基于三维坐标转换的道面图像还原技术与试验

Theoretical and experimental investigation on road image reproduction based on 3D coordinate transformation

机场道面图像采集中存在数字图像失真问题,造成道面图像拼接和损伤识别困难。针对此问题,研究了相机小孔成像原理,将整体坐标系原点设置在道面上、局部坐标系原点设置在数字图像上。通过三维坐标转换公式,将数字图像关键角点在局部坐标系中的坐标转换为整体坐标系下的坐标,从而得到真实道面板数字图像,进而将不同道面板数字图像拼接得到更大范围的真实道面数字图像。为验证该理论可靠性,进行了室外对比试验,将A0号白纸作为模拟道面板,白纸接缝处粘结并涂黑色模拟嵌缝料,模拟道面上设置若干道面损伤,利用相机进行不同角度道面图像采集。结果表明,该方法还原跑道道面图像能力较好,有助于道面板损坏状况的智能评价技术研究及应用。

Numerical image distortion is a significant problem during image capture of airport pavement, leading to difficul- ties in image connection and damage identification. To solve this problem, pinhole imaging theory of camera is studied, by which the original point of global coordinate system is set on pavement and the original point of local coordinate system is set on numerical image. By 3D coordinate transformation formula, the key comer point co- ordinates of numerical image in local coordinate system is transferred to the coordinates of global coordinate sys- tem, and then the actual numerical image of pavement plate could be achieved and the actual numerical image of pavement in larger scale could be obtained by connecting numerical images of different pavement plates. Outdoor test is conducted in order to evaluate the theoretical reliability. In the test, white pieces of paper in A0 size are used to simulate pavement plate, and the connections of them are painted in black to simulate sealing material. Different pavement damages are set on the simulated plate, and camera is used to capture pavement images from different angles. Results show that the image reproducting ability of runway pavement image is good by this method, which could be used in the application and research of intelligent evaluation technology of pavement damage condition.