论文标题
在线非重叠摄像头校准网
On-line non-overlapping camera calibration net
论文作者
论文摘要
我们提出了一种易于使用的非重叠摄像头校准方法。首先，将连续的图像馈送到基于波西特的网络中，以获得帧之间相机的自我动态。接下来，估计相机之间的姿势。我们提出了一种在线相机间姿势估计的在线方法，而不是使用批处理方法。此外，我们在计算图上实现了整个过程。模拟和KITTI数据集的实验显示了提出的有效模拟方法的方法。
We propose an easy-to-use non-overlapping camera calibration method. First, successive images are fed to a PoseNet-based network to obtain ego-motion of cameras between frames. Next, the pose between cameras are estimated. Instead of using a batch method, we propose an on-line method of the inter-camera pose estimation. Furthermore, we implement the entire procedure on a computation graph. Experiments with simulations and the KITTI dataset show the proposed method to be effective in simulation.
