| Conference/Proceedings | International Workshop on Traffic and Street Surveillance for Safety and Security at IEEE AVSS 2017 |
| Start date | 29.08.2017 |
| Address | Lecce, Italy |
| Pages | 1-6 |
| Author(s) | Erik Bochinski, Volker Eiselein and Thomas Sikora |
| Title | [Challenge winner IWOT4S] High-Speed Tracking-by-Detection Without Using Image Information |
| Abstract | Tracking-by-detection is a common approach to multi- object tracking. With ever increasing performances of ob- ject detectors, the basis for a tracker becomes much more reliable. In combination with commonly higher frame rates, this poses a shift in the challenges for a successful tracker. That shift enables the deployment of much simpler tracking algorithms which can compete with more sophisticated approaches at a fraction of the computational cost. We present such an algorithm and show with thorough experiments its potential using a wide range of object detectors. The proposed method can easily run at 100K fps while outperforming the state-of-the-art on the DETRAC vehicle tracking dataset. |
| Key words | multimedia analysis, Multi-Object Tracking, Tracking-by-Detection, Challenge, DETRAC, UA-DETRAC |
| Note | ISBN:978-1-5386-2939-0/17 |
| File | 1517Bochinski2017.pdf |