Light Pose Calibration for Camera-light Vision Systems
This addresses the challenge of reliable vision for robots or systems operating in darkness with artificial lighting, though it appears incremental as it builds on physical light propagation principles.
The paper tackles the problem of nonuniform and dynamic illumination degrading computer vision in dark environments by introducing a light calibration method that estimates light source poses using multi-view images of a reference plane, achieving robust and consistent results as shown in statistical evaluations.
Illuminating a scene with artificial light is a prerequisite for seeing in dark environments. However, nonuniform and dynamic illumination can deteriorate or even break computer vision approaches, for instance when operating a robot with headlights in the darkness. This paper presents a novel light calibration approach by taking multi-view and -distance images of a reference plane in order to provide pose information of the employed light sources to the computer vision system. By following a physical light propagation approach, under consideration of energy preservation, the estimation of light poses is solved by minimizing of the differences between real and rendered pixel intensities. During the evaluation we show the robustness and consistency of this method by statistically analyzing the light pose estimation results with different setups. Although the results are demonstrated using a rotationally-symmetric non-isotropic light, the method is suited also for non-symmetric lights.