Unlock instant, AI-driven research and patent intelligence for your innovation.

A pedestrian recognition method based on a lightweight convolution neural network

A technology of convolutional neural network and pedestrian re-identification, which is applied in the field of pedestrian re-identification based on lightweight convolutional neural network, can solve problems such as changes in viewing angles and low resolution of pedestrian re-identification images, and achieve simplified network structure and improved accuracy Effect of rate and recall, temporal and spatial optimization

Inactive Publication Date: 2019-03-08
FUZHOU UNIV
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The research of pedestrian re-identification faces many challenges such as low image resolution, perspective changes, pose changes, light changes, and occlusions.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A pedestrian recognition method based on a lightweight convolution neural network
  • A pedestrian recognition method based on a lightweight convolution neural network
  • A pedestrian recognition method based on a lightweight convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0047] Please refer to figure 1 , the present invention provides a method for pedestrian re-identification based on a lightweight convolutional neural network, comprising the following steps:

[0048] Step S1: extract the pedestrian re-identification data set from the large-scale public data set;

[0049] Step S2: adopt the method of median filter to carry out the preprocessing operation of image smoothing to the person re-identification data set, obtain the data set after preprocessing;

[0050]Step S3: the preprocessed data set is processed using an image enhancement algorithm of grayscale stretching to obtain an enhanced data set;

[0051] Step S4: train the lightweight convolutional neural network according to the enhanced data set obtained, and obtain the trained lightweight convolutional neural network model;

[0052] Step S5: Input the picture...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a pedestrian weight identification method based on a lightweight convolution neural network, comprising the following steps of S1 extracting a pedestrian weight identificationdata set from a large public data set; S2 carrying out the image smoothing preprocessing operation on the human re-identification data set by using a median filter method to obtain the preprocessed data set; S3 processing the preprocessed data set by the gray-scale stretching image enhancement algorithm to obtain the enhanced data set; S4 training a lightweight convolution neural network according to the obtained enhanced data set to obtain a trained lightweight convolution neural network model; S5 inputting the picture of the target person and the pedestrian image to be recognized and matched into the trained lightweight convolution neural network model respectively, and judging whether the pedestrian to be recognized and matched is the target person or not. The method of the invention can effectively realize pedestrian re-identification.

Description

technical field [0001] The invention relates to the fields of pattern recognition and computer vision, in particular to a pedestrian re-identification method based on a lightweight convolutional neural network. Background technique [0002] Among the information obtained by the human perception system, visual information accounts for about 80%-85%. Applications related to images and videos are increasingly prominent in the daily life of citizens. Image processing is not only a challenging theoretical research direction in the field of science, but also an important application technology in the field of engineering. Person Re-identification (Person Re-identification) is a new technology emerging in the field of intelligent video analysis in recent years. It belongs to the category of image processing and analysis in complex video environments. It is the main task in many monitoring and security applications, and It has gained more and more attention in the field of compute...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/10G06V20/52G06N3/045
Inventor 柯逍秦丽云
Owner FUZHOU UNIV