We present a real time method for pose estimation of objects from an UAV, using visual marks placed on non planar surfaces. It is designed to overcome constraints in small aerial robots, such as slow CPUs, low resolution cameras and image deformations due to distortions introduced by the lens or by the viewpoint changes produced during the flight navigation. The method consists of shape registration from extracted contours in an image. Instead of working with dense image patches or corresponding image features, we optimize a geometric alignment cost computed directly from the raw polygonal representations of the observed regions using efficient clipping algorithms. Moreover, instead of doing 2D image processing operations, the optimization is performed in the polygon representation space, allowing real-time projective matching. Deformation modes are easily included in the optimization scheme, allowing an accurate registration of different markers attached to curved surfaces using a single deformable prototype.\udAs a result, the method achieves accurate object pose estimation precision in real-time, which is very important for interactive UAV tasks, for example for short distance surveillance or bar assembly. We describe the main algorithmic components of the method and present experiments where our method yields an average error of less than 5mm in position at a distance of 0.7m, using a visual mark of 19mm x 19mm. Finally, we compare these results with current computer vision state-of-the-art systems.
展开▼
机译：我们提出了一种实时方法，可使用放置在非平面表面上的视觉标记从无人机进行物体姿态估计。它旨在克服小型空中机器人的约束，例如慢速CPU，低分辨率相机以及由于镜头或飞行导航过程中产生的视点变化而导致的图像变形。该方法包括从图像中提取的轮廓进行形状配准。代替使用密集的图像补丁或相应的图像特征，我们使用有效的裁剪算法来优化直接从观察区域的原始多边形表示计算的几何对齐成本。此外，代替进行2D图像处理操作，还可以在多边形表示空间中执行优化，从而实现实时投影匹配。变形模式很容易包含在优化方案中，从而允许使用单个可变形原型精确定位附着在曲面上的不同标记。\ ud，因此，该方法可实时实现精确的物体姿态估计精度，这对于确保精度非常重要交互式无人机任务，例如用于短距离监视或杆组装。我们描述了该方法的主要算法组成部分，并介绍了实验，其中我们的方法使用19mm x 19mm的可视标记在0.7m的距离上产生的位置平均误差小于5mm。最后，我们将这些结果与当前计算机视觉的最新系统进行比较。
展开▼
