Method, device and equipment for determining video key data
A key data and determination method technology, applied in the field of video processing, can solve problems such as unreasonable key data determination methods, achieve reasonable acquisition, improve work efficiency, and reduce work intensity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] In Embodiment 1 of the present invention, a method for determining video key data is provided, such as figure 2 As shown, it specifically includes the following steps:
[0030] S201. Decode the video to be processed, and extract an I frame of each video frame.
[0031] Further, in the prior art, when decoding the encoded and compressed video, the key frames of each video frame in the video can be extracted, that is, the I frame, and the I frame can be understood as a complete reservation of a frame of picture, which can Provides complete image information for the frame image.
[0032] S202. Perform face recognition on each extracted I frame by using a face recognition algorithm.
[0033] In this step, a face recognition algorithm in the prior art may be used, for example, a face detection and recognition algorithm is used to perform face recognition on each extracted I frame.
[0034] S203. According to the result of face recognition, determine the face that appears...
Embodiment 2
[0049] In Embodiment 2 of the present invention, a method for determining video key data is provided, such as Figure 4 As shown, it specifically includes the following steps:
[0050] S401. Using a face recognition algorithm, perform face recognition on each video frame of the video to be processed.
[0051] In this step, if before the video to be processed is processed, the video to be processed is decoded, and the I frame of each video frame is extracted, this step is: adopt a face recognition algorithm to perform face recognition on each extracted I frame.
[0052] S402. According to the result of face recognition, determine the face that appears most frequently in each video frame as the key face.
[0053]Further, this step can be specifically implemented as: for each recognized human face, compare the human face with the recognized human faces; when the human face matches any recognized human face, compare the The number of occurrences of the identified human face is i...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


