Constraints for Heterogeneous Sensor Auto-Calibration

This paper describes a framework for calibrating motion sensitive sensors attached to an autonomous vehicle. Based on camera auto-calibration techniques, we derive constraints relating sensor measurements to the relative position and orientation of different sensors. For the case of a camera and laser range finder, we present an auto-calibration algorithm for discrete motions. Auto-calibration tools are vital for real world use of vision algorithms, and the framework presented here is important to merge image sensors with GPS, inertial, infrared and ultra-sonic sensors.