Video gesture recognition method and device based on skin color detection and deep learning
A deep learning and skin color detection technology, applied in the field of gesture recognition, can solve the problems of low gesture recognition efficiency and low recognition accuracy, and achieve the effects of improving gesture efficiency and gesture recognition accuracy, improving recognition effect, and shortening time.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0057] This embodiment provides a method for recognizing video gestures based on skin color detection and deep learning, please refer to figure 1 , the method includes:
[0058] First, step S1 is executed: video data is acquired, and the video data is composed of RGB images.
[0059] Specifically, devices such as a camera can be used to obtain video data, and the resolution of the identification data varies according to the configuration of the device, for example, it can be 1280*720. RGB image is the most important mode in digital images. RGB mode is an additive mode. When the values of R, G, and B all reach the maximum value, the three colors are synthesized into white.
[0060] Then step S2 is performed: based on the preset skin color feature segmentation model, the video data is processed frame by frame, the skin area is segmented, and the image corresponding to the skin area is binarized to obtain a binarized image.
[0061] Specifically, the preset skin color feature...
Embodiment 2
[0121] This embodiment provides a video gesture recognition device based on skin color detection and deep learning, please refer to Figure 7 , the device consists of:
[0122] Video data acquiring module 201, for acquiring video data, described video data is made up of RGB image;
[0123] The skin area segmentation module 202 is used to process the video data frame by frame based on the preset skin color feature segmentation model, segment the skin area, and perform binarization on the image corresponding to the skin area to obtain a binarized image;
[0124] The hand contour extraction module 203 is used to extract the hand contour from the binarized image;
[0125] The hand recognition module 204 is configured to recognize the extracted hand outline based on a preset gesture recognition model, wherein the preset gesture recognition model is obtained by training the existing training data using a pyramid pooling module and an attention mechanism, Among them, the ...
Embodiment 3
[0144] Based on the same inventive concept, this application also provides a kind of computer equipment, please refer to Figure 8 , including a storage 601, a processor 602, and a computer program 603 stored in the memory and operable on the processor. The processor 602 implements the method in Embodiment 1 when executing the above program.
[0145] For example, the computer device may be a smart device such as a PC, a tablet computer, or a mobile phone, and the computer device only needs to have an image recognition device, such as a camera, an image sensor, and the like.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More