用AI自动识别蜥蜴晒太阳和捕食行为，提升饲养研究效率。
Bearded Dragon Activity Recognition Pipeline: An AI-Based Approach to Behavioural Monitoring
- 基于YOLO模型检测蜥蜴、灯泡和蟋蟀，实时分析视频流
- 蜥蜴晒太阳识别准确率85.5%，捕食行为因蟋蟀检测弱仅39.2%
- 适合动物行为学研究者，尤其关注自动化监测的团队
传统蜥蜴行为监测耗时且易出错。本项目提出一种基于AI的实时视频分析系统，采用You Only Look Once（YOLO）目标检测模型识别两种关键行为：晒太阳与捕食。在包含1200张图像的自建公开数据集上训练了五种YOLO变体（v5、v7、v8、v11、v12），涵盖蜥蜴（600张）、加热灯（500张）和蟋蟀（100张）。最终选用YOLOv8s模型，其在[email protected]:0.95指标上达到0.855的准确率，兼具高精度与快速推理能力。系统通过提取每帧物体坐标，结合时间插值保证连续性，并使用规则逻辑判定行为。晒太阳检测表现可靠，但捕食检测准确性较低，主因是蟋蟀检测性能差（[email protected] = 0.392）。未来将通过扩大数据集或引入小目标专用检测器优化蟋蟀识别。该系统为受控环境中的爬行动物行为监控提供可扩展解决方案，显著提升科研效率与数据质量。
原文摘要 · Abstract (English)
Traditional monitoring of bearded dragon (Pogona Viticeps) behaviour is time-consuming and prone to errors. This project introduces an automated system for real-time video analysis, using You Only Look Once (YOLO) object detection models to identify two key behaviours: basking and hunting. We trained five YOLO variants (v5, v7, v8, v11, v12) on a custom, publicly available dataset of 1200 images, encompassing bearded dragons (600), heating lamps (500), and crickets (100). YOLOv8s was selected as the optimal model due to its superior balance of accuracy ([email protected]:0.95 = 0.855) and speed. The system processes video footage by extracting per-frame object coordinates, applying temporal interpolation for continuity, and using rule-based logic to classify specific behaviours. Basking detection proved reliable. However, hunting detection was less accurate, primarily due to weak cricket detection ([email protected] = 0.392). Future improvements will focus on enhancing cricket detection through expanded datasets or specialised small-object detectors. This automated system offers a scalable solution for monitoring reptile behaviour in controlled environments, significantly improving research efficiency and data quality.
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。