Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Animal behavior identification method and apparatus based on transfer learning

A technology of transfer learning and recognition method, applied in the field of animal behavior recognition and device based on transfer learning, which can solve problems such as difficulty in obtaining training data

Active Publication Date: 2016-10-26
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the difficulty in obtaining training data in animal behavior recognition, the present invention proposes a method and device for animal behavior recognition based on migration learning

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
  • Animal behavior identification method and apparatus based on transfer learning
  • Animal behavior identification method and apparatus based on transfer learning
  • Animal behavior identification method and apparatus based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Below in conjunction with example, and with reference to accompanying drawing, describe the concrete detail of the present invention, and provide experimental result and relevant analysis.

[0028] The present invention proposes a target animal behavior recognition method based on migration learning, which includes:

[0029] Step 101, extracting original features for each training sample in the training data set and each test sample in the test data set;

[0030] Step 102, using the domain adaptation learning method in transfer learning to map the original features into a common space to obtain new features;

[0031] Step 103, using the new features to train the SVM classifier to obtain the target animal behavior recognition model, and simultaneously test the target animal behavior recognition model;

[0032] Step 104, using the animal behavior recognition model to recognize the behavior of the target animal to be recognized.

[0033] In the above method, the training...

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 provides an animal behavior identification method and apparatus based on transfer learning (TL), i.e., the training sample in a training data set comprises one or more than one from the group composed of a human behavior sample, a non object animal behavior sample and an object animal behavior sample, and a test data set is an object animal behavior sample. The method comprises: step 101, extracting original characteristics for each training sample in the training data set and each test sample in the test data set; step 102, employing a domain adaptation learning (DAL) method in TL to map the original characteristics onto a common space to obtain new characteristics; step 103, utilizing the new characteristics to train a support vector machine (SVM) classifier, obtaining a behavior identification model, and meanwhile testing an object animal behavior identification model; and step 104, utilizing the animal behavior identification model to identify object animal behavior to be identified. The animal behavior identification method based on TL can effectively identify animal behaviors.

Description

technical field [0001] The invention belongs to the application of machine learning and computer vision technology in automatic recognition of animal behavior, and is suitable for various researches in animal behavior such as automatic recognition of animal behavior and analysis of abnormal animal behavior. Background technique [0002] With the increasing amount of surveillance video and network video, the technology of automatically identifying behavior in the video is becoming more and more important. Like human behavior recognition, animal behavior recognition is also very important. Its applications include wild animal behavior analysis, pet monitoring, etc. However, it is difficult to obtain training data of animal behavior videos, especially for some rare animals. [0003] Some philosophers and behavioral researchers believe that behavior is similar across species. Considering that the training data of human behavior is easy to obtain, we ask a new question, can the...

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): G06K9/00G06K9/62
CPCG06V20/52G06F18/2411
Inventor 王亮王威王洪松
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
Eureka Blog
Learn More
PatSnap group products