A Real-time Pedestrian Detection Method Based on Neural Network

Abstract

The invention discloses a real-time pedestrian detection method based on a neural network, comprising the steps of: 1) collecting data and constructing an original training data set; 2) for the images in the original training data set, marking the pedestrian position corresponding to the collected image, and constructing the training data 3) Construct a neural network model; 4) In order to increase the amount of network training data and the applicability of the enhancement method, it is necessary to use a data enhancement method to perform data enhancement on the original input image; 5) The designed neural network model Set the training parameters to train, and save the training neural network model parameters; 6) use the image acquisition device to obtain the image data to be detected pedestrians, and then input the images of the pedestrians to be detected into the preserved neural network model, to obtain the pedestrians to be detected Pedestrian locations of detected images. The invention can reduce a lot of detection time under the premise of satisfying the detection accuracy for pedestrian detection.

Description

Technical field[0001]The present invention relates to the technical field of image pattern identification, in particular, referring to a human real-time detection method based on a neural network.Background technique[0002]Pedestrian Detection In the computer visual field, it refers to the position of the pedestrian location based on the image or video information collected by the camera. Pedestrian testing has extremely significant, it is the first step in applications such as vehicle assist driving, smart video surveillance, and human behavior analysis. Because of public safety, digital entertainment industry and other fields have improved pedestrian testing demand, pedestrian testing technology is increasingly attached to the academic and industrial community. The application scenarios of pedestrians are very broad, such as people traffic statistics of important channel entrances and exits, large Xiamen banned system, safety prevention, etc.[0003]There are many kinds of pedestrian...

AI Technical Summary

Problems solved by technology

By acquiring a large amount of image data, training a deep neural network model, and then performing recognition, the accuracy rate is high and the robustness is strong. However, the deep learning method often has a large amount of calculation, requires a long pedestrian detection time and powerful hardware conditions, and is specific to applications. The scene cannot be satisfied

The above limitations make the current pedestrian detection method based on traditional image processing feature extraction less robust, and it is difficult to use deep learning for real-time and effective pedestrian detection

Images