A remote control method for intelligent drones based on binocular gesture recognition
A gesture recognition and remote control technology, applied in character and pattern recognition, input/output process of data processing, mechanical mode conversion, etc., to achieve the effect of improving detection rate and recognition rate, high flexibility, and personalized control.
Active Publication Date: 2021-05-25
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The current main method of drone control is still based on remote control, or to recognize and track simple specific gestures in a short distance, but the long-range still depends on the remote control. It is an interaction method that conforms to human instincts. New users need to practice constantly to master the control skills. However, if a technology that conforms to human natural interaction habits and controls drones through gestures is invented, it will be a step forward. A big step towards more natural human-computer interaction
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0070] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.
[0071] This system combines intelligent gesture recognition and tracking technology based on binocular stereo vision with the UAV flight platform, so that the UAV can complete different flight tasks according to human intentions, thus realizing the natural human-machine interaction on the flight platform. Collaborative work function. The system is divided into two parts in terms of function, which are static two-hand gesture combination recognition and dynamic three-dimensional gesture tracking. Among them, the visual static recognition module innovatively adopts real-time feature pre-extraction and training technology. While ensuring real-time performance, the correct recognition rate of gestures has reached more than 99%, which meets the real-time and security requirements of gesture-controlled drones. At the same time, it also enables the ...
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
Login to View More Abstract
The invention relates to a method for remote control of an intelligent drone based on binocular gesture recognition, which includes the following steps: collecting multi-frame images of different gestures before operation, extracting hand area and hand feature information based on HSV information, and calculating the parameters of different gestures. The mean and variance of hand feature information; during operation, a binocular camera is used to collect the current gesture image, and a multi-feature hierarchical filtering algorithm is used to process and identify the current gesture image; HSV information, Gaussian filtering, and continuous adaptive mean drift Camshift algorithm are used to The depth image and color image of the current gesture image are processed to obtain the three-dimensional coordinates of the final tracking ROI area; the actual bending curve of the gesture is planned into the actual movement trajectory of the drone in real time. The present invention realizes online control of the flight trajectory by converting the results of gesture recognition into UAV control signals and sending them to the UAV. The human-machine collaborative operation has high real-time, accuracy and reliability.
Description
technical field [0001] The invention belongs to the technical field of pattern recognition and automation, and in particular relates to a remote control method for an intelligent drone based on binocular gesture recognition. Background technique [0002] With the expansion of the application field of drones, drones are gradually integrated into human production and life, and their relationship with humans is becoming increasingly close. Therefore, it is urgent to coordinate drones and humans closely. Good human-computer interaction with drones is an important basis for "human-machine integration" and "human-machine collaboration". Gesture is the most important way of non-verbal communication between people. If gesture interaction is applied to the flight control of UAV, it can make the interaction between UAV and human more convenient and natural. The close coordination of the two is conducive to the realization of human-machine integration. Gesture recognition is an impor...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/32G06K9/46G06T5/20G06T5/30G06T7/11G06T7/246G06F3/01
CPCG06F3/017G06T5/20G06T5/30G06T7/11G06T7/246G06T2207/10024G06T2207/20108G06T2207/20104G06V40/117G06V40/113G06V10/25G06V10/56
Inventor 华春生陈博何玉庆代波韩建达
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI