用无人机视频分析斑马逃跑时的群体行为，发现逃跑中个体更同步、停前短暂分散、中心更集中。
Tracking the Flight: Exploring a Computational Framework for Analyzing Escape Responses in Plains Zebra (Equus quagga)
- 用图像配准与运动结构法分离无人机晃动和斑马真实移动
- 44头斑马逃逸中发现群体极化增强、停前间距变大、中心更紧凑
- 开源易用，适合保护工作者快速分析动物集体行为
行为学研究日益受益于无人机的普及，其可高精度捕捉动物运动的时空细节。但分析此类视频需解决无人机自身运动干扰的问题。本文评估三种方法：基于生物成像的配准技术、运动结构（SfM）流程及混合插值法，应用于一段记录44头平原斑马逃逸的单个无人机视频。采用表现最佳的方法提取个体轨迹，识别出关键行为模式：逃逸过程中群体极化增强（p < 0.05），停止前瞬间间距短暂扩大，靠近群体中心时协调性更紧密。该方法有效且具备扩展至更大数据集的潜力，有助于深入探究动物群体行为。
原文摘要 · Abstract (English)
Ethological research increasingly benefits from the growing affordability and accessibility of drones, which enable the capture of high-resolution footage of animal movement at fine spatial and temporal scales. However, analyzing such footage presents the technical challenge of separating animal movement from drone motion. While non-trivial, computer vision techniques such as image registration and Structure-from-Motion (SfM) offer practical solutions. For conservationists, open-source tools that are user-friendly, require minimal setup, and deliver timely results are especially valuable for efficient data interpretation. This study evaluates three approaches: a bioimaging-based registration technique, an SfM pipeline, and a hybrid interpolation method. We apply these to a recorded escape event involving 44 plains zebras, captured in a single drone video. Using the best-performing method, we extract individual trajectories and identify key behavioral patterns: increased alignment (polarization) during escape, a brief widening of spacing just before stopping, and tighter coordination near the group's center. These insights highlight the method's effectiveness and its potential to scale to larger datasets, contributing to broader investigations of collective animal behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。