Abstract
There is an increase in traffic volumes and, as such, a requirement for maximisation of the road capacity. It is crucial that there is awareness of the traffic volumes in order to make the right choices regarding road development. Video registrations and related software to video analysis to measure traffic volumes are increasingly used, but there is limited documentation on the reliability of these. This paper compares manual registrations, treated as ground truth, the hardware independent software RUBA and an on-the-shelf product. While the RUBA software, in general, had a reasonable precision on the direction parallel to the camera direction (8% and 3% deviations, respectively); it was less precise regarding transversal-driving vehicles (23% deviation). The on-the-shelf hardware had a significantly higher deviation regarding the two parallel directions, (35% and 67% deviations, respectively) and a reasonable deviation regarding transversal-driving vehicles (11% deviation). It indicates that on-the-shelf hardware might need further calibration in general.
| Original language | English |
|---|---|
| Journal | ITS World Congress |
| Volume | 6 |
| Number of pages | 11 |
| ISSN | x000-0181 |
| Publication status | Published - 2018 |
| Event | 25th ITS World Congress - Quality of Life - Bella Center, Copenhagen, Denmark Duration: 17 Sept 2018 → 21 Sept 2018 https://itsworldcongress.com/ |
Conference
| Conference | 25th ITS World Congress - Quality of Life |
|---|---|
| Location | Bella Center |
| Country/Territory | Denmark |
| City | Copenhagen |
| Period | 17/09/2018 → 21/09/2018 |
| Internet address |
Bibliographical note
Paper presented in SP7 - Data and informationKeywords
- Video detetion
- Data quality
- Traffic data
- Transport data