Video Coding Complexity Prediction via Frame Difference Histograms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video coding complexity prediction methods are inefficient due to time-consuming transcoding processes and uncertainty in setting transcoding parameters, leading to inaccurate coding complexity assessments.
Innovation Solution
A method involving acquiring attribute features and frame difference images from target videos, performing histogram calculations, and inputting these features into a coding complexity prediction model, which includes deep learning models for enhanced accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fast transcoding operation is performed to obtain coding complexity, then coding complexity can be predicted, but the process is time consuming and affects efficiency
Solution Approach 1:
The patent extracts only the essential features needed for coding complexity prediction (motion information, block transformation coefficients, quantization parameters) from the video data, rather than performing complete transcoding. This extraction approach obtains the necessary measurement data while avoiding the time-consuming full decoding and encoding process, thus resolving the contradiction between prediction accuracy and processing efficiency
Solution Approach 2:
The patent performs preliminary analysis of video features (extracting motion information, block coefficients, and quantization parameters) before actual transcoding. By preparing these key features in advance, the system can predict coding complexity without needing to complete the full transcoding process, improving efficiency while maintaining prediction capability
2Ease of operation
If manual transcoding parameter setting is performed, then transcoding can be controlled, but uncertainty in parameter setting affects accuracy of coding complexity prediction
Solution Approach 1:
The patent implements automatic determination of transcoding parameters based on the extracted video features and prediction model, eliminating the need for manual parameter setting. The system serves itself by using the analyzed video characteristics (motion information, block coefficients, quantization parameters) to automatically select optimal transcoding parameters, thereby removing the uncertainty associated with manual setting while maintaining operational control
Solution Approach 2:
The patent establishes a feedback mechanism where the prediction model continuously refines transcoding parameter selection based on the relationship between extracted video features and actual coding complexity. The system uses the analyzed features to inform parameter decisions, creating a closed-loop control that improves accuracy by eliminating manual intervention while maintaining adaptive control
Data Source
AI summary
A method, device, apparatus for predicting a video coding complexity and a computer-readable storage medium are provided. The method includes: acquiring an attribute feature of a target video; extracting a plurality of first target image frames from the target video; performing a frame difference calculation on the plurality of the first target image frames, to acquire a plurality of first frame difference images; determining a histogram feature for frame difference images of the target video according to a statistical histogram of each first frame difference image; and inputting a plurality of features of the target video into a coding complexity prediction model to acquire a coding complexity prediction value of the target video. Through the above method, the BPP prediction value can be acquired intelligently.