Details
| Original language | English |
|---|---|
| Title of host publication | IWCTS 2023 - Proceedings of the 16th ACM SIGSPATIAL International Workshop on Computational Transportation Science |
| Editors | Olufemi A. Omitaomu, Andy Berres, Haowen Xu |
| Pages | 42-51 |
| Number of pages | 10 |
| ISBN (electronic) | 9798400703577 |
| Publication status | Published - 15 Nov 2023 |
| Event | 16th ACM SIGSPATIAL International Workshop on Computational Transportation Science, IWCTS 2023 - Hamburg, Germany Duration: 13 Nov 2023 → 13 Nov 2023 |
Abstract
Riding a bicycle in shared traffic alongside motor vehicles causes discomfort or even stress for many cyclists. Avoiding busy or crowded roads is only possible with good local knowledge, as no data is available on the frequency of encounters with motor vehicles for most roads. Acquiring a data set that combines smartphone sensor data with known vehicle encounters can become the foundation for a smartphone based moving vehicle detector. Therefore, readings from the omnipresent smartphone sensors magnetometer and barometer can be exploited as indicators of passing vehicles.In this paper, a novel approach is presented to detect vehicle encounters in smartphone sensor data. For this purpose, a modular mobile sensor platform is first constructed and set up to collect smartphone, camera and ultrasonic sensor data in real traffic scenarios. The platform is designed to be used with various sensor configurations to serve a broader set of use cases in the future. In the presented use case, the platform is constructed to create a reference data set of vehicle encounters consisting of location information, direction, distance, speed and further metadata. To this end, a methodology is presented to process the collected camera images and ultrasonic distance data.Furthermore, two smartphones are used to collect raw data from their magnetometer and barometric sensor. Based on both, the reference and the smartphones' data set, a classifier for the detection of vehicle encounters is then trained to operate on pure smartphone sensor data. Experiments on real data show that a Random Forest classifier can be successfully applied to recorded smartphone sensor data. The results prove that the presented approach is able to detect overtaking vehicle encounters with a F1-score of 71.0%, which is sufficient to rank different cycling routes by their 'stress factor'.
Keywords
- cycling, instrumented bicycle, machine-learning, overtaking distance, traffic safety
ASJC Scopus subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Social Sciences(all)
- Transportation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
IWCTS 2023 - Proceedings of the 16th ACM SIGSPATIAL International Workshop on Computational Transportation Science. ed. / Olufemi A. Omitaomu; Andy Berres; Haowen Xu. 2023. p. 42-51.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Smartphone Based Detection of Vehicle Encounters
AU - Schimansky, Tim Peter Jörg
AU - Wage, Oskar
AU - Golze, Jens
AU - Feuerhake, Udo
N1 - Funding Information: This work is partially funded by the German Federal Ministry for Digital and Transport (BMDV) grand 45FGU121E ’5GAPS’, German Federal Ministry for Economic Affairs and Energy (BMWi) grant 01ME19009B ’d-E-mand’ and German Research Foundation (DFG) GRK 1931 ’SocialCars’.
PY - 2023/11/15
Y1 - 2023/11/15
N2 - Riding a bicycle in shared traffic alongside motor vehicles causes discomfort or even stress for many cyclists. Avoiding busy or crowded roads is only possible with good local knowledge, as no data is available on the frequency of encounters with motor vehicles for most roads. Acquiring a data set that combines smartphone sensor data with known vehicle encounters can become the foundation for a smartphone based moving vehicle detector. Therefore, readings from the omnipresent smartphone sensors magnetometer and barometer can be exploited as indicators of passing vehicles.In this paper, a novel approach is presented to detect vehicle encounters in smartphone sensor data. For this purpose, a modular mobile sensor platform is first constructed and set up to collect smartphone, camera and ultrasonic sensor data in real traffic scenarios. The platform is designed to be used with various sensor configurations to serve a broader set of use cases in the future. In the presented use case, the platform is constructed to create a reference data set of vehicle encounters consisting of location information, direction, distance, speed and further metadata. To this end, a methodology is presented to process the collected camera images and ultrasonic distance data.Furthermore, two smartphones are used to collect raw data from their magnetometer and barometric sensor. Based on both, the reference and the smartphones' data set, a classifier for the detection of vehicle encounters is then trained to operate on pure smartphone sensor data. Experiments on real data show that a Random Forest classifier can be successfully applied to recorded smartphone sensor data. The results prove that the presented approach is able to detect overtaking vehicle encounters with a F1-score of 71.0%, which is sufficient to rank different cycling routes by their 'stress factor'.
AB - Riding a bicycle in shared traffic alongside motor vehicles causes discomfort or even stress for many cyclists. Avoiding busy or crowded roads is only possible with good local knowledge, as no data is available on the frequency of encounters with motor vehicles for most roads. Acquiring a data set that combines smartphone sensor data with known vehicle encounters can become the foundation for a smartphone based moving vehicle detector. Therefore, readings from the omnipresent smartphone sensors magnetometer and barometer can be exploited as indicators of passing vehicles.In this paper, a novel approach is presented to detect vehicle encounters in smartphone sensor data. For this purpose, a modular mobile sensor platform is first constructed and set up to collect smartphone, camera and ultrasonic sensor data in real traffic scenarios. The platform is designed to be used with various sensor configurations to serve a broader set of use cases in the future. In the presented use case, the platform is constructed to create a reference data set of vehicle encounters consisting of location information, direction, distance, speed and further metadata. To this end, a methodology is presented to process the collected camera images and ultrasonic distance data.Furthermore, two smartphones are used to collect raw data from their magnetometer and barometric sensor. Based on both, the reference and the smartphones' data set, a classifier for the detection of vehicle encounters is then trained to operate on pure smartphone sensor data. Experiments on real data show that a Random Forest classifier can be successfully applied to recorded smartphone sensor data. The results prove that the presented approach is able to detect overtaking vehicle encounters with a F1-score of 71.0%, which is sufficient to rank different cycling routes by their 'stress factor'.
KW - cycling
KW - instrumented bicycle
KW - machine-learning
KW - overtaking distance
KW - traffic safety
UR - http://www.scopus.com/inward/record.url?scp=85186747289&partnerID=8YFLogxK
U2 - 10.1145/3615895.3628173
DO - 10.1145/3615895.3628173
M3 - Conference contribution
AN - SCOPUS:85186747289
SP - 42
EP - 51
BT - IWCTS 2023 - Proceedings of the 16th ACM SIGSPATIAL International Workshop on Computational Transportation Science
A2 - Omitaomu, Olufemi A.
A2 - Berres, Andy
A2 - Xu, Haowen
T2 - 16th ACM SIGSPATIAL International Workshop on Computational Transportation Science, IWCTS 2023
Y2 - 13 November 2023 through 13 November 2023
ER -