High-efficiency video coding intra-frame CTU division method and system
A high-efficiency video and encoding frame technology, applied in neural learning methods, digital video signal modification, biological neural network models, etc., can solve the problems of shortening encoding time, high computational complexity, and long encoding time, and achieve shortening encoding time , reduce computational complexity, and ensure accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] figure 1 A schematic flowchart showing a method for dividing CTUs in a high-efficiency video coding frame proposed in an embodiment of the present invention, including the following steps:
[0069] S1. Collect an image data set, and use the image data set to make video sets of different resolutions;
[0070] There are many methods for making a video set. In this embodiment, the collected image data set is a RAISE ultra-high-definition image set, and four YUV format video sets with different resolutions are produced from the RAISE ultra-high-definition image set. The resolutions are Select several 4928x3264, 2560x1600, 1536x1024, 704x576; 4928x3264 ultra-high-definition images, and then downsample some photos to three resolutions of 2560x1600, 1536x1024, 704x576, and randomly divide the YUV format video set of each resolution into 90 % of the training set, 5% of the validation set and 5% of the test set; for the HEVC reference software HM16.20, use the All_intra configu...
Embodiment 2
[0093] image 3 Represents the structure diagram of the A neural network proposed in the embodiment of the present invention, such as image 3 As shown, A neural network includes a first convolution block, a second convolution block, a third convolution block, a fourth convolution block, a fifth convolution block, a fully connected layer and an output layer connected in sequence; the first volume The accumulation block consists of one convolutional layer, and each of the second convolutional block, the third convolutional block, the fourth convolutional block, and the fifth convolutional block consists of two convolutional layers, and the two convolutional The buildup parameters are set the same; see Figure 4 , the first convolution block is set to 64 convolution kernels, and the size of the convolution kernel is 7x7; the second convolution block is set to 64 convolution kernels, and the size of the convolution kernel is 3x3; the third convolution block is It is set to 128 ...
Embodiment 3
[0099] like Figure 5 As shown, the B neural network includes the first convolutional layer, the second convolutional layer, the pooling layer, the third convolutional layer, the fourth convolutional layer, the fully connected layer and the output layer; the first layer of volume The convolution layer is set to 32 convolution kernels, and the size of the convolution kernel is 3x3; the second convolution layer is set to 64 convolution kernels, and the size of the convolution kernel is 3x3; the pooling layer is set to AvgPool operation , the pooling kernel size is 2x2; the third convolution layer is set to 64 convolution kernels, and the size of the convolution kernel is 2x2; the fourth convolution layer is set to 128 convolution kernels, and the size is 2x2;
[0100] The fully connected layer includes two hidden layers, which are randomly lost between the second hidden layer and the output layer with a probability of 50%: the output layer is activated by the Sigmoid function, ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More