Precision Livestock Farming: The Opportunities inPoultry Sector

Precision management of animals using technology is one innovation in agriculture that has the potential to revolutionizewhole livestock industries including the poultry sector. Limited research in precision livestock farming (PLF) in the poultry productionhas been so far conducted and most of them are conducted within the past 5-10 years. The PLF collects real-time data from individual orgroup of animals or birds using sensor technology, and involves the multidisciplinary team approach to give it a reality. Poultry scientistsplay a central role in executing poultry PLF with collaboration from agri-engineers and computer scientists for the type of measurementsto be made on biological or environmental variables. A real-time collection of environmental, behavioral and health data from birdgrow-out facilities can be a strong tool for developing daily action plans for poultry management. Unlike other livestock farming, theattributes of poultry rearing such as a closed housing system and vertically integrated industry provides a greater opportunity for poultrysector to adopt technology-based farming for enhanced production output.

Experimental Evaluation of the Performance of Local Shape Descriptors for the Classification of 3D Data in Precision Farming

Object classification in high-density 3D point clouds with applications in precision farming is a very challenging area due to high intra-class variances and high degrees of occlusions and overlaps due to self-similarities and densely packed plant organs, especially in ripe growing stages. Due to these application specific challenges, this contribution gives an experimental evaluation of the performance of local shape descriptors (namely Point-Feature Histogram (PFH), Fast-Point-Feature Histogram (FPFH), Signature of Histograms of Orientations (SHOT), Rotational Projection Statistics (RoPS) and Spin Images) in the classification of 3D points into different types of plant organs. We achieve very good results on four representative scans of a leave, a grape bunch, a grape branch and a flower of between 94 and 99% accuracy in the case of supervised classification with an SVM and between 88 and 96% accuracy using a k-means clustering approach. Additionally, different distance measures and the influence of the number of cluster centres are examined.

Germination Quality Prognosis: Classifying Spectroscopic Images of the Seed Samples

One of the most critical objectives of precision farming is to assess the germination quality of seeds.Modern models contribute to thisfield primarily through the use of artificial intelligence techniques such as machine learning,which present difficulties in feature extraction and optimization,which are critical factors in predicting accuracy with few false alarms,and another significant dif-ficulty is assessing germination quality.Additionally,the majority of these contri-butions make use of benchmark classification methods that are either inept or too complex to train with the supplied features.This manuscript addressed these issues by introducing a novel ensemble classification strategy dubbed“Assessing Germination Quality of Seed Samples(AGQSS)by Adaptive Boosting Ensemble Classification”that learns from quantitative phase features as well as universal features in greyscale spectroscopic images.The experimental inquiry illustrates the significance of the proposed model,which outperformed the currently avail-able models when performance analysis was performed.

Spatial Variability of Soil Chemical Properties in the Reclaiming Marine Foreland to Yellow Sea of China

Precise information about the spatial variability of soil properties is essential in developing site-specific soil management, such as variable rate application of fertilizers. In this study the sampling grid of 100 m × 100 m was established to collect 1 703 soil samples at the depth of 0-20 cm, and examine spatial patterns including 13 soil chemical properties （pH, OM, NH4^＋, P, K, Ca, Mg, S, B, Cu, Fe, Mn, and Zn） in a 1 760 ha rice field in Haifeng farm, China, from 6th to 22nd of April, 2006, before fertilizer application and planting. Soil analysis was performed by ASI （Agro Services International） and data were analyzed both statistically and geostatistically. Results showed that the contents of soil OM, NH4^＋, and Zn in Haifeng farm were very low for rice production and those of others were enough to meet the need for rice cultivation. The spatial distribution model and spatial dependence level for 13 soil chemical properties varied in the field. Soil Mg and B showed strong spatial variability on both descriptive statistics and geostatistics, and other properties showed moderate spatial variability. The maximum ranges for K, Ca, Mg, S, Cu and Mn were all - 3 990.6 m and the minimum ranges for soil pH, OM, NH4^＋, P, Fe, and Zn ranged from 516.7 to 1 166.2 m. Clear patchy distribution of N, P, K, Mg, S, B, Mn, and Zn were found from their spatial distribution maps. This proved that sampling strategy for estimating variability should be adapted to the different soil chemical properties and field management. Therefore, the spatial variability of soil chemical properties with strong spatial dependence could be readily managed and a site-specific fertilization scheme for precision farming could be easily developed.

Precision Livestock Farming: Precision feeding technologies and sustainable livestock production

In order to be able to produce safe,uniform,cheap,environmentally-and welfare-friendly food products and market these products in an increasingly complex international agricultural market,livestock producers must have access to timely production related information.Especially the information related to feeding/nutritional issues is important,as feeding related costs are always significant part of variables costs for all types of livestock production.Therefore,automating the collection,analysis and use of production related information on livestock farms will be essential for improving livestock productivity in the future.Electronically-controlled livestock production systems with an information and communication technology(ICT)focus are required to ensure that information is collected in a cost effective and timely manner and readily acted upon on farms.New electronic and ICT related technologies introduced on farms as part of Precision Livestock Farming(PLF)systems will facilitate livestock management methods that are more responsive to market signals.The PLF technologies encompass methods for electronically measuring the critical components of the production system that indicate the efficiency of resource use,interpreting the information captured and controlling processes to ensure optimum efficiency of both resource use and livestock productivity.These envisaged real-time monitoring and control systems could dramatically improve production efficiency of livestock enterprises.However,further research and development is required,as some of the components of PLF systems are in different stages of development.In addition,an overall strategy for the adoption and commercial exploitation of PLF systems needs to be developed in collaboration with private companies.This article outlines the potential role PLF can play in ensuring that the best possible management processes are implemented on farms to improve farm profitability,quality of products,welfare of livestock and sustainability of the farm environment,especially as it related to intensive livestock species.

Geostatistical Assessment of the Spatial Distribution of Some Chemical Properties in Calcareous Soils

Spatial patterns of soil fertility parameters and other extrinsic factors need to be identified to develop farming practices that match agricultural inputs with local crop needs. Little is known about the spatial structure of nutrition in Iran. The present study was conducted in a 132-ha field located in central Iran. Soil samples were collected at 0-30 cm depth and were then analyzed for total nitrogen （N）, available phosphorus （P）, available potassium （K）, available copper （Cu）, available zinc （Zn）, available iron （Fe） and available manganese （Mn）. The results showed that the contents of soil organic matter, Cu and Zn in Marvdasht＇s farms were low. The spatial distribution model and spatial dependence level for soil chemical properties varied in the field. N, K, carbonate calcium equivalent （CaCO3） and electrical conductivity （EC） data indicated the existence of moderate spatial dependence. The variograms for other variables revealed stronger spatial structure. The results showed a longer range value for available P （480 m）, followed by total N （429 m）. The value of other chemical properties values showed a shorter range （128 to 174 m）. Clear patchy distribution of N, P, K, Fe, Mn, Cu and Zn were found from their spatial distribution maps. This proved that sampling strategy for estimating variability should be adapted to the different soil chemical properties and field management. Therefore, the spatial variability of soil chemical properties with strong spatial dependence could be readily managed and a site-specific fertilization scheme for precision farming could be easily developed.

ICT-based agricultural advisory services and nitrogen management practices:A case study of wheat production in China

Excessive use of nitrogen fertilizer in China and its adverse effects on agricultural production have been a national and global concern.In addition to massive public initiatives to promote sustainable farm practices,grass-rooted innovations are emerging in the niche,many of which take the forms of information and communication technologies(ICT)and digital services.This study examines the effects of ICT-based extension services provided by an entrepreneurial startup on adopting sustainable farming practices.We found no significant reduction in N-fertilizer use for wheat production.But the ICT-based services promoted farmers to adapt N-fertilizer use towards site-specific management.The business model of the entrepreneurial venture faces great challenges in becoming participatory and financially sustainable.

Plan of Using Modern Agriculture High-New Information Technology for Building Stable Nation Commercial Grain and Green Agriculture Base of China

The North-East China is nation commercial grain base of China.It provides important grain supply for other areas of the country every year.The nation and modern farmers are looking for advanced technological solutions to increase production and preserve environment.Considering of this aim,this paper introduce a new planning that using 3S technology to develop precision farming,explaining its technology frame,operation steps and advantages.On the other hand,this paper also introduce the concept of precision farming and discusses the role of 3S technology as a data collection,management and analysis tool.

Mitigating nitrous oxide emissions from agricultural soils by precision management

Nitrous oxide(N2O)emissions make up a significant part of agricultural greenhouse gas emissions.There is an urgent need to identify new approaches to the mitigation of these emissions with emerging technology.In this short review four approaches to precision managements of agricultural systems are described based on examples of work being undertaken in the UK and New Zealand.They offer the opportunity for N2 O mitigation without any reduction in productivity.These approaches depend upon new sensor technology,modeling and spatial information with which to make management decisions and interventions that can both improve agricultural productivity and environmental protection.

A novel low-cost visual ear tag based identification system for precision beef cattle livestock farming

The precision livestock farming(PLF)has the objective to maximize each animal's performance while reducing the environmental impact and maintaining the quality and safety of meat production.Among the PLF techniques,the personalised management of each individual animal based on sensors systems,represents a viable option.It is worth noting that the implementation of an effective PLF approach can be still expensive,especially for small and medium-sized farms;for this reason,to guarantee the sustainability of a customized livestock management system and encourage its use,plug and play and cost-effective systems are needed.Within this context,we present a novel low-cost method for identifying beef cattle and recognizing their basic activities by a single surveillance camera.By leveraging the current state-of-the-art methods for real-time object detection,(i.e.,YOLOv3)cattle's face areas,we propose a novel mechanism able to detect the ear tag as well as the water ingestion state when the cattle is close to the drinker.The cow IDs are read by an Optical Character Recognition(OCR)algorithm for which,an ad hoc error correction algorithm is here presented to avoid numbers misreading and correctly match the IDs to only actually present IDs.Thanks to the detection of the tag position,the OCR algorithm can be applied only to a specific region of interest reducing the computational cost and the time needed.Activity times for the areas are outputted as cattle activity recognition results.Evaluation results demonstrate the effectiveness of our proposed method,showing a mAP@0.50 of 89%.

A novel artificial bee colony-optimized visible oblique dipyramid greenness index for visionbased aquaponic lettuce biophysical signatures estimation

In response to the challenges in providing real-time extraction of crop biophysical signatures,computer vision in computational crop phenotyping highlights the opportunities of computational intelligence solutions.Shadow and angular brightness due to the presence of photosynthetic light unevenly illuminate crop canopy.In this study,a novel vegetation index named artificial bee colony-optimized visible band oblique dipyramid greenness index(vODGIabc)was proposed to enhance vegetation pixels by correcting the saturation and brightness levels,and the ratio of visible RGB reflectance intensities.Consumer-grade smartphone was used to acquire indoor and outdoor aquaponic lettuce images daily for full 6-week crop life cycle.The introduced saturation rectification coeffi-cient(X),value rectification coefficient(m),green–red wavelength adjustment factor(a),and green–blue wavelength adjustment factor(b)on the original triangular greenness index resulted in 3D canopy reflectance spectrum with two oblique tetrahedrons formed by connecting the vertices of visible RGB band reflectance and maximum wavelength point map to corresponding saturation and value of lettuce-captured images.Hybrid neighborhood component analysis(NCA),minimum redundancy maximum relevance(MRMR),Pearson’s correlation coefficient(PCC),and analysis of variance(ANOVA)weighted most of the canopy area,energy,and homogeneity.Strong linear relationships were exhibited by using vODGIabc in estimating lettuce crop fresh weight,height,number of spanning leaves,leaf area index,and growth stage with R2 values of 0.9368 for InceptionV3,0.9574 for ResNet101,0.9612 for ResNet101,0.9999 for Gaussian processing regression,and accuracy of 88.89%for ResNet101,respectively.This low-cost approach on developing greenness index for biophysical signatures estimation proved to be more accurate than the previously established triangular greenness index(TGI)using RGB smartphone camera.

Vision-based measuring method for individual cow feed intake using depth images and a Siamese network

Feed intake is an important indicator to reflect the production performance and disease risk of dairy cows,which can also evaluate the utilization rate of pasture feed.To achieve an automatic and non-contact measurement of feed intake,this paper proposes a method for measuring the feed intake of cows based on computer vision technology with a Siamese network and depth images.An automated data acquisition system was first designed to collect depth images of feed piles and constructed a dataset with 24150 samples.A deep learning model based on the Siamese network was then constructed to implement non-contact measurement of feed intake for dairy cows by training with collected data.The experimental results show that the mean absolute error(MAE)and the root mean square error(RMSE)of this method are 0.100 kg and 0.128 kg in the range of 0-8.2 kg respectively,which outperformed existing works.This work provides a new idea and technology for the intelligent measuring of dairy cow feed intake.

DEVELOPMENT OF AN AUTOMATIC WEIGHING PLATFORM FOR MONITORING BODYWEIGHT OF BROILER CHICKENS IN COMMERCIAL PRODUCTION

Bodyweight is a key indicator of broiler production as it measures the production efficiency and indicates the health of a flock.Currently,broiler weight(i.e.,bodyweight)is primarily weighed manually,which is timeconsuming and labor-intensive,and tends to create stress in birds.This study aimed to develop an automatic and stress-free weighing platform for monitoring the weight of floor-reared broiler chickens in commercial production.The developed system consists of a weighing platform,a real-time communication terminal,computer software and a smart phone applet userinterface.The system collected weight data of chickens on the weighing platform at intervals of 6 s,followed by filtering of outliers and repeating readings.The performance and stability of this system was systematically evaluated under commercial production conditions.With the adoption of data preprocessing protocol,the average error of the new automatic weighing system was only 10.3 g,with an average accuracy 99.5%with the standard deviation of 2.3%.Further regression analysis showed a strong agreement between estimated weight and the standard weight obtained by the established live-bird sales system.The variance(an indicator of flock uniformity)of broiler weight estimated using automatic weighing platforms was in accordance with the standard weight.The weighing system demonstrated superior stability for different growth stages,rearing seasons,growth rate types(medium-and slow-growing chickens)and sexes.The system is applicable for daily weight monitoring in floor-reared broiler houses to improve feeding management,growth monitoring and finishing day prediction.Its application in commercial farms would improve the sustainability of poultry industry.

A deep learning method for monitoring spatial distributionof cage-free hens

The spatial distribution of laying hens in cage-free houses is an indicator of flock's health and welfare.While larger space allows chickens to perform more natural behaviors such as dustbathing,foraging,and perching in cage-free houses,an inherent challenge is evaluating chickens'locomotion and spatial distribution(e.g.,realtime birds'number on perches or in nesting boxes).Manual inspection of hen's spatial distribution requires closer observation,which is labor intensive,time consuming,subject to human errors,and stress causing on birds.Therefore,an automated monitoring system is required to track the spatial distribution of hens for early detection of animal welfare and health concerns.In this study,a non–intrusive machine vision method was developed to monitor hens'spatial distribution automatically.An improved You Only Look Once version 5(YOLOv5)method was developed and trained to test hens'distribution in research cage-free facilities(e.g.,200 hens per house).The spatial distribution of hens the system monitored includes perch zone,feeding zone,drinking zone,and nesting zone.The dataset contains a whole growth period of chickens from day 1 to day 252.About 3000 images were extracted randomly from recorded videos for model training,validation,and testing.About 2400 images were used for training and 600 images for testing,respectively.Results show that the accuracy of the new model were 87–94%for tracking distribution in different zones for different ages of hens/pullets.Birds'age affected the performance of the model as younger birds had smaller body size and were hard to be detected due to blackness or occultation by equipment.The performance of the model was 0.891 and 0.942 for baby chicks(≤10 days old)and older birds(>10 days)in detecting perching behaviors;0.874 and 0.932 in detecting feeding/drinking behaviors.Miss detection happened when the flock density was high(>18 birds/m2)and chicken body was occluded by other facilities(e.g.,nest boxes,feeders,and perches).Further studies such as chicken behavior identification works in commercial housing system should be combined with the model to reach an automatic detection system.

Improved inclination correction method applied to the guidance system of agricultural vehicles

This research introduces a new inclination correction method with increased accuracy applied to the guidance system of an agricultural vehicle.The method considers the geometry of a robot tractor and uses an Inertial Measurement Unit(IMU)to correct the lateral error of the RTK-GPS antenna measurements raised by the tractor's inclinations.A parameters optimization experiment and an automatic guidance experiment under real working conditions were used to compare the accuracy of a traditional correction method with the new correction method,by calculating the RMSE of the lateral error and the error reduction percentage.An additional tuned correction method was found by using a simple analytical method to find the optimal variables that reduced the lateral error to a minimum.The results indicate that the new correction method and the tuned correction method display a significant error reduction percentage compared to the traditional correction method.The methods could correct the GPS lateral error caused by the roll inclinations in real-time.The resulting lateral deviation caused by the tractor's inclinations could be reduced up to 23%for typical travelling speeds.

P recision L ivestock F arming: A n international review of scientific and commercial aspects

Precision Livestock Farming(PLF)is potentially one of the most powerful developments amongst a number of interesting new and upcoming technologies that have the potential to revolutionise the livestock farming industries.If properly implemented,PLF or Smart Farming could(1)improve or at least objectively document animal welfare on farms;(2)reduce greenhouse gas(GHG)emission and improve environmental performance of farms;(3)facilitate product segmentation and better marketing of livestock products;(4)reduce illegal trading of livestock products;and(5)improve the economic stability of rural areas.However,there are only a few examples of successful commercialisation of PLF technologies introduced by a small number of commercial companies which are actively involved in the PLF commercialisation process.To ensure that the potential of PLF is taken to the industry,it is recommended to:(1)establish a new service industry;(2)verify,demonstrate and publicise the benefits of PLF;(3)better coordinate the efforts of different industry and academic organisations interested in the development and implementation of PLF technologies on farms;and(4)encourage the commercial sectors to assist with professionally managed product development.

Automatic body condition scoring system for dairy cows based on depth-image analysis

Body condition score(BCS)is an important management tool in the modern dairy industry,and one of the basic techniques for animal welfare and precision dairy farming.The objective of this study was to use a vision system to evaluate the fat cover on the back of cows and to automatically determine BCS.A 3D camera was used to capture the depth images of the back of cows twice a day as each cow passed beneath the camera.Through background subtraction,the back area of the cow was extracted from the depth image.The thurl,sacral ligament,hook bone,and pin bone were located via depth image analysis and evaluated by calculating their visibility and curvature,and those four anatomical features were used to measure fatness.A dataset containing 4820 depth images of cows with 7 BCS levels was built,among which 952 images were used as training data.Taking four anatomical features as input and BCS as output,decision tree learning,linear regression,and BP network were calibrated on the training dataset and tested on the entire dataset.On average,the BP network model scored each cow within 0.25 BCS points compared to their manual scores during the study period.The measured values of visibility and curvature used in this study have strong correlations with BCS and can be used to automatically assess BCS with high accuracy.This study demonstrates that the automatic body condition scoring system has the possibility of being more accurate than human scoring.

Sensor fusion-based approach for the field robot localization on Rovitis 4.0 vineyard robot

This study proposed an approach for robot localization using data from multiple low-cost sensors with two goals in mind,to produce accurate localization data and to keep the computation as simple as possible.The approach used data from wheel odometry,inertial-motion data from the Inertial Motion Unit(IMU),and a location fix from a Real-Time Kinematics Global Positioning System(RTK GPS).Each of the sensors is prone to errors in some situations,resulting in inaccurate localization.The odometry is affected by errors caused by slipping when turning the robot or putting it on slippery ground.The IMU produces drifts due to vibrations,and RTK GPS does not return to an accurate fix in(semi-)occluded areas.None of these sensors is accurate enough to produce a precise reading for a sound localization of the robot in an outdoor environment.To solve this challenge,sensor fusion was implemented on the robot to prevent possible localization errors.It worked by selecting the most accurate readings in a given moment to produce a precise pose estimation.To evaluate the approach,two different tests were performed,one with robot localization from the robot operating system(ROS)repository and the other with the presented Field Robot Localization.The first did not perform well,while the second did and was evaluated by comparing the location and orientation estimate with ground truth,captured by a hovering drone above the testing ground,which revealed an average error of 0.005 m±0.220 m in estimating the position,and 0.6°±3.5°when estimating orientation.The tests proved that the developed field robot localization is accurate and robust enough to be used on a ROVITIS 4.0 vineyard robot.

Real-time recognition of sows in video: A supervised approach

This paper proposes a supervised classification approach for the real-time pattern recognition of sows in an animal supervision system(asup).Our approach offers the possibility of the foreground subtraction in an asup’s image processing module where there is lack of statistical information regarding the background.A set of 7 farrowing sessions of sows,during day and night,have been captured(approximately 7 days/sow),which is used for this study.The frames of these recordings have been grabbed with a time shift of 20 s.A collection of 215 frames of 7 different sows with the same lighting condition have been marked and used as the training set.Based on small neighborhoods around a point,a number of image local features are defined,and their separability and performance metrics are compared.For the classification task,a feed-forward neural network(NN)is studied and a realistic configuration in terms of an acceptable level of accuracy and computation time is chosen.The results show that the dense neighborhood feature(d.3×3)is the smallest local set of features with an acceptable level of separability,while it has no negative effect on the complexity of NN.The results also confirm that a significant amount of the desired pattern is accurately detected,even in situations where a portion of the body of a sow is covered by the crate’s elements.The performance of the proposed feature set coupled with our chosen configuration reached the rate of 8.5 fps.The true positive rate(TPR)of the classifier is 84.6%,while the false negative rate(FNR)is only about 3%.A comparison between linear logistic regression and NN shows the highly non-linear nature of our proposed set of features.

Leaf chlorophyll and nitrogen dynamics and their relationship to lowland rice yield for site-specific paddy management

The optimum rate and application timing of Nitrogen(N)fertilizer are crucial in achieving a high yield in rice cultivation;however,conventional laboratory testing of plant nutrients is time-consuming and expensive.To develop a site-specific spatial variable rate application method to overcome the limitations of traditional techniques,especially in fields under a double-cropping system,this study focused on the relationship between Soil Plant Analysis Development(SPAD)chlorophyll meter readings and N content in leaves during different growth stages to introduce the most suitable stage for assessment of crop N and prediction of rice yield.The SPAD readings and leaf N content were measured on the uppermost fully expanded leaf at panicle formation and booting stages.Grain yield was also measured at the end of the season.The analysis of variance,variogram,and kriging were calculated to determine the variability of attributes and their relationship,and finally,variability maps were created.Significant linear relationships were observed between attributes,with the same trends in different sampling dates;however,accuracy of semivariance estimation reduces with the growth stage.Results of the study also implied that there was a better relationship between rice leaf N content(R^2=0.93),as well as yield(R2=0.81),with SPAD readings at the panicle formation stage.Therefore,the SPAD-based evaluation of N status and prediction of rice yield is more reliable on this stage rather than at the booting stage.This study proved that the application of SPAD chlorophyll meter paves the way for real-time paddy N management and grain yield estimation.It can be reliably exploited in precision agriculture of paddy fields under double-cropping cultivation to understand and control spatial variations.