Distortion Estimation Through Explicit Modeling of the Refractive Surface
This addresses a specific calibration challenge in 3D computer vision for applications like robotics or surveillance, but it is incremental as it builds on existing distortion correction methods.
The paper tackled the problem of image distortion caused by refraction when cameras are behind protective glass, by modeling the refractive surface geometry and using an RBF neural network for parameter estimation, achieving results tested on synthetic and real-world data.
Precise calibration is a must for high reliance 3D computer vision algorithms. A challenging case is when the camera is behind a protective glass or transparent object: due to refraction, the image is heavily distorted; the pinhole camera model alone can not be used and a distortion correction step is required. By directly modeling the geometry of the refractive media, we build the image generation process by tracing individual light rays from the camera to a target. Comparing the generated images to their distorted - observed - counterparts, we estimate the geometry parameters of the refractive surface via model inversion by employing an RBF neural network. We present an image collection methodology that produces data suited for finding the distortion parameters and test our algorithm on synthetic and real-world data. We analyze the results of the algorithm.