ROI-based video coding method and system and video transmission and coding system
A technology of video coding and coding, which is applied in closed-circuit television systems, video conference systems, two-way working systems, etc., can solve problems such as failure to achieve satisfactory results, reduce user visual experience, and fail to improve the subjective visual quality of pictures.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0134] Image 6 A real-time video encoding method 400 according to Embodiment 1 of the present invention is shown. The system is a real-time video communication / recording system for adaptively extracting ROI with the following characteristics: the background is relatively fixed, and the panorama is dominated by head-and-shoulders sequences or other moving objects. The method 400 includes:
[0135] In step S401, a basic DNN model and a training framework are selected, and a DNN model without motion estimation information and a DNN model combined with motion estimation information are established according to the basic DNN model.
[0136] In step S402, the following types of short videos are selected to form the original training set: video conference content, live video content, video surveillance content, and news broadcast content; foreground and background are marked. Based on the original training set, establish a training set for labeling ROI areas and a training set for...
Embodiment 2
[0142] Figure 7 The second preferred embodiment according to the present invention is shown, which specifically relates to a video transmission and encoding system 500, which includes a camera 501 and the above-mentioned video encoding device 300. The camera 501 is configured to collect images in real time, and the video frame acquisition unit 301 of the video encoding device 300 communicates with the camera 501 to obtain the images captured by the camera in real time as the video to be encoded, and use the neural network model to process the image Perform ROI identification and extraction, and encode according to the ROI extraction results, and then use it for transmission or storage. Additionally preferably, the video transmission and encoding system 500 may further include a camera control mechanism 502, which is connected to the camera and can control the angle and / or focal length of the camera. For example, a preset area can be set in the field of view of the camera 501...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


