In this paper, we present a localization system for the use of drone in a remote laboratory. The objective is to allow a drone to inspect remote electronic instruments autonomously, as well as to return to its base and land on a platform for the recharge of its batteries. In addition, the drone should be able to detect the presence of a teacher in the laboratory and to center the human face in the image in order to enable remote student–teacher communication. To achieve the first objective, the localization approach is composed of a monocular simultaneous localization and mapping algorithm, parallel tracking and mapping and an estimation based on the homography transform. For the face-drone servoing, the approach is based on the 3D Candide model. Both approaches work in real time. Quantitative and qualitative experiments are presented that show the robustness of both methods.

在本文中，我们提出了一种在远程实验室中使用无人机的本地化系统。目的是让无人机自主检查远程电子仪器，并返回其基地并降落在平台上以为其电池充电。此外，无人驾驶飞机应该能够检测到实验室中有老师在场，并将人脸置于图像的中央，以便实现远程师生交流。为了实现第一个目标，定位方法由单眼同时定位和映射算法，并行跟踪和映射以及基于单应性变换的估计组成。对于端面无人机伺服，该方法基于3D Candide模型。两种方法都是实时工作的。