We propose a novel stereo visual odometry approach, which is especially suited for poorly textured environments.udWe introduce a novel, fast line segment detector and matcher, which detects vertical lines supportedudby an IMU. The patches around lines are then used to directly estimate the pose of consecutive camerasudby minimizing the photometric error. Our algorithm outperforms state-of-the-art approaches in challengingudenvironments. Our implementation runs in real-time and is therefore well suited for various robotics andudaugmented reality applications.
展开▼
机译：我们提出了一种新颖的立体视觉测量方法，这尤其适用于纹理较差的环境。 UDWE介绍了一种新颖的快速线段检测器和匹配器，可检测支持的垂直线 UDBY A IMU。然后，围绕线条周围的贴片来直接估计连续相机的姿势 UDB，最小化光度误差。我们的算法优于充满挑战的挑战 udenvironments的最先进的方法。我们的实现实时运行，因此适用于各种机器人和 Udaummented现实应用。
展开▼
