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

Training method and training device

A training method and training sample technology, applied in the field of artificial intelligence, can solve problems such as low accuracy rate, insufficient smoothness and continuity in the time domain of recognition results, and key points that cannot be correctly identified, so as to achieve the effect of ensuring continuity and high accuracy rate

Pending Publication Date: 2022-04-15
BEIJING CHAOWEIJING BIOLOGICAL TECH CO LTD +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The recognition results obtained by this single recognition method are not smooth and continuous in the time domain.
In addition; at the same time, when the image to be recognized is blurred or the key points are occluded, the key points in the image may not be correctly recognized, resulting in low recognition accuracy

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

[0038] The method and device in the embodiments of the present application can be applied to various scenarios based on gesture recognition of moving creatures in image sequences. The image sequence may be multiple image frames in the video. The multiple image frames may be consecutive multiple image frames in the video. The image sequence may also be multiple images of animals collected by an image collection device such as a camera. The moving creature may be an animal. The animal can be, for example, a rodent such as a mouse.

[0039]In order to facilitate the understanding of the embodiments of the present application, the background of the present application will be described in detail by taking gesture recognition of animals as an example.

[0040] The behavior of biological neurons is closely related to the activities of animals, and changes in the posture of animals usually cause corresponding changes in neurons. Therefore, exploring the connection and interaction...

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: when a neural network model is trained, adding a time constraint term and a space constraint term in a loss function; wherein the time constraint term is used for constraining the position of a key point in the attitude of the moving organism between adjacent image frames in the image sequence, and the space constraint term is used for limiting the position of the key point in the attitude of the moving organism in the same image frame. The neural network model trained according to the above method can ensure high accuracy when processing occluded and blurred images, and also can ensure continuity of an identification result in a time domain.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a training method and a training device. Background technique [0002] Gesture recognition refers to the use of neural network models to identify and / or extract the actions and / or key points of moving creatures in images or videos. [0003] In the prior art, when identifying key points in an image sequence recording the behavior of a moving creature, it usually relies on extracting and matching features in a single image or a single image frame in a moving creature video. The recognition results obtained by this single recognition method are not smooth and continuous in the time domain. In addition; at the same time, when the image to be recognized is blurred or the key points are occluded, the key points in the image may not be correctly recognized, resulting in a low recognition accuracy. Contents of the invention [0004] In view of this, the embo...

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): G06V40/10G06V20/05G06V20/40G06V10/62G06V10/776G06V10/82G06K9/62G06T7/254G06N3/04G06N3/08
CPCG06T7/254G06N3/08G06T2207/30241G06T2207/10016G06T2207/20224G06N3/045G06F18/217
Inventor 王瑶张珏程和平
Owner BEIJING CHAOWEIJING BIOLOGICAL TECH CO LTD