Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An Attention Model Approach to Video Surveillance Pedestrian Search Based on Natural Language Description

An attention model and natural language technology, applied in character and pattern recognition, instruments, computing, etc., can solve problems such as unsatisfactory effects and high difficulty, and achieve the effect of improving effects, improving representativeness and effectiveness

Active Publication Date: 2021-07-13
TIANJIN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Compared with the widely used attribute-based pedestrian search, video surveillance pedestrian search using human natural language description is more conducive to the use of actual scenes, but the difficulty of implementation is also higher than attribute-based pedestrian search
In the video surveillance pedestrian search task based on human natural language description, the effect of the existing attention model algorithm is not ideal

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
  • An Attention Model Approach to Video Surveillance Pedestrian Search Based on Natural Language Description
  • An Attention Model Approach to Video Surveillance Pedestrian Search Based on Natural Language Description
  • An Attention Model Approach to Video Surveillance Pedestrian Search Based on Natural Language Description

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The attention model method for video surveillance pedestrian search based on natural language description of the present invention will be described in detail below with reference to the embodiments and drawings.

[0032] The attention model method of video surveillance pedestrian search based on natural language description of the present invention uses the attention weight formed by the fused feature vector to carry out attention weighting on the image feature vector to obtain the connection degree between the text and the image. At the same time, the text is weighted by using the attention weight formed by the text feature vector to obtain the importance of the text. The attention evaluation score is obtained by multiplying the degree of connection between the text and the image by the importance of the text. Specifically include the following steps:

[0033] 1) Let the nth image feature vector extracted by the convolutional neural network be I n ; The natural lang...

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

An attention model method for video surveillance pedestrian search based on natural language description, using the attention weight formed by the fused feature vectors to weight the image feature vectors to obtain the degree of connection between text and images. At the same time, the text is weighted by using the attention weight formed by the text feature vector to obtain the importance of the text. The attention evaluation score is obtained by multiplying the degree of connection between the text and the image by the importance of the text. The present invention uses three different attention weighting methods, more effectively highlights the importance of each word text vector and improves the representativeness and effectiveness of feature vectors, and can use feature vectors more fully and effectively. Effective features in the feature vector can be fully utilized to improve the effect of training and testing. It can solve some artificial intelligence, machine learning, and video surveillance pedestrian search based on natural language description and other related work and problems.

Description

technical field [0001] The invention relates to an attention model method for pedestrian search in video surveillance. In particular, it concerns an attention model approach for pedestrian search in video surveillance based on natural language description. Background technique [0002] With the continuous development of artificial intelligence and deep learning, people's requirements for artificial intelligence and deep learning are also getting higher and higher. The feature vectors extracted from images and texts and the effective use of these feature vectors are very important for the training and testing process of deep learning, and can even play a decisive role. In order to enable deep learning to use feature vectors more effectively, many attention models have been proposed and widely used in various types of deep learning tasks, such as image classification, image recognition, and subtitle generation. Meanwhile, different kinds of attention models are also frequent...

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
CPCG06V40/10G06V20/46G06F18/2413G06F18/25
Inventor 冀中李晟嘉
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products