DronePaint：基于 DNN 手势识别的集群光绘
摘要
我们提出了一种新颖的人-集群交互系统，允许用户通过基于 DNN 的手势识别的手势界面绘制轨迹，直接在复杂环境中控制无人机集群。所开发的基于计算机视觉（CV）的系统允许用户通过实时的人类手势和动作控制集群行为而无需额外设备，为改变集群的形状和编队提供了便捷的工具。我们提出并实现了两种类型的交互来调整集群层级：轨迹绘制和自由形态轨迹生成控制。实验结果显示，手势识别系统具有很高的准确率（99.75%），使得用户在三种评估的轨迹模式上能够实现相对较高的轨迹绘制精度（平均误差为 5.6 cm，相比之下鼠标绘制的平均误差为 3.1 cm）。所提出的系统可潜在应用于复杂环境探索、无人机喷漆和互动无人机表演，允许用户通过无人机集群创作自己的艺术作品。
引用
@article{arxiv.2107.11288,
title = {DronePaint: Swarm Light Painting with DNN-based Gesture Recognition},
author = {Valerii Serpiva and Ekaterina Karmanova and Aleksey Fedoseev and Stepan Perminov and Dzmitry Tsetserukou},
journal= {arXiv preprint arXiv:2107.11288},
year = {2021}
}
备注
ACM SIGGRAPH 21. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. arXiv admin note: substantial text overlap with arXiv:2106.14698