计算机视觉技术在智慧羊场中的研究进展     

姚州  谭焓  田芳  周勇  章程 《中国饲料》2021,1(7):7-12

智慧羊场具有科学化、标准化管理的优点,是羊场转型发展的趋势。计算机视觉技术是人工智能的核心,可以实现非接触性、自动化、实时监测羊的个体信息。本文总结并分析了计算机视觉在羊场的个体识别方法、行为识别方法、体尺与体重估测、疾病监测的研究现状,并指出计算机视觉在智慧羊场的进一步发展趋势。 [关键词] 计算机视觉|智慧羊场|个体识别|行为识别|体尺与体重估测|疾病监测  相似文献   

Genetic analysis for sow stayability at different parities in purebred Landrace and Large White pigs     

Shinichiro Ogawa  Makoto Kimata  Kazuo Ishii  Yoshinobu Uemoto  Masahiro Satoh 《Animal Science Journal》2021,92(1):e13599

Genetic parameters for sow stayability were estimated from farrowing records of 10,295 Landrace sows and 8192 Large White sows. The record for sow stayability from parity k to parity k + 1 (k = 1, …, 6) was 0 when a sow had a farrowing record at parity k but not at parity k + 1, and 1 when a sow had both records. Heritability was estimated by using single-trait linear and threshold animal models. Genetic correlations among parities were estimated by using two-trait linear–linear and single-trait random regression linear animal models. Genetic correlations with litter traits at birth were estimated by using a two-trait linear–linear animal model. Heritability estimates by linear model analysis were low (0.065–0.119 in Landrace & 0.061–0.157 in Large White); those by threshold model analysis were higher (0.136–0.200 & 0.110–0.283). Genetic correlations among parities differed between breeds and models. Genetic correlation between sow stayability and number born alive was positive in many cases, implying that selection for number born alive does not reduce sow stayability. The results seem to be affected by decisions on culling made by farmers.  相似文献   

Potential effects of RNA interference of Asian longhorned beetle on its parasitoid     

Xingeng Wang  Jessica Faucher  Ramesh Kumar Dhandapani  Jian J. Duan  Subba Reddy Palli 《Pest management science》2023,79(4):1557-1565

  相似文献   

Sentinel lymph node mapping in canine mast cell tumours using a preoperative radiographic indirect lymphography: Technique description and results in 138 cases     

Maurizio Annoni  Simone Borgonovo  Marina Aralla 《Veterinary and comparative oncology》2023,21(3):469-481

Several sentinel lymph node (SLN) mapping techniques, to detect nodal metastasis in canine tumours have been investigated in the last 10 years in veterinary oncology. The purpose of this prospective study was to describe a reliable, quick, and inexpensive technique for SLN mapping in canine patients affected by cutaneous and subcutaneous mast cell tumours (MCT). Eighty dogs were enrolled in this study for a total of 138 cytologically diagnosed MCTs. Sentinel lymph node mapping was performed by injecting iomeprole peritumorally followed by serial radiographs at 1, 3, 6 and 9-min post injection. A total of 168 SLNs were detected, 90% at first radiograph, 1 min after the peritumoral iomeprole injection, while in the rest of the cases SLN was identified at 3 min. Sentinel lymph nodes detected by the preoperative radiographic indirect lymphography with iomeprole (PRILI) differed from regional lymph nodes in 57% of cases. The PRILI technique detected simultaneously multiple SLNs in the 26% of cases and multiple lymph centers in the 31% of MCTs. To allow the surgical identification of the SLNs, a peritumoral injection of methylene blue was performed at the time of surgery. This study reports a widely available technique for SLN mapping using digital radiographs in combination with a water-soluble medium, representing a cost-effective alternative to other SLN mapping procedures. Based on our results, this technique can be effective for SLNs mapping in dogs with MCTs but further comparative studies are needed to assess its reliability and efficacy in different tumours.  相似文献   

AN ACCELERATION SEARCH METHOD FOR UNCONSTRAINED OPTIMIZATION AND ITS APPLICATION IN MODEL PARAMETER ESTIMATION     

Sun Dihua Yang Yongzhen 《保鲜与加工》1991,(6):62-68

In order to improve the convergence rate of the algorithms, an acceleration search method along a straight or curve is proposed,and the specific calculation steps of the algorithms are presented. The numerical results in model parameter estimation show that the convergence rate is improved and the calculation accords with the practical demands.  相似文献   

Comparison between Calibration Procedure and Econometric Estimation   总被引：1，自引：0，他引：1  

ZHOU Zhuo-hu  ZHANG Zong-yi 《保鲜与加工》2001,(2):103-106

The two methods of estimating parameter in computable general equilibrium(CGE) model are introduced and compared:the calibration procedure and econometric estimation. The conclusions are:the estimation of parameter in CGE model must use the calibration procedure coupled with the econometric estimation method;the elasticity of output with respect to labor input,the marginal expenditure share for households and price elasticity of export demand are estimated by econometric estimation method;and other parameters of the CGE model can be get by calibration procedure.  相似文献   

Approximate Estimate of Lateral Deflection for Rigid Frame and Frame-Shear Wall Structure Systems     

《保鲜与加工》1997,(6):86-92

This paper expounds the engineering significance of deliberating a method of approximate calculation,and has a discussion on lateral deflection of frame and frame_shear wall structures.  相似文献   

Summarization of Current Research on Application of Durability of Structures     

LI Hong yi  CHEN Zhao hui  BAI Shao liang  XIANG Chang kui 《保鲜与加工》2001,(2):98-103

This paper summarized the recent research results about the durability of structures, introduced their current application in durability design, appraisal, estimation of rest life and strategy of maintenance and strengthening as well as in other fields.  相似文献   

基于无人机影像自动检测冠层果的油茶快速估产方法   总被引：2，自引：2，他引：0  

严恩萍  棘玉  尹显明  莫登奎 《农业工程学报》2021,37(16):39-46

快速准确的产量估算对油茶经营管理和可持续发展具有重要意义。该研究针对油茶快速估产的应用现状,提出一种基于无人机影像自动检测冠层果的方法用于油茶快速估产。首先借助无人机航拍影像,通过随机抽样选取120株油茶树进行无人机近景摄影和人工采摘称量;然后利用Mask RCNN(Mask Region Convolutional Neural Networks)网络开展基于近景影像的油茶冠层果自动检测与计数;采用线性回归和K最邻近建立冠层果数与单株果数之间的关系,同时结合研究区典型样木株数和平均单果质量,构建基于冠层果自动检测的估产模型。结果表明:1)无人机超低空近景影像结合Mask RCNN网络能够有效检测不同光照条件油茶果,平均F1值达89.91%;2)同传统卫星遥感相比,基于无人机近景摄影的冠层果自动检测在作物产量估测方面显示出明显优势,Mask RCNN网络预测的冠层果数与油茶样木单株果数之间具有良好的一致性,拟合决定系数R2达0.871;3)结合线性回归和K最邻近构建的模型估产精度均较高,拟合决定系数R~2和标准均方根误差NRMSE(Normalized Root Mean Square Error)分别在0.892～0.913和28.01%～31.00%之间,表明基于无人机影像自动检测冠层果的油茶快速估产是一种切实可行的方法。研究结果可为油茶快速估产和智能监测提供参考。  相似文献   

基于自监督学习的温室移动机器人位姿跟踪     

周云成  许童羽  邓寒冰  苗腾  吴琼 《农业工程学报》2021,37(9):263-274

为实现温室环境下机器人行进过程中的位置及姿态跟踪,该研究提出一种基于时序一致性约束的自监督位姿变换估计模型。模型用软遮罩,处理视频帧间静止造成的位姿预测值收缩现象,进一步用归一化遮罩,解决非刚体场景和目标遮挡问题。设计了一种星型扩张卷积,并基于该卷积,为模型构建自编码器。在采集自种植作物为番茄的日光温室视频数据上开展训练和测试试验。结果表明,与不采用遮罩处理的模型相比,采用软遮罩的模型,位置和姿态估计相对误差分别减少5.06个百分点和11.05个百分点,采用归一化遮罩的模型,这2项误差则分别减少4.15个百分点和3.86个百分点,2种遮罩均可显著提高模型精度;星型扩张卷积对降低模型误差是有效的,在网络参数不变的前提下,该卷积使姿态估计相对误差减少7.54个百分点;时序一致性约束使姿态估计均方根误差下降36.48%,每百帧累积姿态角误差降低54.75%,该约束可用于提高模型精度及稳定性;该研究的位置及姿态估计相对误差分别为8.29%和5.71%,与Monodepth2相比,减少了8.61%和6.83%。该研究可为温室移动机器人导航系统设计提供参考。  相似文献