Livestock Fever Detection | 畜禽体温异常检测

Combines livestock behavior in continuous barn videos with environmental sensor data (temperature, humidity, ammonia, etc.) to identify group stress responses caused by abnormal in-barn conditions. | 结合畜禽行为与环境传感器，识别温湿度异常时的群体应激反应。

Detects morbid behavioral cues in poultry and pigs from continuous barn videos — such as difficulty standing, ruffled feathers/piloerection, isolation, drowsiness and appetite loss — and outputs behavior type with risk level up to 2-3 days ahead of visible clinical signs. | 识别站立困难、羽毛蓬松、离群、嗜睡等病态行为，比人工观察提前2-3天。

Automatically detects and counts livestock or poultry individuals from barn or passage camera images/videos, outputting total headcount with confidence for fast inventory. | 自动识别并统计畜禽数量，实现快速存栏盘点。

Analyzes fixed-camera videos of feeders and waterers to quantify livestock feeding duration, feeding bouts and drinking frequency, comparing them against individual baselines to raise behavior anomaly alerts. | 通过视频统计畜禽采食时长、饮水频次，异常时预警。

Using a fixed thermal-imaging camera installed in public areas (e.g., living room, dining room), the system automatically analyzes each person's skin-surface temperature (usually forehead or facial region) when multiple people gather, and computes the difference between an individual's temperature and the average temperature of others in the scene. | 通过安装于公共区域（如客厅、餐厅）的固定热成像摄像头，在多人聚集时自动分析每个人的体表温度（通常为额头或面部区域），计算个体温度与场景内其他人平均温度的差值。当某个人温度显著高于周边人群（差值超过预设阈值，如1.5℃）时，输出'体温相对异常'提醒，建议使用额温枪复测。

Detects aggressive interactions in livestock and poultry from continuous barn videos — including fighting, biting, chasing and butting — and outputs behavior type, intensity level and alert level. | 识别打斗、撕咬等攻击行为，及时预警。