Real Space Information Learning for Selective Sensor Upload
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of efficiently uploading sensor data from mobile devices to a server for generating accurate real space information is hindered by slow communication speeds, especially when devices are moving, and the increasing data capacity requirements of high-resolution sensors like omni-directional cameras and three-dimensional image sensors.
Innovation Solution
A learning-type real space information generation system where information terminal devices prioritize the transmission of sensor data based on importance, using a feature model generated by a server computer to determine which data to transmit preferentially, optimizing data transfer in varying communication environments and energy levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data is transmitted from mobile devices to server in real time, then real space information can be generated accurately, but communication bandwidth consumption increases significantly
Solution Approach 1:
The system dynamically changes the transmission parameter (whether to transmit sensor data) based on the importance value calculated by the determination unit. Only sensor data with high importance values are transmitted to the server, while low importance data are discarded locally, thus reducing communication bandwidth consumption while maintaining accurate real space information generation.
2Measurement precision
If all sensor data is transmitted to server, then real space information accuracy is improved, but battery consumption of mobile devices increases
Solution Approach 1:
The system changes the transmission parameter based on importance evaluation. The determination unit calculates importance values for different sensor data, and only high-importance data are transmitted to the server. This selective transmission reduces the energy consumed by the transmission unit while maintaining the accuracy needed for real space information generation.
3Use of energy by moving object
If sensor data transmission is limited due to slow communication speed, then battery consumption is reduced, but real space information generation accuracy deteriorates
Solution Approach 1:
Instead of uniformly limiting all sensor data transmission, the system dynamically changes the transmission decision for each sensor data based on its calculated importance value. High-importance data are transmitted even under communication constraints, while low-importance data are discarded. This ensures accurate real space information generation is maintained while minimizing battery consumption.
Solution Approach 2:
The determination unit extracts and identifies the essential and important information from sensor data by calculating importance values. Only the extracted high-importance sensor data are transmitted to the server, separating essential data from non-essential data. This extraction process ensures accuracy is maintained with minimal data transmission.
4Measurement precision
If high-resolution cameras and three-dimensional image sensors are used, then sensor data quality is improved, but communication bandwidth requirement increases
Solution Approach 1:
The system changes the transmission parameter based on the importance of each sensor data item. Even with high-resolution cameras and three-dimensional image sensors generating large amounts of data, only the high-importance data are transmitted to the server. Low-importance high-resolution data are discarded locally, thus reducing communication bandwidth requirements while maintaining sensor data quality for essential information.
Data Source
AI summary
A learning-type real space information generation system uses sensor data that can be efficiently uploaded from an information terminal device to a server, and which is capable of generating highly accurate real space information. A plurality of information terminal devices and a server are connected via in a communicable state via a network. The control unit of each information terminal device controls a transmission unit, based on the importance of elements configuring real space information, the importance being determined by an importance determination unit of the server such that sensor data corresponding to an element configuring the real space information and having high importance is preferentially transmitted. The generation unit of the server uses a feature model to generate real space information, based on elements configuring real space information and having high importance extracted by an extraction unit from the most recent sensor data received by a reception unit.