Object-Based Data Compression for Higher Multidimensional Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for compressing multidimensional data, such as those using neural networks, often fail to achieve sufficient compression efficiency, particularly with sensor data like point cloud and image data from LiDAR sensors and cameras.
Innovation Solution
An information compression system that includes an acquisition section, a generation section, and a compression section, which determines objects and their senses, converts pixel values to identification information, and compresses the data using quantization and entropy encoding to reduce redundancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multidimensional data is compressed as is using existing neural network technology, then compression is achieved, but compression efficiency is insufficient
Solution Approach 1:
The patent segments the compression process into distinct functional sections: an acquisition section for obtaining data, a generation section for creating compression target data by determining objects and their senses, and a compression section for actual compression. This segmentation allows each section to be optimized independently, improving overall compression efficiency.
Solution Approach 2:
The generation section performs preliminary processing by determining objects and their senses before compression. This preliminary action converts raw data into structured compression target data, making the subsequent compression process more efficient and effective.
2Quantity of substance
If pixel values are converted to identification information, then data redundancy is reduced, but processing complexity increases
Solution Approach 1:
The patent changes the parameter representation from continuous pixel values to discrete identification information. This parameter transformation reduces data redundancy by mapping multiple similar pixel values to the same identification, while the structured approach manages processing complexity.
Solution Approach 2:
The generation section acts as an intermediary between the acquisition section and the compression section. It processes raw data into structured compression target data by determining objects and senses, serving as a mediator that prepares data for efficient compression while managing complexity.
Data Source
AI summary
The present disclosure provides an information compression system that is capable of achieving higher compression efficiency. A data acquisition section acquires data. A generation section (segmentation section and integration section) determines each object depicted by the data and a sense of each object, and according to results of the determination, generates compression target data by converting values of elements in the data to identification information indicating each object and the sense of each object. A data storage section generates compressed data by compressing the compression target data. This makes it possible to convert highly random element values to slightly random identification information and compress the resulting converted information while reducing the amount of information. Consequently, the compression ratio can be increased.