Pinch gesture detection and recognition method, device and system
AssigneeQingdao Pico Technology Co., Ltd.
InventorTao Wu
Life of this patent
Estimating the term…
Abstract
The present application relates to the technical field of image recognition and provides a pinch gesture detection and recognition method, which is applied to an electronic device and includes: acquiring, in real time, image data of each frame in a video to be detected; performing a hand location detection on the image data based on a pre-trained hand detection model, to determine a hand position of the image data; performing a skeleton point recognition at the hand position based on the pre-trained skeleton point recognition model, to determine a preset number of skeleton points at the hand position; and determining whether a hand corresponding to the image data is in a pinch gesture or not according to information of a distance between the skeleton points of preset fingers.
Claims20
A pinch gesture detection and recognition method, applied to an electronic device, comprising:
- acquiring, in real time, image data of each frame in a video to be detected;
- performing a hand location detection on the image data based on a pre-trained hand detection model, to determine a hand position of the image data;
- performing a skeleton point recognition at the hand position based on a pre-trained skeleton point recognition model, to determine a preset number of skeleton points at the hand position;
- and
- determining whether a hand corresponding to the image data is in a pinch gesture or not according to information of a distance between the skeleton points of preset fingers,
- wherein the determining the preset number of skeleton points at the hand position comprises:
- determining two-dimensional coordinate information of the preset number of skeleton points at the hand position based on the skeleton point recognition model;
- and
- acquiring three-dimensional position coordinate information corresponding to the two-dimensional coordinate information in real time according to the two-dimensional coordinate information and a stereoscopic triangulation imaging principle;
- wherein the three-dimensional position coordinate information is used for determining the information of the distance between the skeleton points of the preset fingers, and/or
- wherein the method further comprises:
- acquiring pinch gesture information of the image data of a preset number of continuous frames;
- and
- determining the hand in the video to be detected is in the pinch gesture in a case where the hands of the image data of the preset number of frames are all in pinch gestures.
An electronic device comprising:
- a memory, a processor and a camera device, wherein the memory includes a pinch gesture detection and recognition program, when the pinch gesture detection and recognition program is executed by the processor, the following operations are implemented:
- acquiring, in real time, image data of each frame in a video to be detected;
- performing a hand location detection on the image data based on a pre-trained hand detection model, to determine a hand position of the image data;
- performing a skeleton point recognition at the hand position based on the pre-trained skeleton point recognition model, to determine a preset number of skeleton points at the hand position;
- and
- determining whether the hand is in a pinch gesture or not according to information of a distance between the skeleton points of preset fingers,
- wherein the determining the preset number of skeleton points at the hand position comprises:
- determining two-dimensional coordinate information of the preset number of skeleton points at the hand position based on the skeleton point recognition model;
- and
- acquiring three-dimensional position coordinate information corresponding to the two-dimensional coordinate information in real time according to the two-dimensional coordinate information and a stereoscopic triangulation imaging principle;
- wherein the three-dimensional position coordinate information is used for determining the information of the distance between the skeleton points of the preset fingers, and/or
- wherein when the pinch gesture detection and recognition program is executed by the processor, the following further operations are implemented;
- acquiring pinch gesture information of the image data of a preset number of continuous frames;
- and
- determining the hand in the video to be detected is in the pinch gesture in a case where the hands of the image data of the preset number of frames are all in pinch gestures.
A pinch gesture detection and recognition system, comprises a memory storing instructions and a processor in communication with the memory, wherein the processor is configured to execute the instructions to:
- acquire, in real time, image data of each frame in a video to be detected;
- perform a hand location detection on the image data based on a pre-trained hand detection model, to determine a hand position of the image data;
- perform a skeleton point recognition at the hand position based on the pre-trained skeleton point recognition model, to determine a preset number of skeleton points at the hand position;
- and
- determine whether a hand corresponding to the image data is in a pinch gesture or not according to information of a distance between the skeleton points of preset fingers,
- wherein the processor, when determine the preset number of skeleton points at the hand position, is further configured to:
- determine two-dimensional coordinate information of the preset number of skeleton points at the hand position based on the skeleton point recognition model;
- and
- acquire three-dimensional position coordinate information corresponding to the two-dimensional coordinate information in real time according to the two-dimensional coordinate information and a stereoscopic triangulation imaging principle;
- wherein the three-dimensional position coordinate information is used for determining the information of the distance between the skeleton points of the preset fingers, and/or
- wherein the processor is further configured to:
- acquire pinch gesture information of the image data of a preset number of continuous frames;
- and
- determine the hand in the video to be detected is in the pinch gesture in a case where the hands of the image data of the preset number of frames are all in pinch gestures.
Dependencies are inferred from the claim text.