摘要
为了实现生猪耳根体表温度自动检测,减少快速判别尺寸空间跟踪(Fast discriminative scale space tracking,FDSST)方法在热红外视频中进行头部跟踪产生的误差,提出了一种利用骨架扫描策略改进FDSST的生猪耳根体表温度检测方法。首先对视频的初始帧进行预处理,提取精简后的生猪整体骨架;其次,设计骨架扫描策略,扫描头部骨架前端关键点,实现头部在初始帧的定位;再次,采用FDSST跟踪生猪头部,每连续跟踪N帧后,采用骨架扫描策略重新定位头部,减少跟踪框漂移;最后提出耳根体表温度提取方法,根据头部左右耳侧温度分布,提取耳根温度并误差校正。利用采集到的30只生猪的视频数据,在Matlab平台上进行了测试,并与FDSST算法、压缩感知跟踪和核相关滤波跟踪等高效算法对比分析。结果表明,本文方法的跟踪平均精确度分别提高了7.82、11.82、8.78个百分点,提取的耳根最大温度误差为0.32℃。
To realize the automatic detection of pig ear-based surface temperature and reduce the error caused by fast discriminative scale space tracking(FDSST)in the head tracking in the thermal infrared video,an improved detection method of pig ear-based surface temperature by using the skeleton scanning strategy was proposed.Firstly,the initial frame of the video was preprocessed to extract the simplified pig skeleton.Secondly,the skeleton scanning strategy was designed to scan the key points of the head skeleton and realize the head positioning in the initial frame.Thirdly,FDSST was used to track the hog head.After each continuous tracking of N frames,skeleton scanning strategy was adopted to reposition the head and reduce the tracking frame drift.Finally,a method for extracting the surface temperature of the ear base was proposed.According to the temperature distribution of the left and right ear sides of the head,the temperature of the ear base was extracted and the error was corrected.The method was tested on the Matlab platform by using the collected videos of 30 pigs.Compared with FDSST,compressed sensing tracking and nuclear correlation filtering tracking,the average tracking accuracy of the proposed method was improved by 7.82 percentage points,11.82 percentage points and 8.78 percentage points,respectively.The maximum error of the extracted ear base surface temperature was 0.32℃.This study can provide technical support for automatic detection of pig ear base surface temperature.
作者
马丽
张旭东
邢子正
冯彦坤
刘刚
刘元杰
MA Li;ZHANG Xudong;XING Zizheng;FENG Yankun;LIU Gang;LIU Yuanjie(College of Information Science and Technology, Hebei Agricultural University, Baoding 071001, China2.Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs, China Agricultural University, Beijing 100083, China)
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2020年第S01期371-377,共7页
Transactions of the Chinese Society for Agricultural Machinery
基金
国家重点研发计划项目(2016YFD0700204)
河北农业大学精准畜牧学科群建设项目(1090064)。
关键词
猪耳根
体表温度
快速判别尺寸空间跟踪
热红外视频
pig ear base
surface temperature
fast discriminative scale space tracking
thermal infrared video
