Polarimetric imaging has been applied in a growing number of applications in robotic vision (ex. underwater navigation, glare removal, de-hazing, object classification, and depth estimation). One can find on the market RGB Polarization cameras that can capture both color and polarimetric state of the light in a single snapshot. Due to the sensor's characteristic dispersion, and the use of lenses, it is crucial to calibrate these types of cameras so as to obtain correct polarization measurements. The calibration methods that have been developed so far are either not adapted to this type of cameras, or they require complex equipment and time consuming experiments in strict setups. In this paper, we propose a new method to overcome the need for complex optical systems to efficiently calibrate these cameras. We show that the proposed calibration method has several advantages such as that any user can easily calibrate the camera using a uniform, linearly polarized light source without any a priori knowledge of its polarization state, and with a limited number of acquisitions. We will make our calibration code publicly available.
翻译:在越来越多的机器人视觉应用中应用了几何成像(例如水下导航、玻璃除去、脱色、物体分类和深度估计),人们可以在市场上找到RGB极化摄像机,这种摄像机可以在单一的快照中捕捉光的颜色和极度状态。由于传感器的特性分散和使用镜片,必须校准这些类型的照相机,以便获得正确的极化测量结果。迄今为止开发的校准方法要么没有适应这种类型的照相机,要么需要复杂的设备和严格设置的耗时试验。在这个文件中,我们提出一种新的方法,以克服复杂的光学系统需要,以便有效地校准这些照相机。我们表明,拟议的校准方法有若干优点,例如任何用户都可以使用统一的线性极化光源来很容易校准这些照相机,而不必事先知道其极化状态,而且取得的数量也有限。我们将公开我们的校准代码。