Robot remote control method and human body bounding box determination method and system

Abstract

The invention relates to a robot remote control method and a human body bounding box determination method and system, and belongs to the technical field of image processing and robot control. The remote control method comprises the following steps: (1) displaying a robot field image at an operation end, and receiving operation video data of an operator; (2) in the image of the video data, based onthe joint point coordinate data in the previous frame of image, generating a cutting boundary frame for the human body image in the current frame of image; (3) cutting a current human body image based on the cutting boundary frame and converting the current human body image into a standard to-be-identified image; and (4) acquiring human body joint coordinate data in the current frame image basedon a pre-trained human body posture estimation network model, and generating a robot control instruction according to the joint coordinate data. According to the method, the real-time performance of control instruction generation is better ensured by simplifying the human body bounding box determination method, and the method can be widely applied to the fields of robot remote control and the like.

Description

technical field [0001] The present invention relates to the field of robot control based on image processing technology, in particular to a method and system capable of quickly determining the bounding box of a human body in a video image, a robot control method based on the method and a virtual animation generate method. Background technique [0002] With the development of robot technology, it replaces operators to perform related work in more and more industrial fields, such as industrial robots used in automobile production; in addition, it also directly replaces operators to perform related work in some dangerous working environments, such as Entering the deep sea operation environment, bomb disposal and mine clearance and other operating environments that will affect the safety of operators; the widespread use of robots in these fields can well ensure the personal safety of operators, but because the control technology of robots has not yet been To achieve a truly int...

AI Technical Summary

Problems solved by technology

The technical scheme identifies the joint coordinates based on the marks attached to the human body, so that the on-site operation robot can be controlled based on the identified joint coordinate data; in addition, real-time virtual animation can also be performed after identifying the joint coordinates of the human body based on this technology generation; however, this technology needs to use markers to mark joint points and perform image recognition. more complex

[0004] In addition, patent documents such as publication number CN109345504A disclose the use of models such as convolutional neural networks to determine the bounding box of the human body in order to prepare and quickly obtain the human body image area, but the calculation method is too bloated, and the calculation is time-consuming when implemented. Large, it is difficult to meet the real-time requirements of robot control

Images