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

Repeated action recognition method, device, medium and equipment

A technology of repetitive actions and recognition methods, applied in the field of computer vision, can solve problems such as inability to supervise staff and safety problems, and achieve the effect of improving the efficiency of food safety supervision, reducing labor and material costs, and improving accuracy.

Active Publication Date: 2022-03-08
东莞先知大数据有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing tableware cleaning for canteens generally adopts manual cleaning methods. Due to the large flow of people in schools, enterprises, factories and other canteens and the concentration of meal time, many people often send the tableware after meals to the plate recycling place at the same time. The stacking of disks puts a lot of pressure on the staff to recover and clean. Once the staff is slack and irresponsible, safety problems are prone to occur. Although monitoring is installed in the cleaning room, the current video surveillance return visit cannot be realized through random inspection. The performance of staff on the job is fully supervised, and there are great loopholes and potential safety hazards

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
  • Repeated action recognition method, device, medium and equipment
  • Repeated action recognition method, device, medium and equipment
  • Repeated action recognition method, device, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification Obviously, the described embodiments are only some of the embodiments in the description, not all of them. Based on one or more embodiments in the description, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the embodiments of the description.

[0052] The embodiments provided in this specification can be applied to electronic equipment such as terminal equipment, computer systems, and servers, which can operate together with many other general-purpose or special-purpose computer system environments or configurations. Examples of well-known terminal equipment, comput...

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 this specification discloses a repetitive action recognition method, device and electronic equipment. The method includes inputting each frame of image into a pre-trained operation area recognition model and operator recognition model to obtain an operation area detection frame and an operator detection frame. Screen the operators in the operating area, input the screened images into the pre-trained body recognition model, obtain the operator's torso information and arm information, and perform single action recognition on the operator in each operating area based on the torso information and arm information ; Calculate the time when there is a single action in the operation area with the same serial number in different frame images of the video to be tested. When the time of the single action is greater than the time threshold, it is judged that the operator in the operation area has performed a repeated action. It helps to improve the accuracy of repetitive action recognition, effectively supervise non-standard repetitive actions, improve the efficiency of food safety supervision, and reduce the cost of manpower and material resources for enterprises.

Description

technical field [0001] This description relates to the technical field of computer vision, and in particular to a repetitive action recognition method, device, medium and equipment. Background technique [0002] Schools, enterprises, factories and other canteens have a large number of diners. Food safety involves all aspects. Not only must the source of food materials be reliable and the processing process is safe and hygienic, but if the tableware is not cleaned cleanly, the remaining food residues will produce harmful substances and breed harmful bacteria. It will pose a threat to the health of dining employees in schools, enterprises, and factories, so the disinfection and cleaning of tableware cannot be ignored. [0003] The existing tableware cleaning for canteens generally adopts manual cleaning. Due to the large flow of people in schools, enterprises, factories and other canteens and the concentration of meal time, many people often send the tableware after meals to t...

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 Patents(China)
IPC IPC(8): G06V40/20G06V20/40G06V10/764G06V10/774G06V10/82G06K9/62G06Q10/06G06Q50/04G06N3/04
CPCG06Q10/06393G06Q50/04G06V40/20G06V20/46G06N3/045G06F18/24G06F18/214Y02P90/30
Inventor 梁帆
Owner 东莞先知大数据有限公司