Digital Video Reference Frame Compression via Adaptive Bit Truncation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital video frame buffer compression methods require significant memory access time and power consumption, particularly when accessing referencing frames, which can lead to bottlenecks in semiconductor memory I/O bandwidth.
Innovation Solution
A method for efficient digital video referencing frame image compression and decompression that reduces memory density and access time by determining pixel block lengths for lossless compression, calculating differential values for simpler patterns, applying transform functions and quantization for complex patterns, and adjusting bit rates between luminance and chrominance components, while truncating bits in less complex blocks to allocate more bits to complex patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple memory chips are used to store referencing frames to overcome I/O bandwidth limitations, then memory storage capacity is improved, but device complexity and cost increase linearly
Solution Approach 1:
The referencing frame buffer is segmented into multiple compression units, each capable of independently compressing and storing frame data. This segmentation allows the system to achieve high storage capacity without requiring proportionally high device complexity, as each unit operates autonomously with dedicated compression logic.
Solution Approach 2:
Frame data is compressed in advance before being stored in the referencing frame buffer. By performing compression as a preliminary action during frame capture or transfer, the system reduces the amount of data that needs to be stored and accessed, thereby improving storage efficiency without requiring additional memory chips or increasing device complexity.
2Speed
If higher speed clock rate is used to access memory to solve I/O bandwidth bottleneck, then data transfer speed is improved, but power consumption and cost increase
Solution Approach 1:
The system changes the data representation parameters by applying compression algorithms that reduce the bit depth or precision of frame data stored in the referencing buffer. This parameter change allows slower memory access speeds to achieve the same effective data transfer rate, thereby reducing power consumption and avoiding the need for high-speed expensive memory.
3Loss of time
If referencing frame buffer is compressed to reduce memory density and access time, then memory access efficiency is improved, but computing time for compression increases
Solution Approach 1:
The compression algorithm applies partial compression to the referencing frame buffer, focusing computational effort on the most critical portions of the frame data that will be accessed most frequently. This partial action approach achieves sufficient compression to reduce memory access time without requiring complete compression of all frame data, thereby balancing computing time requirements.
4Reliability
If lossless compression is applied to all pixel blocks, then image quality is maintained, but bit rate and storage requirements increase
Solution Approach 1:
The system applies different compression strategies to different regions of the frame based on local characteristics. High-priority regions that require lossless compression are identified and processed with higher quality algorithms, while lower-priority regions use more aggressive compression. This local quality differentiation maintains overall image quality while significantly reducing the total bit rate and storage requirements.
Data Source
AI summary
The digital video referencing frame image is compressed block by block by applying lossless compression algorithm to pixel components with full length, or 1 bit, 2 bits, 3 bits or 4 bits LSB bits truncation. If a sub-block has high complexity which results in more than 3 bits error for most pixel components, a transfer algorithm with quantization and VLC coding is applied to compress this sub-block. Should the complexity is higher than a threshold or at least one sub-block having error of more than 3 bits for most pixel components, truncating 1 LSB bit of sub-block with simple pattern to save more bits to be allocate to code the sub-block with highest complex pattern.