Pedestrian detection method based on YOLO neural network

Abstract

The invention discloses a pedestrian detection method based on YOLO neural network. The method of the invention uses artificially divided pedestrian detection scene pictures to learn YOLO neural network so that the YOLO neural network can recognize pedestrians. This method realizes a pedestrian detection method based on YOLO neural network. Compared with the existing methods, it has better detection effect and performance.

Description

technical field [0001] The invention relates to the automatic identification of pedestrians in pedestrian pictures in blocks, in particular to a target identification method based on a deep YOLO neural network. Background technique [0002] Pedestrian detection has always been one of the hot research topics in the field of computer vision, and it is widely used in many aspects such as video surveillance and automatic driving. [0003] At present, the main method of pedestrian detection is to use effective feature extraction methods, and use HOG, PGA and other methods for feature dimensionality reduction, and then use classifiers such as support vector machines to achieve binary classification, so as to determine whether the target object is a pedestrian to be detected. With the development of convolutional neural networks, the research on using convolutional neural networks for pedestrian recognition is increasing, and better recognition results have been obtained. However, ...

AI Technical Summary

Problems solved by technology

With the development of convolutional neural networks, the research on pedestrian recognition using convolutional neural networks has increased, and better recognition results have been obtained. However, with the complexity of the network scale, the detection speed cannot meet the real-time requirements.

Images