Distributed AR Processing via Trigger-Based Offloading
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Augmented reality systems face disruptions in user experience due to computationally intensive operations, particularly in object detection and tracking, which can lead to latency issues and inefficient processing.
Innovation Solution
A distributed processing system where latency-sensitive operations are performed on a mobile platform, while computationally intensive operations are offloaded to a remote server, allowing for efficient data processing and minimizing network transmissions by using a trigger event-based data transmission mechanism.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If computationally intensive operations are performed on the mobile platform, then processing capability is improved, but latency and user experience disruption worsen
Solution Approach 1:
The system segments processing operations into two categories: latency-sensitive operations performed locally on the mobile platform, and computationally intensive but latency-insensitive operations offloaded to a remote server. This segmentation allows each type of operation to be executed in the most appropriate environment, resolving the contradiction between processing power and latency.
Solution Approach 2:
A trigger event-based mechanism acts as an intermediary between the mobile platform and remote server. The mobile platform monitors for trigger events (changes in sensor data) and only transmits data to the server when such events occur. This intermediary approach minimizes network transmissions while ensuring necessary data is processed, reducing latency without sacrificing processing capability.
2Measurement precision
If sensor data is transmitted frequently to the server, then processing accuracy is improved, but network overhead and latency worsen
Solution Approach 1:
Instead of continuous transmission, the system uses periodic action triggered by specific events. The mobile platform transmits sensor data to the server only when trigger events occur (changes in sensor data relative to previously acquired data). This periodic transmission approach maintains processing accuracy by ensuring relevant data is sent while minimizing network overhead by avoiding unnecessary transmissions.
3Adaptability or versatility
If all operations are performed on the mobile platform, then system independence is improved, but computational load and energy consumption worsen
Solution Approach 1:
The system segments computational tasks between the mobile platform and remote server based on their characteristics. Latency-sensitive operations remain on the mobile platform maintaining system independence, while computationally intensive operations are offloaded to reduce energy consumption. This segmentation resolves the contradiction between system independence and energy efficiency.
Solution Approach 2:
The system extracts computationally intensive but latency-insensitive operations from the mobile platform and places them on a remote server. This extraction reduces the computational load and energy consumption on the mobile device while maintaining overall system functionality through the trigger event-based transmission mechanism.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A mobile platform efficiently processes sensor data, including image data, using distributed processing in which latency sensitive operations are performed on the mobile platform, while latency insensitive, but computationally intensive operations are performed on a remote server. The mobile platform acquires sensor data, such as image data, and determines whether there is a trigger event to transmit the sensor data to the server. The trigger event may be a change in the sensor data relative to previously acquired sensor data, e.g., a scene change in an image. When a change is present, the sensor data may be transmitted to the server for processing. The server processes the sensor data and returns information related to the sensor data, such as identification of an object in an image or a reference image or model. The mobile platform may then perform reference based tracking using the identified object or reference image or model.