A pedestrian detection method based on depth-supervised learning to extract multi-level features of images

Abstract

A pedestrian detection method based on depth-supervised learning to extract multi-level features of an image, which comprises the following steps: constructing an infrared pedestrian detection training set and a test data set; a pedestrian detection network based on depth-supervised learning being built on a depth-supervised learning framework Caffe; using RMSprop learning strategy to train the pedestrian detection network, wherein Parameter initialization method is msra, Batchsize size is 48, initial learning rate is 0.025, 5 epochs per iteration, learning rate attenuation is once, attenuation rate is 0.98, after 240000 iterations, the best effect is achieved; aiming at Intel Haswell CPU hardware platform, the forward reasoning phase of pedestrian detection network being optimized and accelerated. The invention does not need a pre-training model, and the pedestrian detection method trained from zero realizes the end-to-end training on the infrared data set, and improves the accuracy of pedestrian detection based on the far-infrared image, which can realize real-time detection based on PC X86 CPU and embedded ARM CPU.

Description

technical field [0001] The invention relates to a pedestrian detection method. In particular, it involves a pedestrian detection method based on deep supervised learning to extract multi-level features of images. Background technique [0002] Pedestrian detection is to use computer vision technology to judge whether there are pedestrians in the image and give precise positioning. Pedestrian detection for far-infrared images has many advantages and a wide range of application scenarios. Compared with the visible light band, far-infrared thermal imaging has a long detection distance, high imaging quality, and prominent pedestrian target features. It is widely used in vehicle automatic driving, assisted driving, security monitoring, airport security and other fields. [0003] Deep learning techniques and convolutional neural networks have performed well in many computer vision tasks in recent years. Many pedestrian detection methods using deep learning detection models have ...

AI Technical Summary

Problems solved by technology

However, the far-infrared image is a single-channel grayscale image, while the pre-trained ImageNet dataset is a color three-channel image. The details of far-infrared thermal imaging are also very different from those of visible light images. There will be transfer learning from the classification model to the detection task. Bottleneck, these factors greatly affect the training results of the neural network and limit the accuracy of the infrared pedestrian detection system

[0004] Although the pedestrian detection method based on deep learning has excellent performance, it also has the disadvantages of large amount of calculation and large memory space. The current algorithm mostly runs on the GPU platform, which limits its application on embedded terminals and PC CPUs.

Images