基于多视角姿态估计的视觉周界防御
Vision-based Perimeter Defense via Multiview Pose Estimation
摘要：
以前的研究在周边防御游戏主要集中在完全可观察的设置，真正的球员状态是已知的所有球员。然而，这对于实际实现是不现实的，因为防御者可能必须感知入侵者并估计其状态。在这项工作中，我们研究了周边防御游戏中的照片般逼真的模拟器和现实世界中，要求防御者估计入侵者的状态从视觉。我们训练一个基于深度机器学习的系统，用于具有域随机化的入侵者姿态检测，该系统聚合多个视图以减少状态估计错误，并调整防御策略以解决此问题。我们新引入的性能指标来评估基于视觉的周边防御。通过大量的实验，我们表明，我们的方法提高了状态估计，并最终，周边防御性能在两个1防御者vs 1入侵者的游戏，和2防御者vs 1入侵者的游戏。
英文摘要：
Previous studies in the perimeter defense game have largely focused on the fully observable setting where the true player states are known to all players. However, this is unrealistic for practical implementation since defenders may have to perceive the intruders and estimate their states. In this work, we study the perimeter defense game in a photo-realistic simulator and the real world, requiring defenders to estimate intruder states from vision. We train a deep machine learning-based system for intruder pose detection with domain randomization that aggregates multiple views to reduce state estimation errors and adapt the defensive strategy to account for this. We newly introduce performance metrics to evaluate the vision-based perimeter defense. Through extensive experiments, we show that our approach improves state estimation, and eventually, perimeter defense performance in both 1-defender-vs-1-intruder games, and 2-defenders-vs-1-intruder games.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
