Lightweight convolutional neural network pedestrian recognition method

Abstract

The invention discloses a lightweight convolutional neural network pedestrian recognition method, and the method comprises the steps: obtaining original pedestrian data, obtaining a pedestrian image with mark information, and constructing a pedestrian data set; designing an input size of a pedestrian model network, clustering the data set, and selecting an appropriate candidate box; preprocessingthe image, and expanding data; constructing a convolutional neural network, and sending the preprocessed image to the network for training to obtain a network model with a pedestrian recognition function; sending the images with the mark information into a network in batches for training; and checking the loss value and the accuracy on the training set, adjusting the learning rate or increasing the number of iterations and then training again if the result is not ideal, testing the trained network on the verification set if the result is ideal, and adjusting the network again according to theverification result. The identification precision can be improved while the real-time performance of the target detection model is ensured, so that the network model can run on a hardware platform with relatively low configuration.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, in particular to a lightweight convolutional neural network pedestrian recognition method. Background technique [0002] In recent years, with the rise of the artificial intelligence industry and the continuous development of transportation and other industries, pedestrian detection technology has received extensive attention in the fields of intelligent monitoring and intelligent driving. In traditional pedestrian detection methods, manually designed feature extractors, such as Haar, HOG, LBP, etc., extract pedestrian features from training samples, and then use the extracted pedestrian features to train classifiers such as SVM to perform pedestrian detection tasks. For example, the HOG+LBP feature can be used to deal with the pedestrian occlusion problem to improve the accuracy of pedestrian detection. With the introduction of ICF, ACF, gradient amplitude features, and LUV color fe...

AI Technical Summary

Problems solved by technology

Although this method improves the accuracy of pedestrian detection, the amount of network calculation is still large, and it is difficult to deploy on the mobile terminal

[0007] To sum up, although there are many studies on pedestrian detection based on convolutional neural network at home and abroad, most of them have problems with too many network parameters and complex network structure, and have high requirements for hardware equipment and running memory.

Images