an aerial photography data set of an unmanned aerial vehicle, the detecting accuracy rate of the algorithm is increased on the condition of not losing too much detecting time, and the balance of the accurate rate and the time is achieved.

Description

technical field [0001] The invention relates to vehicle flow detection, in particular to a real-time vehicle flow detection and tracking method based on aerial photography data. Background technique [0002] At present, the relatively mature traffic detection technology is mainly based on the inter-frame difference method. First, the video is converted into an image sequence and processed in grayscale. The difference image is obtained by the inter-frame difference method, and then the difference image is filtered, binarized and morphological. Finally, the contour detection algorithm is used to detect and track the vehicle. [0003] The method of directly detecting vehicles based on pixel intensity changes in aerial video data has the advantage of good accuracy, but it has the following shortcomings due to theoretical limitations: [0004] (1) The image information loss of the binary image obtained by the inter-frame difference method is easy to cause missed and repeated det...

AI Technical Summary

Problems solved by technology

[0004] (1) The image information loss of the binary image obtained by the inter-frame difference method, this technology can easily lead to missed and repeated detection of vehicles

[0005] (2) The technology is less robust to traffic detection in complex natural scenes

Images