首页> 外文会议>Oceans (Conference) >Image Rectification with the Pinax Camera Model in Underwater Stereo Systems with Verged Cameras
【24h】

Image Rectification with the Pinax Camera Model in Underwater Stereo Systems with Verged Cameras

机译:用已覆盖相机的水下立体声系统中的Pinax相机模型的图像整流

获取原文

摘要

Vision methods are very commonly used in underwater robotics. However, the cameras must be enclosed in a sealed housing for which flat-pane windows are the most economical and hence most popular solution. But they cause non-trivial refraction-based distortions at the air-glass-water interface. Recently, a new model for underwater cameras calibration called Pinax was introduced, which combines aspects of an axial and a pinhole camera model to derive an as accurate as possible and at the same time computational feasible solution. Here it is shown, how the Pinax model can be applied to stereo cameras when two verged cameras are behind a single flat glass panel. Real world experiments under different water conditions show that our method outperforms standard methods using pinhole models in combination with in-water calibration.
机译:视觉方法非常常用于水下机器人。然而,相机必须封闭在密封外壳中,平板窗口是最经济的,因此最受欢迎的解决方案。但它们在空气玻璃水界面造成基于非琐碎的折射的扭曲。近来,引入了一种名为松动的水下相机校准的新模型,其结合了轴向和针孔相机模型的各个方面,以尽可能准确地获得和同时计算可行解决方案。这里显示了,当两个已预测的相机位于一个平面玻璃面板后面时,如何将PINAX模型应用于立体声相机。不同水条件下的现实世界实验表明,我们的方法优于使用针孔模型与水中校准相结合的标准方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号