VISCODA: Vehicle Lane Merge Visual Benchmark

We present a dataset which enables the evaluation of vehicle localization approaches as well as the study of cooperative maneuvers. It consists of temporally synchronized multi-view video streams, accurate camera calibration, and ground truth vehicle descriptions, including position, heading, speed, and shape.
Objective 1: Evaluation of vehicle localization techniques
Objective 2: Learning of lane merge coordination
VLMV Dataset as presented at ICPR 2020/21:
- 85 lane merges performed by human drivers on 7 recording days
- Temporally synchronized multi-view video streams (four cameras)
- Accurate camera calibration
- Ground truth vehicle positions (GNSS RTK, camera-based)
www.vlmv.visco...
K. Cordes and H. Broszio: "Vehicle Lane Merge Visual Benchmark",
25th International Conference on Pattern Recognition (ICPR), pp. 715-722, 2021