Yu Hongshan, Zhu Jiang, Wang Yaonan, Jia Wenyan, Sun Mingui, Tang Yandong
College of Electrical and Information Engineering, Hunan University, Changsha 410082, China.
Laboratory for Computational Neuroscience, University of Pittsburgh, Pittsburgh, PA 15213, USA.
Sensors (Basel). 2014 Jun 18;14(6):10753-82. doi: 10.3390/s140610753.
Inspired by the human 3D visual perception system, we present an obstacle detection and classification method based on the use of Time-of-Flight (ToF) cameras for robotic navigation in unstructured environments. The ToF camera provides 3D sensing by capturing an image along with per-pixel 3D space information. Based on this valuable feature and human knowledge of navigation, the proposed method first removes irrelevant regions which do not affect robot's movement from the scene. In the second step, regions of interest are detected and clustered as possible obstacles using both 3D information and intensity image obtained by the ToF camera. Consequently, a multiple relevance vector machine (RVM) classifier is designed to classify obstacles into four possible classes based on the terrain traversability and geometrical features of the obstacles. Finally, experimental results in various unstructured environments are presented to verify the robustness and performance of the proposed approach. We have found that, compared with the existing obstacle recognition methods, the new approach is more accurate and efficient.
受人类3D视觉感知系统的启发，我们提出了一种基于飞行时间（ToF）相机的障碍物检测与分类方法，用于非结构化环境中的机器人导航。ToF相机通过捕获图像以及每个像素的3D空间信息来提供3D传感。基于这一宝贵特性和人类的导航知识，所提出的方法首先从场景中去除不影响机器人运动的无关区域。第二步，利用ToF相机获得的3D信息和强度图像，检测感兴趣区域并将其聚类为可能的障碍物。因此，设计了一种多相关向量机（RVM）分类器，根据障碍物的地形可穿越性和几何特征将障碍物分为四种可能的类别。最后，给出了在各种非结构化环境中的实验结果，以验证所提方法的鲁棒性和性能。我们发现，与现有的障碍物识别方法相比，新方法更加准确和高效。
