Vehicle Crash Impact Detection Using Multi-Device Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle crash prediction systems face challenges in accuracy, particularly in verifying predictions before taking actions, as they often rely on data from a single mobile device, leading to potential false alarms and difficulties in independently confirming crash events.
Innovation Solution
A method and system that utilize data from two or more mobile devices to determine if multiple events correspond to the same crash event by aligning characteristics such as time, location, and point-of-impact, thereby improving verification and reducing false predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If crash prediction is performed based on data from a single mobile device, then the system complexity is low, but the accuracy and reliability of crash event verification deteriorates
Solution Approach 1:
The patent combines data from multiple mobile devices (first mobile device and second mobile device) to verify crash events. The server receives crash data from both devices and determines whether they correspond to the same crash event by comparing characteristics such as location, time, and impact patterns. This merging of multiple data sources improves verification accuracy while the server handles the coordination complexity centrally.
2Measurement precision
If multiple mobile devices are used for crash prediction, then the accuracy of crash event verification improves, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent introduces a server as an intermediary that receives crash data from multiple mobile devices, processes the data, and determines whether the events correspond to the same crash. The server performs the complex data correlation and comparison operations, while the mobile devices themselves remain relatively simple data collection and transmission units. This intermediary handles the data processing complexity centrally.
Solution Approach 2:
The system segments the crash detection function across multiple mobile devices, with each device independently detecting and reporting crash events. The server then segments the verification process by comparing specific characteristics (location, time, impact patterns) from different devices to determine if they represent the same event. This segmentation allows parallel data collection while maintaining manageable processing complexity.
Data Source
AI summary
Techniques are disclosed for detecting a point-of-impact of a vehicle collision. A mobile device receives a set of sensor measurements from sensors of the mobile device. The mobile device generates a crash feature vector from the sensor measurements and one or more point-of-impact features. The mobile device executes a set of classifiers using the crash feature vector and the one or more point-of-impact features. Each classifier of the set of classifiers is configured to generate an output that is partially indicative of a point-of-impact of the collision. The mobile device generates, from the output of each classifier of the set of classifiers, a prediction of a point of impact of the vehicle collision. The mobile device then transmits an indication of the point of impact to a remote device.