畜禽养殖疾病诊断智能传感技术研究进展
李奇峰,李嘉位,马为红,高荣华,余礼根,丁露雨,于沁杨

Research Progress of Intelligent Sensing Technology for Diagnosis of Livestock and Poultry Diseases
LI QiFeng,LI JiaWei,MA WeiHong,GAO RongHua,YU LiGen,DING LuYu,YU QinYang
表5 疾病自动诊疗依据特征表
Table 5 Characteristics for automatic diagnosis and treatment of diseases
动物特征
Features
主要方法
Method
成熟程度
Maturity
存在问题
Problems
改进措施
Improvement measures
外型与形态
Shape and pattern
机器视觉(可见光、深度、红外)
Machine vision(visible light\depth\infrared)
较高
High
视野容易受限
Easy to view limited
优化图像传感器部署方式,研究相关校正算法
Optimize correlation correction algorithm
行为与动作
Behavior and action
机器视觉、加速度传感器
Machine vision, Acceleration sensor

High
个体跟踪困难
Individual tracking difficult
引入深层卷积网络模型,扩大训练数据集
Use deep convolutional network and expand the training data set
鸣叫与声音
Chirps and sounds
音频处理
Audio processing
较高
High
噪音滤除 问题
Noise problem
优化拾音器部署方案,综合分析多种声音特征
Analyze multiple sound features comprehensively
体温与健康
Body temperature
and health
红外热成像,植入/捆绑传感器
Infrared thermal imaging, Implant sensor
一般
Common
易造成环境与动物应激
Environmental animal stress
研究嵌入式设备,可见光与红外融合目标定位
Embedded equipment, visible light and infrared fusion target location
心率与血压
Heart rate and blood pressure
红外热成像,植入/捆绑传感器
Infrared thermal imaging, Implant sensor
较低
Low
精度与稳定性不高
Low accuracy and stability
优化算法提升植入设备精度与设备续航能力
Optimization algorithm precision and endurance of the implanted device
排泄物
Waste
电子鼻、机器视觉
Electronic nose, machine vision

Low
识别精低
Low identification accuracy
问题具体化,多源数据融合分析
Multi-source data fusion analysis