Infrared Pedestrian Detection Method Based on Deep Learning Features of Image Blocks

Abstract

The invention relates to an infrared pedestrian detection method based on deep learning features of image blocks, belonging to the technical fields of image processing and computer vision. This method divides the data set into a training set and a test set. In the training phase, firstly, small image blocks are extracted by sliding on the positive and negative samples of the infrared pedestrian data set, and then clustered to train a convolutional neural network for each type of image block. network. Then use the trained convolutional neural network group to extract features from the positive and negative samples, and train the SVM classifier. In the testing phase, first extract the region of interest from the test image, then use the trained convolutional neural network group to extract features for the region of interest, and finally use the SVM classifier to predict. The present invention achieves the purpose of pedestrian detection by checking whether each region of interest belongs to a pedestrian area, and can accurately detect pedestrians in infrared images under the conditions of complex detection scenes, high ambient temperature, and large differences in pedestrian scale and posture. , and provide support for subsequent research in related fields such as intelligent video.

Description

technical field [0001] The invention belongs to the technical field of image processing and computer vision, and relates to an infrared pedestrian detection method based on deep learning features of image blocks. Background technique [0002] In recent years, intelligent video analysis has become an important task in the field of computer vision. At this stage, intelligent video analysis is a crucial technology for many applications, including robotics, intelligent traffic surveillance, autonomous driving technology, behavior recognition, etc. In the application of intelligent video analysis, pedestrian detection is a very meaningful work, which can provide the most important element in the application scene - the position of "people". [0003] Pedestrian detection in visible light has been a hot topic for a long time. However, under different scenes, lighting conditions and even different clothing, the appearance of pedestrians may vary greatly. Infrared images are relat...

AI Technical Summary

Problems solved by technology

The extraction of this type of features conforms to the characteristics of infrared images, but the information provided is too little

In recent years, related algorithms have proposed to use deep learning-based features for infrared pedestrian detection, but due to the current small dataset of infrared pedestrian images, such features are difficult to be universal

Images