Group behavior recognition model based on progressive relationship learning and training method thereof

A recognition model, progressive technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem of low accuracy of group behavior recognition

Pending Publication Date: 2019-11-29
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem of low group behavior recognition accuracy in the prior art, the first aspect of the present invention, a group behavior recognitio

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
  • Group behavior recognition model based on progressive relationship learning and training method thereof
  • Group behavior recognition model based on progressive relationship learning and training method thereof
  • Group behavior recognition model based on progressive relationship learning and training method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] Example 1: Group Behavior Recognition Model Based on Progressive Relational Learning

[0096] to combine Figure 1-Figure 4 The group behavior recognition model based on progressive relationship learning in this embodiment is described, the group behavior recognition model based on progressive relationship learning in this embodiment is as follows figure 1 Shown includes a semantic relational graph generation network, a reinforcement learning network, and a softmax classification layer.

[0097] 1. Semantic relationship graph generation network

[0098] The semantic relationship graph generation network is used to obtain the semantic relationship graph of individuals in selected video frames of the video clip to be recognized.

[0099] The method of obtaining the semantic relationship graph of individuals in the video frame in the semantic relationship graph generation network is as follows:

[0100] Step S110, constructing an initial semantic relationship graph base...

Embodiment 2

[0153] Embodiment 2: Training method of group behavior recognition model based on progressive relational learning

[0154] Based on the group behavior recognition model based on progressive relationship learning in the above embodiments, the training method of the group behavior recognition model based on progressive relationship learning in an embodiment of the present invention will be described in detail below.

[0155] The method for training a group behavior recognition model based on progressive relationship learning in an embodiment of the present invention is used to train the aforementioned group behavior recognition model based on progressive relationship learning to obtain a trained group behavior recognition model, thereby realizing the Recognition classification of crowd behavior in video clips. Its specific training methods are as follows: Figure 5 shown, including:

[0156] Step A100, obtaining a training sample set, the training sample set includes a plurali...

Embodiment 3

[0180] Embodiment 3: Group Behavior Recognition Method

[0181] The group behavior recognition method of the embodiment of the present invention includes:

[0182] Obtain the group behavior classification information of the video clip to be recognized through the trained group behavior recognition model;

[0183] The group behavior recognition model is the above-mentioned group behavior recognition model based on progressive relational learning;

[0184] The group behavior recognition model is trained by the above-mentioned group behavior recognition model training method based on progressive relational learning.

[0185] Those skilled in the art can clearly understand that for the convenience and brevity of the description, the working process and relevant instructions of the group behavior recognition model and its training method in the group behavior recognition method described above can refer to the aforementioned progressive relational learning-based The corresponding...

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 belongs to the field of behavior recognition, particularly relates to a group behavior recognition model based on progressive relation learning and a training method thereof, and aims tosolve the problem of low group behavior recognition accuracy in the prior art by mining key relations in group behaviors. The group behavior recognition model comprises a semantic relation graph generation network, a reinforcement learning network and a softmax classification layer. The network parameters of the other network are trained on the basis of alternately keeping the network parametersof one network unchanged/removing the network for the semantic relation graph network and the reinforcement learning network until a preset training end condition is met, and the trained group behavior recognition model is obtained. The group behavior recognition model obtained through the method has higher recognition accuracy.

Description

technical field [0001] The invention belongs to the field of behavior recognition, and in particular relates to a group behavior recognition model based on progressive relational learning and a training method thereof. Background technique [0002] Behavior recognition has a wide range of applications in the fields of intelligent monitoring, human-computer interaction and automatic driving. According to the number of individuals involved, behavior recognition can be divided into single individual behavior recognition, double individual behavior recognition and group behavior recognition. Group behavior recognition has the characteristics of many parameter individuals, not only needs to model the spatiotemporal dynamics of each individual, but also needs to model the complex interaction relationship between individuals. At the same time, group behavior videos are rich in a large amount of semantic noise, and the category of group behavior is usually only determined by a fe...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/53G06V20/41G06F18/217G06F18/214
Inventor 胡古月余山崔波何媛
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap