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

Mask pooling model training and person re-identification method for person re-identification

A pedestrian re-identification and model training technology, applied in the field of computer vision, to achieve the effect of improving accuracy and efficiency, improving accuracy and speeding up the convergence process

Active Publication Date: 2021-06-04
SUN YAT SEN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] There are many loss methods used to guide model training

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
  • Mask pooling model training and person re-identification method for person re-identification
  • Mask pooling model training and person re-identification method for person re-identification
  • Mask pooling model training and person re-identification method for person re-identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Such as figure 1 As shown, this embodiment provides a mask pooling model training method for pedestrian re-identification, including training steps:

[0061] S1. Obtain anchor image a, positive sample image p, and negative sample image n;

[0062] S2. Input a, p, n and the masks corresponding to a, p, n into the mask pooling model respectively, and obtain the corresponding tensor T a , T p , T n ;

[0063] S3. to T a , T p , T n Perform pooling operation and convolution operation respectively to obtain the corresponding tensor H a 、H p 、H n ;

[0064] S4. H a 、H p 、H n Enter the classifier respectively to get the corresponding prediction result R a , R p , R n ;

[0065] S5. According to the prediction result R a , R p , R n Calculate the loss value;

[0066] S6. Train the mask pooling model according to the loss value.

[0067] The traditional triple loss method requires images with 3 input channels: anchor image a, positive sample image p, and ne...

Embodiment 2

[0125] A pedestrian re-identification method, comprising: inputting a pedestrian image to be recognized into a mask pooling model, and the mask pooling model is trained by using the mask pooling model training method as described in Embodiment 1.

[0126] Through the mask pooling model described in Example 1, background features can be gradually removed and the most critical pedestrian features can be obtained. Such as Figure 4 Shown is the result of removing background features from pedestrian images. It can be seen that the outline features of pedestrians have been preserved to the greatest extent, and the cluttered background has been effectively removed, improving the accuracy and efficiency of pedestrian re-identification.

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 present invention relates to a mask pooling model training and a pedestrian re-identification method for pedestrian re-identification, comprising S1. acquiring an anchor image a, a positive sample image p, and a negative sample image n; S2. combining a, p, n and The masks corresponding to a, p, and n are respectively input into the mask pooling model to obtain the corresponding three-dimensional tensor T a , T p , T n ; S3. to T a , T p , T n Perform pooling operation and convolution operation respectively to obtain the corresponding H a 、H p 、H n ; S4. Put H a 、H p 、H n Enter the classifier respectively to get the corresponding prediction result R a , R p , R n ; S5. According to the prediction result R a , R p , R n Calculate the loss value; S6. Train the mask pooling model according to the loss value. The invention can enhance the non-background information in the image and learn the most critical features of the image.

Description

technical field [0001] The present invention relates to the technical field of computer vision, and more specifically, to a mask pooling model training for pedestrian re-identification and a pedestrian re-identification method. Background technique [0002] Person re-identification (Person Re-identification, Person ReID), also known as person re-identification, is a technology that uses computer vision technology to determine whether a specific pedestrian exists in an image or video sequence, and is widely considered to be a sub-problem of image retrieval. Person ReID refers to given a monitored pedestrian image, retrieves the pedestrian image under cross-device, aims to make up for the visual limitations of the current fixed camera, and can be combined with pedestrian detection / pedestrian tracking technology, and can be widely used in intelligent video surveillance , intelligent security and other fields. [0003] Due to the differences between different camera equipment, ...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/103G06F18/24G06F18/214
Inventor 卢宇彤蔡婷婷郑馥丹王莹邓楚富陈志广
Owner SUN YAT SEN UNIV