Research On Pedestrian Detection Based On Deep Learning

Pedestrian detection is a hot research topic because it is extremely important in many applications,especially in the automotive,surveillance and robotics fields.Despite significant improvements in current technology,pedestrian detection remains an open challenge requiring more and more precise algorithms.In recent years,deep learning,especially convolutional neural networks,has become the most advanced technology in the accuracy of computer vision tasks such as image classification,target detection and segmentation,far exceeding the previous gold standard.This paper illustrates the disadvantages of traditional pedestrian detection algorithms by studying the pedestrian detection based on traditional algorithms,and highlights the superiority of pedestrian detection based on deep learning.A generalized convolutional network is adapted to the current task for the monitoring scenario,and a pedestrian detection algorithm based on deep learning is proposed.This paper introduces the "head and shoulders" model by analyzing the pedestrian characteristics of the monitoring scene,improves the RPN network to make it more suitable for pedestrian detection,and builds a database based on the head and shoulder model in combination with the commonly used pedestrian database,and uses a superior convolution network.The model is designed according to the characteristics of the output characteristics of the convolutional layer,and the role of shallow features is enhanced to improve the detection accuracy.The experimental results show that the proposed algorithm has certain advantages in speed and precision compared with other algorithms.