Targetless Rotational Auto-Calibration of Radar and Camera for Intelligent Transportation Systems
Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception. The calibration of these heterogeneous sensor types in an automatic fashion during system operation is challenging due to differing physical measurement principles and the high sparsity of traffic radars. We propose – to the best of our knowledge – the first data-driven method for automatic rotational radar-camera calibration without dedicated calibration targets. Our approach is based on a coarse and a fine convolutional neural network. We employ a boosting-inspired training algorithm, where we train the fine network on the residual error of the coarse network. Due to the unavailability of public datasets combining radar and camera measurements, we recorded our own real-world data. We demonstrate that our method is able to reach precise and robust sensor registration and show its generalization capabilities to different sensor alignments and perspectives.
FURTHER CURRENT TOPICS
Resilience for sensors and algorithms: 3 errors in focus
The external infrastructure plays an important role in compensating for sensor errors and making connected driving safer and more reliable. AI expert Dinu Purice from Providentia++ partner Cognition Factory is working on algorithms to improve reliabilit.
Plausibility checks of sensors: Particularly efficient in networks
The more sensors are integrated in a network such as Providentia++, the easier it is to find errors. Intel has developed a plausibility check for the roadside infrastructure monitoring sensors. Researcher Dr. Florian Geißler on identifying and excluding bad measurements.
Traffic: Digitalizing like a real-time company
The more traffic is digitalized, the better accidents and traffic jams can be prevented. Real-time decisions have long been established in companies. What can we learn from the world of business? A commentary by Prof. Alois Knoll.