Search

China is the major producer and consumer of pork all around the world. In China, pork production has accounted for more than 60% of meat production for a long time. Nowadays, the pig industry has gradually shifted from decentralized and extensive breeding to intensive large-scale breeding, promoting production efficiency. At present, as people's demand for the quantity and quality of pork is increasing, China's pig industry faces the problem that the output and quality of pork can not meet people's daily needs. With the rise of artificial intelligence technology in recent years, deep learning technology has been developed rapidly and widely used in image and audio recognition, natural language processing, robotics, bioinformatics, chemistry, finance, and other fields. It is also an essential tool in developing precision livestock farming. The body condition, behavior and health status of pigs could directly affect the income level of pig farms, so through using deep learning technology, we can quickly and accurately acquire the relevant information about pigs, and carry out precise management to improve the feeding efficiency and welfare levels of pigs. This paper expounds on the research progress and application status of deep learning technology used in target pig detection, pig image segmentation, pig body condition and abnormal monitoring, as well as pig behavior recognition. Then we put forward the improvement strategy of deep learning technology used in the process of pig feeding, which make it easier for researchers to understand. At the same time, we summarize and analyze the data sources and datasets, application scope, and model optimization of previous works using deep learning technology in pig breeding. In the field of data sources and datasets, mobile computer vision systems are currently more suitable than systems with many fixed cameras when they are applied in pig houses, therefore, further research could focus on how to use deep learning technology to mobile computer vision systems. Deep learning technology requires a large amount of data to learn data features, which is a massive disadvantage for pig applications. To get pre-training weights suitable for agricultural data sets, a large number of public datasets and a unified dataset standard suited to the pig field should be established. In terms of application scope, due to the short application time of deep learning in the process of raising pigs, many critical occasions are not involved or seldom involved in existing research, so the application scope of deep learning should further expand. In model optimization, optimizing the model to meet the needs of practical application scenarios is the direction of future research. Optimizing the model to achieve a better balance between size and model performance requires further study. Optimizing the model to locate the start and end time of the behavior in unclipped video and recognize the behavior of target pigs is the challenge in identifying the behavior of pigs in future. China's research on deep learning is at the top level, so the application prospect of deep learning in pig farming is highly expected. Combined with the actual production scene of pigs, deep learning technology will significantly contribute to the development of precision livestock farming. [ABSTRACT FROM AUTHOR]

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Housing environment has become a driving factor on hen health, egg quality and efficient production in intensive poultry industry. In large layer poultry housing system, an environmental index is typically used to control air conditions, including air temperature (T), relative humidity (RH) and concentration of carbon dioxide (CO2) in different season. In hot seasons, thermal environment of laying hen housing is usually assessed using the temperature humidity index (THI) via the online monitored temperature and relative humidity. However, the simple assessment cannot meet the harsh requirement of indoor air quality in a large layer house, as the stocking density increases in recent years. In this paper, a comprehensive environmental index (CEI) was proposed based on the radar map to integrate the impacts of both thermal and air quality factors, in order to systematically assess the environment comfort of the birds. A LabVIEW software system was selected to illustrate the environmental comfort using the fuzzy mathematics. Five key environmental factors, including temperature, RH, air velocity, concentration of CO2 and ammonia (NH3), were used to evaluate the environmental comfort of laying hen housing, where the their weights were normalized in a radar map. In the visualized system, early warning can be delivered when either a single factor or the CEI was over the prescribed value, and thereby a quick action can be taken to adjust the environmental conditions in the layer housing to a comfort level. A field measurement was carried out at a commercial layer breeder farm in Hebei province from January to February, and from July to August, 2019. The experimental results indicated that a good performance of the CEI can be obtained to assess the comprehensive environment in the tested house via monitoring the five environmental indexes. The specific sensors were properly settled in the henhouse. The data of environmental conditions was collected to verify, and then the maximum of five indexes were selected for later use. During the summer daytime, the CEI agreed well with the THI, indicating the positive impacts of thermal environment on the comfort of the birds, while it performed better to integrate the thermal and air quality at night time. In winter, the increase in the weight of CO2 concentration can contribute to the CEI for the comfort in layer housing system. The in situ monitoring data in the actual use demonstrated that the CEI can efficiently represent the change of comprehensive environmental comfort in the chicken house, and respond to the interaction between environmental factors in each period, especially when the air quality has an increasing influence on the comprehensive environmental comfort at night in summer and in winter. The findings can provide a promising method to systematically evaluate the housing environment via the five key factors in laying hen housing, further to improve the birds comfort via precisely controlling the air conditions in intensive poultry production. [ABSTRACT FROM AUTHOR]

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The body condition scoring (BCS) is an important tool of assessment method on body condition for sow raising and management. It has been divided into 5 grades that from emaciated to overly fat grade and each grade had a score. The traditional method has negative effect on animals and farmers, and the process is complex with excessive contact. The body size and shape of sows are correlated with their reproductive performance but are difficult to measure manually. There is subjective uncertainty in the process of manual measurement. The Kinect’s 3D reconstruction technology was used to estimate and analyze the buttock shape of sows. A total of 108 images of Large White sows were manually acquired by Kinect camera during the feeding process at Feng Ning Animal Experimental Building in Chengde, Hebei Province of China, from July 25, 2017 to August 15, 2017. The hip height and hip width were measured by using tape and the back fat thickness was measured by using back fat measuring instrument. The hip height, hip width and area of buttock were obtained by analyzing the key points of 48 images. In order to obtain the measurement points of the livestock, several processing steps were taken, and the steps were as follow: 1) The sow stall was removed manually by Geomagic, and the target pig was acquired. In order to improve post-processing speed, the vertex culling algorithm was used to simplify the Three-dimensional model. 2) Since the models acquired were from different angles, the principal component analysis (PCA) was used to acquire new coordinate system. By using the geometrical relationship among the coordinate axes, standard measuring coordinate system was defined in this paper. 3) According to the geometric feature of the measurement points, the hip height, hip width and area of buttock were obtained. The results showed that the root mean square error of estimated body size was less than 2.1 cm, which meet the requirements of precision. The slice method was used to draw a curve at the highest point of the area of buttock based on the point cloud data. The least square fitting method was used to get the curve of hip contour. The hip radius of curvature was calculated by derivation formula. The results showed that the height-width ratio, area and radius of curvature of the sow’s hip had the correlation with the back fat thickness. The correlation coefficients were 0.567, 0.502 and 0.951 respectively. With radius of curvature as the main parameter, the sow body condition estimation model was built based on the experience of hip morphology. 60 images were selected for validation. By comparing the measured and the estimated values of back fat thickness, the maximum absolute error of back fat detection is 1.3 mm and the average relative error is 3.7%. The accuracy of body condition assessment was 91.7% compared with the traditional methods. All the results mentioned above indicate that this study provides a non-contact body condition assessment method based on 3D reconstruction technology and has certain application potential in the real livestock productive. [ABSTRACT FROM AUTHOR]

Living in a comfortable environment during the period of egg production will enable laying hens to achieve their genetic potential. With the development of the poultry industry to larger scale, the air quality in laying house has become the most important factor affecting the health level and production performance of laying hens. Because of the complexity of environmental factors, such as temperature, relative humidity, wind speed, and concentration of CO2 and NH3, it is difficult to describe the level of the environmental comfort quantitatively. In this study, the real-time system of monitoring environment comfort for laying hens was established by the following methods. Firstly, the comfort thresholds of temperature, relative humidity, wind speed, and concentration of CO2 and NH3 for laying hens were established respectively by investigating relevant references. The results showed that the temperatures for comfortable zone (CZ), less comfortable zone (LCZ) and uncomfortable zone (UZ) were 18-21 ℃, 13-18 or 21-26 ℃, and <5 ℃ or >30 ℃ respectively. As for the RH, the temperatures for these 3 zones were 60%-70%, 40%-60% or 70%-72%, and <40% or >72% respectively. The ranges of wind speed for CZ, LCZ and UZ in winter were 0.1-0.2 m/s, 0-0.1 or 0.2-0.25 m/s and >0.25 m/s respectively, and in summer were 0.5-1.5 m/s, 0.25-0.5 or 1.5-2.5 m/s and <0.25 or >2.5 m/s respectively. And the concentrations of CO2 for these 3 zones were <1 500, 1 500-4 000, and >4 000 mg/m3 respectively; the concentrations of NH3 were <15, 15-20, and >25 mg/m3, respectively. Secondly, the theory of fuzzy comprehensive evaluation was used for data fusion of the environment factors, and AHP (analytic hierarchy process) was applied to determine the weight of the environment factors in winter and summer. The results showed that the weight set of temperature, relative humidity, wind speed, concentration of CO2 and NH3 in winter was 0.428 6, 0.151 1, 0.049 5, 0.282 8, and 0.087 9, respectively, and in summer was 0.432 6, 0.241 8, 0.102 9, 0.081 3, and 0.141 4, respectively. Thirdly, a real-time data collection and analysis system of laying house environment was built through the LabVIEW platform, and the real-time environmental comfort evaluation was presented in this system. Lastly, a new method named comfort time proportion method was developed to collect the statistic data of environmental comfort during feeding period. On the basis of the platform of Agricultural Internet constructed by Key Laboratory of Agriculture Engineering in Structure and Environment, Ministry of Agriculture, the laying houses in the Huangshan Deqingyuan Poultry company and in the Shangzhuang Experimental Station of China Agricultural University were selected as the environmental data acquisition node, and then the real-time monitoring system of environmental comfort for laying hens was tested and verified. Compared with the single environment factor, the system can reflect the environmental comfort of the house more comprehensively. And the environment comfort of the laying house in Deqingyuan was better than that in Shangzhuang Experimental Station in winter. The outcomes of this paper will be helpful for evaluating the environment comfort for laying hens. [ABSTRACT FROM AUTHOR]

With the advancement of digital agriculture, researching on pig weight estimation by using machine vision technology has become one of hotspots. The outside light environment of machine vision has a great influence on the quality of captured images. Ignoring the significance of lighting system, majorities of studies on pig weight estimation focused on algorithms and image processing without quantitative assessment methods of light environment. This research focus on the light environment for machine vision in typical piggery and the purpose is to explore a method to achieve effectively screening images taken by monitoring platform to filter out a large amount of invalid images interfered by outside light environment. This paper, based on pig weight monitoring platform, LabVIEW software was used to analyze the image quality of actual light environment condition. Researches consisted of field test and laboratory test. Light measurement of region of interest was mainly carried out in field test during different breeding periods as well as with different heights of pig body. Laboratory test was divided into two parts. One was the calibration of light sensor and the other was image processing for comparing the difference between the algorithm value and the real value. Experiments were carried out in the experimental station of Shangzhuang of China Agricultural University and the test objects were 5 heads of castration landrace. AS813 illuminance meter of SMART SENSOR Company was used to conduct research in test spot. In order to ensure the data accuracy, it was conducted two times of sensor calibration. The analysis of uniformity of illumination in measurement area was referred to lighting engineering standards for evaluating the intensity of illumination evenness. U1 and U2 parameters were used to evaluate evenness index of illumination intensity. U1 is the ratio of the minimum illuminance and the maximum illuminance. U2 is the ratio of the minimum illuminance and the average illuminance. By means of computer software program, it could replace artificial measures to realize the measurement of illumination simulation values, the gray level change rate and image exposure judgement parameters. After on-site validation experiments as well as data analysis, it had not significant difference among light measurements of various height of pig body during breeding period. Also, it had no obvious difference between measured value and simulation value. The correlation coefficient of U1 between measured value and simulation value is 0.791 and the correlation coefficient of U2 between measured value and simulation value is 0.853. Replacing measured values, simulation can fast achieve the distribution of the light environment approximately. Illumination correction coefficient τ was put forward in order to ensure the validity of the data, reflect the true light environment and make up for 20% relative error of the measurement instrument. In addition, it is obviously different among ideal image, overexposed image, natural light image and Yin and Yang image in the parameters of exposure and uniformity ratio of illumination: the illumination uniformity parameters of ideal image and overexposed image meet the requirement of standards of illuminating engineering, and the normal rate of exposure for ideal image rate is higher. The illumination uniformity parameters of natural light image and Yin and Yang image did not meet the requirements of standards of illuminating engineering. Judgment standards of normal exposure were determined at U1>0.7 and U2>0.8 to realize the filter of ideal image which is convenient for researchers screening out ideal image. [ABSTRACT FROM AUTHOR]

In order to improve the welfare and health level of laying hens, alternative housing systems for egg production are emerging and increasingly adopted by egg producers.Perching systems are among those worthy of consideration for adoption, since they can increase the laying hens′ vertical and horizontal activity space, and also allow them to express their natural roosting behavior, which is an important indicator of good welfare.Yet along with the shift to the perching systems comes the need to investigate whether the new design of such system, such as the location, number, or size of the perches, can accommodate the laying hens′ behavioral needs when at rest.These needs are often investigated by observing the laying hens′ distribution in the perches.However, such information is seriously lacking or hard to acquire automatically, and the manual collection of the data is not only inefficient, but also disturbs the laying hens even though it′s achievable occasionally.To enable continuous monitoring of perch use, time spent at perches and frequency of visits to perches by laying hens, a system for the automatic monitoring of laying hens′ perch distribution based on LabVIEW platform was developed, and the main features consist of an on site data acquisition module, a system calibration module, a data analysis module, and a remote user interface module.The automated monitoring system employs load cell weighing, video imaging and a data acquisition system.The experiment was carried out in a perch system between August 26, 2015 and September 26, 2015 at the Shang Zhuang Experimental Station of China Agricultural University.The system was equipped by feeders, manure belt, nest boxes, perches, egg belt and etc.The experiment unit housed a breeding group of 80 hens and 8 cockerels, and 15 perches were equipped inside and numbered from 1 to 15.Every weighing node was formed by 2 weight sensors fixed on the cage stents and a two meter long perch.The weight calibration equation was obtained at the beginning of the experiment by least square fitting the collection value and the actual weight value and was applied to the data acquisition program.A synchronous image was captured by a network camera when the distribution weight data were collected.The laying hens′ distribution values on the 6th, 7th and 8th perches for every image were identified manually and then compared with the data calculated by the system to verify the system accuracy.The results showed that the accuracy of the laying hens′ average distribution value was higher than 90%, and when the distribution number was less than 6, the accuracy was greater than 99%.There were about 40 hens on the perches at night during the period of the experiment, which indicated the 50% perch utilization.At the age of 70 weeks, the absolute error of the laying hens′ average weight between measured manually and calculated by the system was within 0.1 kg.Thus, the simplified system can be applied to monitor the average body weights of laying hens during rearing period.The monitoring system can supply the real time information of laying hen perch distribution accurately in the perching systems.This paper describes the detailed design and development of the automated monitoring system of laying hens perch distribution.Such a system can provide data support and reference for perching system design of laying hens. [ABSTRACT FROM AUTHOR]