华南农业大学学报2024，Vol.45Issue(2)：304-310,7.DOI:10.7671/j.issn.1001-411X.202212024
基于红外图像的笼养白羽肉鸡体温检测方法
Temperature detection method of caged white feather broilers based on infrared image
摘要
Abstract
[Objective]To address the challenge of automatic temperature detection for large-scale caged broilers,a method combining deep learning and regression analysis was proposed.[Method]An infrared thermal imager was used to capture infrared images of broiler chickens,the YOLOv5s deep learning algorithm was used to train the model for the region of interest(broiler chicken head).Multiple linear regression and multiple nonlinear regression were respectively introduced to establish prediction models between the temperature of the broiler's region of interest and the temperature under its wings,ultimately achieving the goal of automatic body temperature detection.[Result]The test results showed that the precision and recall of the region of interest model based on deep learning were 93.8%and 95.8%respectively.The average relative errors of the multiple linear regression 1 and multiple nonlinear regression temperature prediction models were 0.28%and 0.27%respectively,and the maximum differences between the predicted and actual temperature values were 0.34 and 0.32℃respectively.[Conclusion]The nonlinear model has a higher accuracy rate in predicting the body temperature of broilers,providing technical support and a preliminary research basis for automated in-house temperature inspection equipment for chicken farming.关键词
深度学习/红外热成像/温度检测/肉鸡/反演Key words
Deep learning/Infrared thermal imaging/Temperature detection/Broiler/Inversion分类
农业科技引用本文复制引用
姜来,王英超,霍晓静,王辉,王文娣,唐娟,李丽华..基于红外图像的笼养白羽肉鸡体温检测方法[J].华南农业大学学报,2024,45(2):304-310,7.基金项目
国家自然科学基金(31902209) （31902209）
河北省重点研发计划(20327220D) （20327220D）
河北省现代农业产业技术体系创新团队建设项目(HBCT2018060204) （HBCT2018060204）
