Key point prediction method and device, electronic device and storage medium

A prediction method and key point technology, applied in the field of image recognition, can solve the problems of reduced prediction accuracy, inability to integrate time series features, and low prediction accuracy

Active Publication Date: 2018-06-26
BEIJING SENSETIME TECH DEV CO LTD
View PDF3 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the traditional predictions of key points of the human body are based on manually designed graphical models, which are limited by the performance capabilities of the models, resulting in low prediction accuracy
[0003] With the development of convolutional neural networks, the prediction technology of key points of the human bo

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
  • Key point prediction method and device, electronic device and storage medium
  • Key point prediction method and device, electronic device and storage medium
  • Key point prediction method and device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0122] Example 1

[0123] figure 1 A flowchart of a method for predicting key points provided in Embodiment 1 of the present invention. The method may be executed by a device for predicting key points provided in real time by the present invention, and the device may be implemented in software and / or hardware. For example, key points The predicting means may be implemented by a processor in which it is arranged to execute corresponding instructions stored in the memory. see figure 1 , the method includes:

[0124] S110. Acquire a target area in the video frame that includes the person to be identified.

[0125] The video to be processed includes at least one video frame, and each video frame includes a person to be identified. The target area refers to an area in the video frame that contains the person to be recognized. Optionally, the target area may be an original video frame, or a sub-image generated by performing image preprocessing on the original video frame. Exemp...

Example Embodiment

[0174] Embodiment 2

[0175] Figure 5 This is a flowchart of a method for predicting key points provided by the second embodiment of the present invention. On the basis of the above embodiment, a method for predicting key points by any neural network unit in the neural network is provided. Accordingly, the method specifically includes:

[0176] S210: Acquire a target area in the video frame that includes the person to be identified.

[0177] S220. Input the target region into any neural network unit in the neural network.

[0178] S230. Extract the contour feature map of the target area based on the first sub-network of any neural network unit.

[0179] S240. Combine the contour feature map, the key point heat map of the previous target area, and the standard center heat map in sequence to generate a combined feature map, and input the combined feature map into the long short-term memory sub-network of any neural network unit.

[0180] S250 , generating a memory feature m...

Example Embodiment

[0191] Embodiment 3

[0192] Figure 9 This is a flowchart of a method for predicting key points provided by the third embodiment of the present invention. On the basis of the above embodiment, a method for predicting key points by multiple neural network units in a neural network is provided. Accordingly, the method specifically includes:

[0193] S310: Acquire a target area in the video frame that includes the person to be identified.

[0194] S320: Group the target areas, and input the target areas in each group into the corresponding neural network units in the neural network, wherein the number of target areas in each group is the same as the number of neural network units in the neural network.

[0195] S330. Extract the contour feature map of the target area based on the first sub-network of the corresponding neural network unit.

[0196] S340 . Combine the contour feature map, the key point heat map of the previous target area, and the standard center heat map in se...

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 embodiment of the invention discloses a key point prediction method and device, an electronic device and a storage medium. The method comprises: a target area including a to-be-identified person in a video frame is obtained; the target area is inputted into any neural network unit in a neural network and a key point hotspot map is generated, wherein the neural network includes a plurality of cascaded neural network units, each neural network unit includes a long-term and short-term memory sub network for screening a memory feature according to the target area and an output result from thelong-term and short-term memory sub network corresponding to the previous-stage neural network unit of the current neural network unit, and the memory feature is used for determining the key point hotspot map; and on the basis of the key point hotspot, location information of a body key point in the video frame is determined. Therefore, quick and high-precision key point prediction of a video is realized; and the accuracy of the key point prediction is improved.

Description

technical field [0001] Embodiments of the present invention relate to image recognition technology, and in particular to a method, device, electronic device, and storage medium for predicting key points of a human body. Background technique [0002] The prediction of key points of the human body is an important research topic in the field of visual analysis of human motion, and is widely used in fields such as augmented reality, computer animation, and automatic photo processing. Most of the traditional predictions of key points of the human body are based on manually designed graphical models, which are limited by the performance of the models, resulting in low prediction accuracy. [0003] With the development of convolutional neural networks, the prediction technology of key points of the human body has also been rapidly developed, but the current predictions are all static image predictions, which cannot integrate temporal features, and the prediction errors of static ke...

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): G06K9/00G06K9/62G06K9/46
CPCG06V40/10G06V20/46G06V10/44G06F18/214
Inventor 杨涛颜深根
Owner BEIJING SENSETIME TECH DEV 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
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