[论文解读] Brain over Brawn - Using a Stereo Camera to Detect, Track and Intercept a Faster UAV by Reconstructing Its Trajectory.

Antonella Barišić, Frano Petric+1 more|arXiv (Cornell University)|Jul 2, 2021

Advanced Vision and Imaging参考文献 29被引用 5

一句话总结

本文提出一种基于立体视觉的系统，采用ZED Mini相机与YOLOv3 Tiny，通过伯努利双曲叶线近似重建目标，实现对更快突防无人机的3D轨迹追踪，从而实现精确拦截。该方法在非结构化户外环境中实现了12次拦截中的9次成功，并在仿真中使追踪速度比拦截器快30%。

ABSTRACT

The work presented in this paper demonstrates our approach to intercepting a faster intruder UAV, inspired by the MBZIRC2020 Challenge 1. By leveraging the knowledge of the shape of the intruder's trajectory we are able to calculate the interception point. Target tracking is based on image processing by a YOLOv3 Tiny convolutional neural network, combined with depth calculation using a gimbal-mounted ZED Mini stereo camera. We use RGB and depth data from ZED Mini to extract the 3D position of the target, for which we devise a histogram-of-depth based processing to reduce noise. Obtained 3D measurements of target's position are used to calculate the position, the orientation and the size of a figure-eight shaped trajectory, which we approximate using lemniscate of Bernoulli. Once the approximation is deemed sufficiently precise, measured by Hausdorff distance between measurements and the approximation, an interception point is calculated to position the intercepting UAV right on the path of the target. The proposed method, which has been significantly improved based on the experience gathered during the MBZIRC competition, has been validated in simulation and through field experiments. The results confirmed that an efficient visual perception module which extracts information related to the motion of the target UAV as a basis for the interception, has been developed. The system is able to track and intercept the target which is 30% faster than the interceptor in majority of simulation experiments. Tests in the unstructured environment yielded 9 out of 12 successful results.

研究动机与目标

• 开发一种实时视觉感知系统，能够在动态、非结构化环境中检测并追踪速度更快的入侵无人机。
• 通过基于3D运动重建的未来轨迹预测，克服拦截器速度比目标无人机慢30%的挑战。
• 通过深度测量的直方图处理减少噪声，提升在真实环境下的鲁棒性。
• 基于拟合的双曲叶线轨迹模型计算最优拦截点，实现自主拦截。
• 在仿真与真实野外实验中验证系统，以证明其在实际约束条件下的可靠性与性能。

提出的方法

• 采用云台安装的ZED Mini立体相机，同步捕获RGB与深度数据，用于目标无人机的3D位置估计。
• 使用YOLOv3 Tiny实现实时RGB图像中的目标检测，实现快速轻量的推理，适用于机载处理。
• 应用深度测量的直方图处理方法，降低深度测量噪声，提升3D位置估计的准确性。
• 通过将3D位置数据拟合为伯努利双曲叶线，重建目标的飞行轨迹，建模为“8”字形飞行路径。
• 利用测量点与拟合双曲叶线之间的豪斯多夫距离，评估轨迹近似的质量。
• 在轨迹近似达到足够精度后，计算拦截点，使拦截器能够沿目标飞行路径预置位置。

实验结果

研究问题

• RQ1 采用轻量级深度学习推理的立体视觉系统能否在真实环境中可靠地实时追踪速度更快的无人机？
• RQ2 在真实环境下，伯努利双曲叶线对机动无人机轨迹的建模精度如何？
• RQ3 深度测量的直方图处理在多大程度上提升了轨迹重建的深度测量精度？
• RQ4 当目标无人机比拦截器快30%时，在非结构化环境中自主拦截的成功率如何？
• RQ5 与仿真结果相比，该系统在真实野外测试中的表现如何？

主要发现

• 在多数仿真实验中，系统成功追踪并拦截了比拦截器快30%的目标无人机。
• 在非结构化环境中的野外实验中，实现了12次拦截中的9次成功，证明了系统在真实环境下的鲁棒性。
• 直方图深度处理显著降低了深度测量噪声，提升了3D位置估计的可靠性。
• 伯努利双曲叶线有效近似了目标的“8”字形飞行轨迹，豪斯多夫距离被用作拦截准备状态的置信度度量。
• YOLOv3 Tiny与立体深度感知的集成实现了适用于自主无人机拦截的实时机载处理。
• 系统在从仿真到真实部署的泛化能力表现优异，验证了其在动态环境中的实际适用性。