Designing a Multi-Modal Vehicle Data Capture System for Forensic Accident Analysis
Traffic accidents and road incidents are major concerns for governments, transportation safety agencies, and the public. Statistics indicate an increase in the number of accidents in Indonesia over the past few years. The primary contributing factors to these accidents include human, vehicle, and en...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/22/e3sconf_interconnects2025_01004.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Traffic accidents and road incidents are major concerns for governments, transportation safety agencies, and the public. Statistics indicate an increase in the number of accidents in Indonesia over the past few years. The primary contributing factors to these accidents include human, vehicle, and environmental elements. However, collecting evidence or data often poses challenges, particularly regarding driver statements and witness accounts. To address these issues, this study develops a data recording system for motor vehicles. The system records data such as speed, location, time of occurrence, vehicle tilt, as well as audio and video inside the cabin, using a Raspberry Pi 4 Model B and ESP32 as the main controllers. Testing was conducted on a car with simulations on provincial roads and highways to evaluate the performance of each sensor. The test results showed good performance, with the MPU6050 sensor error rate ranging from 0.028% to 0.123%, the Beitian Be-220 GPS sensor error rate at 2%, and latitude-longitude coordinates with an error margin of 0.000661% to 0.001403%. This system is expected to support traffic investigations and assist regulatory authorities by providing more accurate evidence, while also increasing awareness of road safety. |
|---|---|
| ISSN: | 2267-1242 |