飛行中のボディランゲージ理解を目指したロバストな3Dアバター配置学習
Learning to Understand Body Language from Flight through Robust 3D Avatar Placing
UAV映像に人間の意図を表すアバターを正確に配置するデータセットを構築し、そのデータで学習することで長距離からの人間の動作・意図認識精度を大幅に向上させた。
著者: Dragos Costea, Alina Marcu, Cristina Lazar, Marius Leordeanu
分類: cs.CV
原文アブストラクト
Perceiving human motion and intent at long range is a prerequisite for socially intelligent aerial robots, yet the data to learn it barely exists. We introduce Drones2BodyLanguage, a dataset grounding human motion in real UAV footage: avatars manifesting ten communicative intents are placed into unmodified 4K drone scenes with metrically correct position, scale and orientation, maintained over hundreds of frames of camera motion. Enabling it is a lightweight geometric world model of the local scene - semantically selected anchors lifted to 3D through streaming monocular depth - in which a placement point is predicted as an affine anchor combination with provably rigid-invariant weights, and re-rendered under an SVD-fitted ground rotation. Across twelve architectures on scene- and motion-disjoint splits, training on placed data lifts mean intent accuracy by a wide margin for real, retargeted and generated motion alike, with gains confirmed on two in-the-wild scenes.