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

Training method and training device

A training method and a technology of training samples, which are applied in the field of artificial intelligence, can solve the problems that the movement trajectory of key points is not smooth enough, and the recognition results are prone to jitter, etc., and achieve the effect of suppressing jitter and high accuracy

Pending Publication Date: 2022-04-12
NANJING RAYGEN HEALTH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The recognition results obtained in this way are prone to jitter, making the trajectory of key points not smooth enough

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
  • Training method and training device
  • Training method and training device
  • Training method and training device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The method and apparatus in the present application embodiment can be applied to a scene that recognizes the gesture of the rodents based on the image sequence. The image sequence can be a plurality of image frames in the video. Multiple image frames can be a plurality of image frames in a video. The image sequence can also be multiple images of animals collected by image acquisition devices such as cameras. The rodent can be, for example, a mouse or the like.

[0036] In order to facilitate the understanding of the present application embodiment, the background of the present application will be described in detail.

[0037]The behavior of biological neurons is related to the activity of animals, and the attitude variation of animals typically causing corresponding changes in neurons. Therefore, the exploration of the connection and interactive mode of complex network composed of neurons under specific behavior is very important in the field of neuroscience and medical. Th...

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 a training method and a training device. The method comprises the following steps: acquiring a training sample, wherein the training sample is an image sequence for recording rodent movement; inputting the training sample into a neural network model to obtain a recognition result of the posture of the rodent, the recognition result comprising key points in the posture of the rodent; and training the neural network model by using a gradient descent method by using a loss function according to the recognition result of the posture of the rodent. Wherein the loss function comprises a time constraint term, and the time constraint term is used for constraining the position of a key point in the posture of the rodent between adjacent image frames in the image sequence. When the neural network model trained according to the method is used for posture recognition of rodents such as mice, the jitter phenomenon of the recognition result in the time domain can be effectively avoided.

Description

Technical field [0001] The present application relates to the field of artificial intelligence, and therefore specifically involves a training method and a training device. Background technique [0002] The gesture recognition refers to identifying and / or extracting and / or extracting the action and / or key points of the organisms in the image or video using the neural network model. [0003] In the prior art, when the key point in the image sequence of the rodent motion is performed, the key points in a single image or a single image frame are typically extracted, and the key points may be, for example, the joints of a rodent. . The identification result obtained in this way is prone to jitter, so that the motion trajectory of the key point is not smooth enough. Inventive content [0004] In view of this, the present application example provides a training method and a training device to improve the accuracy and identification efficiency of the neural network model in perfo...

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): G06V40/20G06V10/764G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08G06T7/246G06T7/269
Inventor 王瑶张珏程和平
Owner NANJING RAYGEN HEALTH CO LTD
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