Pedestrian detection and tracking method based on accelerated area Convolutional Neural Network

Abstract

The invention relates to a pedestrian recognition and tracking method based on an accelerated area Convolutional Neural Network. Firstly, training and testing data set are preprocessed according to the requirements through a robot with an infrared camera to acquire a training dataset and a testing dataset at night, and then, actual target position labeling is conducted on all training and testing photos and is recorded to a sample file; then, the accelerated area Convolutional Neural Network is constructed, the accelerated area Convolutional Neural Network is trained by using the training dataset, and the final probability belonging to a pedestrian area and a bounding box of the area are calculated out from network output by the usage of a non-maximum suppression algorithm; the accuracy of the network is tested by the usage of the testing dataset, and a network model consistent with the requirements is obtained; photos collected by the robot at night are input to an accelerated area Convolutional Neural Network model, and the probability belonging to the pedestrian area and the bounding box of the area are online output by a model in real time. According to the pedestrian detection and tracking method based on the accelerated area Convolutional Neural Network, a pedestrian in an infrared image can be effectively recognized, and real-time tracking for a pedestrian target in an infrared video can be achieved.

Description

technical field [0001] The invention relates to a nighttime robot pedestrian detection and tracking method based on an accelerated regional convolutional neural network. The method belongs to the field of infrared night vision image processing, and the robot can detect and track pedestrians in real time at night through the method. Background technique [0002] With the rapid development of robot technology and infrared imaging technology, the application fields of the combination of the two are becoming more and more extensive. For example, robots are used to detect and track pedestrians at night to achieve the effect of detection and monitoring. As a higher realization of the robot, when the unmanned driving system is driving at night, pedestrians are also the main objects of its detection. However, the infrared image itself is a grayscale image with no color information, less texture details, and low signal-to-noise ratio. Therefore, pedestrian detection and tracking in ...

AI Technical Summary

Problems solved by technology

[0007] Although Fast-RCNN has improved, it is very time-consuming to generate candidate regions separately using the selective search algorithm, which is the fatal reason why the algorithm cannot achieve real-time

Images