Gesture control method and device, and terminal device
A gesture control and gesture technology, applied in the field of information processing, can solve the problems of occupying network resources, occupying client system resources, audience dislike, etc., to save system resources, reduce dislike, and increase interest.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] figure 1 It is a flow chart showing the gesture control method according to Embodiment 1 of the present invention. The method is performed by a computer system including a gesture control device.
[0046] refer to figure 1 , in step S110, perform gesture detection on the currently playing video image.
[0047] Wherein, the video image may be an image of a live video that is being broadcast live, may also be a video image in a recorded video, or may be a video image in the process of recording, etc. Gestures may include hand waving, scissors, fist clenching, clasping hands, closing or opening of palms, and the like.
[0048] In the implementation, take live video as an example. At present, there are multiple live video platforms, such as Huajiao live platform, YY live broadcast platform, etc. Each live broadcast platform includes multiple live broadcast rooms, and each live broadcast room will include at least one An anchor, an anchor can broadcast live video images ...
Embodiment 2
[0064] figure 2 It is a flow chart showing the method for obtaining the first convolutional network model and the second convolutional network model according to Embodiment 2 of the present invention.
[0065] The processing of performing gesture detection on the currently playing video image in step S110 in the first embodiment above can be implemented by using a corresponding feature extraction algorithm or using a neural network model such as a convolutional network model. In this embodiment, taking the convolutional network model as an example, the human hand candidate area where the human hand is located and gesture detection are performed on the video image. Therefore, the first convolutional network model for detecting the human hand candidate area in the image can be pre-trained and used for A second convolutional network model for gesture detection from human hand candidate regions. Among them, the gestures include: waving, scissors hand, fist clenching, clapping ha...
Embodiment 3
[0092] image 3 It is a flow chart showing the gesture control method according to Embodiment 3 of the present invention. Wherein, the video image is a live video image, and the business object is a special effect containing semantic information, which may specifically include at least one of the following special effects including advertising information: two-dimensional sticker special effects, three-dimensional special effects, particle special effects, etc.
[0093] In step S310, the currently played video image is acquired.
[0094] Wherein, for the content of the above step S310, refer to the related content of the step S110 in the above first embodiment, which will not be repeated here.
[0095] In this embodiment, the human hand candidate area corresponding to the hand information can be determined through the video image and the pre-trained convolutional network model, and hand gestures can be detected in the human hand candidate area. For the corresponding processin...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com