- Jannik Fritsch, Introduction of KITTI-ROAD for Benchmarking Road Detection Algorithms (KeyNote).
- Guo, Fritsch and Alvarez, Towards co-evolution of road / lane detection and benchmarking (Open Discussion)
Regular Session (Workshop papers)
- Giovani Barnardes Vitor, Alessandro Correa Victorino and Janito Vaqueiro Ferreira, Comprehensive Performance Analysis of Road Detection Algorithms Using the Common Urban Kitti-Road Benchmark.
- Inna Stainvas and Yosi Buda, Performance Detection for Curb Detection Problem.
- Bihao Wang, Vincent Fremont and Sergio Alberto Rodriguez Florez, Color-Based Road Detection and its Evaluation on the KITTI Road Benchmark.
Regular Session (Conference papers)
- Patrick Shinzato, Denis Wolf and Christoph Stiller, Road Terrain Detection: Avoiding Common Obstacle Detection Assumptions using Sensor Fusion.
- Xiao Hu, Sergio Alberto Rodriguez Florez and Alexander Gepperth, A Multi-Modal System for Road Detection and Segmentation. Download video demo.
- Volker Patricio Schomerus, Dennis Rosebrock and Friedrich M. Wahl, Camera-based Lane Border Detection in Arbitrarily Structured Environments.
- Chunzhao Guo, Toyota Central R&D Labs., Inc., Japan
José M. Álvarez, NICTA, Australia
Jannik Fritsch, Honda Research Institute Europe, Germany
Andreas Geiger, Max Planck Institute for Intelligent Systems, Germany
Description of the workshop
Detecting the road area and ego-lane ahead of a vehicle is central to modern driver assistance systems. While lane-detection on well-marked roads is already available in modern vehicles, finding the boundaries of unmarked or weakly marked roads and lanes as they appear in inner-city and rural environments remains an unsolved problem due to the high variability in scene layout and illumination conditions, amongs others. While recent years have witnessed great interest in this subject, to date no commonly agreed upon benchmark exists, rendering a fair comparison amongst methods dif?cult. The target of this workshop is to bring together researchers active in the field in order to enable a better comparison of approaches. By encouraging submissions operating on public benchmarks (e.g., KITTI-ROAD) the workshop aims to foster research progress in road terrain and lane detection algorithms for application in real vehicles driving on arbitrary non-highway roads.
Relevant topics of interest include, but are not limited to:
- Road segmentation approaches operating on KITTI-ROAD,
- Ego lane detection approaches operating on KITTI-ROAD,
- New evaluation measures for comparing road terrain/lane detection algorithms,
- Comparison of available road terrain/lane detection benchmarks.
- New benchmarks for road terrain/lane detection algorithms.
Next Steps in Benchmarking Road Detection Algorithms
- Please, contact us in case you are interested in a future workshop.