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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


