A pedestrian and vehicle detection method and system based on improved YOLOv3

Abstract

The invention discloses a pedestrian and vehicle detection method and system based on improved YOLOv3. According to the method, an improved YOLOv3 network based on Darknet-33 is adopted as a main network to extract features; the cross-layer fusion and reuse of multi-scale features in the backbone network are carried out by adopting a transmittable feature map scale reduction method; and then a feature pyramid network is constructed by adopting a scale amplification method. In the training stage, a K-means clustering method is used for clustering the training set, and the cross-to-parallel ratio of a prediction frame to a real frame is used as a similarity standard to select a priori frame; and then the BBox regression and the multi-label classification are performed according to the loss function. And in the detection stage, for all the detection frames, a non-maximum suppression method is adopted to remove redundant detection frames according to confidence scores and IOU values, and an optimal target object is predicted. According to the method, a feature extraction network Darknet-33 of feature map scale reduction fusion is adopted, a feature pyramid is constructed through feature map scale amplification migration fusion, and a priori frame is selected through clustering, so that the speed and precision of the pedestrian and vehicle detection can be improved.

Description

technical field [0001] The present invention relates to a pedestrian and vehicle target detection method and system, in particular to a target detection method and system for feature map scale conversion migration fusion and Feature Pyramid Networks (FPN, Feature Pyramid Networks) multi-scale feature prediction, which belongs to the field of computer vision Target detection technology field. Background technique [0002] With the increase of urban population and the improvement of people's pursuit of quality of life, the number of private cars in cities is increasing day by day. Under the environment where urban road construction has not kept up with the pace and public transportation facilities are still sub-perfect, roads are congested, A series of problems such as frequent traffic accidents have become increasingly prominent. In recent years, the emergence of intelligent transportation systems has greatly relieved the growing pressure of modern transportation systems. It...

AI Technical Summary

Problems solved by technology

Manual settings need to rely on experience and luck to obtain better features, so it is difficult to guarantee the essential characteristics of actions from drastically changing scenes

Therefore, an automatic learning method is needed to solve the blindness and one-sidedness of the time-consuming manual feature extraction method.

[0004] The YOLO (You Only Look Once) algorithm proposed by Redmon et al. in 2016 is a convolutional neural network that can predict multiple Box positions and categories at one time. The network design strategy of the YOLO algorithm continues the core idea of ​​GoogleNet and realizes it in a real sense. End-to-end target detection has been achieved, and the advantages of fast speed have been taken advantage of, but its accuracy has declined.

Images