Purpose-The livestock industry is undergoing a critical transition to intensive,large-scale farming.Intelligent monitoring technologies are essential for improving epidemic early warning systems,reducing breeding cost...Purpose-The livestock industry is undergoing a critical transition to intensive,large-scale farming.Intelligent monitoring technologies are essential for improving epidemic early warning systems,reducing breeding costs,and promoting sustainable production.This study aimed to develop a novel pig behavior recognition method using advanced computer vision technology to support intelligent livestock farming.Design/methodology/approach-The YOLOv5 model was utilized to achieve contactless and efficient monitoring of daily pig activities.The study enhanced the YOLOv5 model by improving its input mechanism,backbone network and by incorporating the shuffle attention module.These modifications significantly improved the ability of the model to capture and interpret the spatiotemporal features of pig behavior.Findings-The experimental results demonstrate that compared with the original YOLOv5 model,the Precision,Recall,mAP@0.5 and mAp@0.5:0.95 of the proposed model has improved by 3.0%,2.3%,2.6%and 10.5%,respectively.These findings showcase the model’s effectiveness and potential for real-world applications in intelligent livestock farming,and highlight the feasibility of employing advanced computer vision models to enhance monitoring and management in animal farming environments.Originality/value-This study presents a novel approach to pig behavior recognition by integrating cutting-edge computer vision techniques with YOLOv5 enhancements.This study contributes to the field by addressing the challenges of spatiotemporal feature extraction and demonstrating the practical application of these methods in intelligent livestock farming.Future research directions include generalization to other animal species,integration with other sensor data,teal-time monitoring and decision support and application in wildlife and laboratory animal research,thus further advancing the intelligent breeding industry.展开更多
[Objective] This experiment aimed to compare piglets behavior under microbial fermentation bed breeding mode and traditional rearing mode. [Method] Pig behavior＇s statistical analysis under both microbial fermentatio...[Objective] This experiment aimed to compare piglets behavior under microbial fermentation bed breeding mode and traditional rearing mode. [Method] Pig behavior＇s statistical analysis under both microbial fermentation bed pig breeding mode and traditional rearing mode was se lected to study the effect of different breeding environment on pig＇s growth [ Result] The results showed that the duration of piglets lying and sleeping behavior accounted for the highest proportion of tested behavior, up to more than 70% ,followed by feeding and drinking which reached 15.96% （under microbial fermentation bed breeding mode） and 9.33% （under traditional rearing mode） respectively. Compared with traditional intensive rearing mode, piglet exploratory behavior＇s occurrence probability and duration increased significantly, by 28.62% and 12.21% respectively. Fighting behavior＇s occurrence probability and duration decreased significantly, by 49.83% and 91.26% respectively. Nutrient index and health index were introduced to evaluate piglet＇s general heath condition under microbial fermentation bed breeding mode, and results indicated that the health index of piglets under microbial fermentation bed breeding mode had slight difference from that under traditional mode, namely 10.83 and 10.03 respectively. But health index of piglets under microbial fermentation bed breeding mode was 245.12, much higher than 21.96 under traditional mode. [ Conclusion] Piglets would be healthier under microbial fermentation bed breeding mode.展开更多
Previous studies suggested that pigs prefer lower environmental temperatures during nighttime compared to daytime. So reducing nocturnal temperature in nursery barns may not jeopardize performance or welfare of pigs, ...Previous studies suggested that pigs prefer lower environmental temperatures during nighttime compared to daytime. So reducing nocturnal temperature in nursery barns may not jeopardize performance or welfare of pigs, but can save energy for heating the barn. A study was conducted to investigate growth performance and behavioral response of nursery pigs to reduced nocturnal temperature. This study was conducted in four replicates, each utilizing 270 newly weaned pigs and lasting for 5 wk. Temperature setpoint in the control room （CON） was started at 30℃ and decreased by 2℃ per week. In the treatment room （RNT）, temperature setpoint was maintained same as in CON between 7：00 h and 19：00 h, and reduced by 8~C between 19：00 h and 7：00 h starting from d 5. Growth performance （15 pens/room, 9 pigs/pen, BW=（6.3±0.61） kg） was monitored for 5 wk, and behaviors in 6 pens in each room were video-recorded for 24 h 3 d after being exposed to the experimental temperature. Instantaneous scan sampling was performed to determine time budgets for standing, sitting, eating, drinking, belly nosing, three postures of lying, and huddling. Two focal pigs were continuously viewed to record duration and occurrence of eating and drinking. Reduced nocturnal temperature did not affect the growth performance of the pigs, time spent standing, sitting, total lying and eating or duration and frequencies of eating and drinking （all P〉0.10）. However, RNT increased time spent lying sternal （83 vs. 72%, P〈0.001） and number of pigs that were huddling （70 vs. 50% of lying pigs, P〈0.001）, and decreased time spent lying laterally （0.8 vs. 4.6%, P〈0.001）, lying half laterally （5.3 vs. 11.0%, P〈0.001）, and belly nosing （0.9 vs. 1.7%, P=0.01） during nighttime. These results indicate that nursery pigs adopted the posture of lying sternal and huddled together to reduce heat loss from their body surface to maintain thermal balance and growth performance in RNT. Such mild reduction in nocturnal temperature in the nursery barn can save energy for heating the barn without negative effects on performance and behavior of nursery pigs.展开更多
The use of iron ores bearing titanium as a raw material is an effective measure to prevent hearth erosion and prolong the life of a blast furnace. In this research, the effect of titanium content on the precipitation ...The use of iron ores bearing titanium as a raw material is an effective measure to prevent hearth erosion and prolong the life of a blast furnace. In this research, the effect of titanium content on the precipitation behaviors of high-melting phases of carbon-saturated molten pig iron were studied by confocal scanning laser microscopy. The results showed that, when the titanium content was less than 0.25 wt%,Fe_3C was precipitated as a single phase from the molten carbon-saturated iron. The growth rate of the precipitated Fe_3C crystals was very high, reaching 7387 μm^2/s. When the titanium content in the molten pig iron was greater than 0.47 wt%, TiC crystals precipitated first. The shape and size of the precipitated TiC crystals did not obviously change. After TiC was precipitated, the fluidity of the molten pig iron worsened. With a decrease in temperature, Fe_3C was also precipitated but the growth rate of Fe_3C was limited by the presence of the first precipitated TiC phase. The crystal size of the precipitated Fe_3C was much smaller than that of pure Fe_3C.展开更多
A total of 60 crossbred(Large White×Landrace) pigs of halothane genotype NN(castrated males and females) were allotted to three treatments:3 h lairage with toys,3 h lairage and 0 h lairage in a randomized complet...A total of 60 crossbred(Large White×Landrace) pigs of halothane genotype NN(castrated males and females) were allotted to three treatments:3 h lairage with toys,3 h lairage and 0 h lairage in a randomized complete block design and used to evaluate the influence of lairage conditions on behavior, biochemical indicators and meat quality for finishing pigs at slaughter.Behavior of the pigs was scored subjectively during lairage.Blood samples were taken at exsanguination s to measure blood temperature, plasma Cortisol,ACTH,glucose,lactate,plasma enzymes and hematological indices.Post-mortem meat quality measurements included muscle colour value(MCV),electrical conductivity(EC),pH at 45 min and 24 h from Longissimus thoracis(LM) and Semimembranosus(SM) mucles and drip loss from LM. The results showed that 3 h lairage group with toys demonstrated significantly improved behavior than the group without toys at 3 sampling times.All the pigs showed increasing calmness as the time of lairage progressed.The omission of lairage increased plasma Cortisol,ACTH,glucose and lactate(P【0.05),and decreased plasma lactate dehydrogenase(LDH),and creatine kinase(CK)(P【0.05).No biochemical index was influenced by the presence or absence of toys during lairage(P【0.05).Muscle colour value, electrical conductivity,pH at 45 min and 24 h from LM and SM and drip loss were not affected by any treatment(P【0.05).Pigs provided 3 h lairage,with or without toys,exhibited lower red blood cell(RBC), hemoglobin(HGB),and haematocrit(HCT) when compared to 0 h lairage.3 h lairage with or without toys resulted in higher white blood cell(WBC) and lymphocyte(W-SCC) levels than 0 h lairage.None of the hemocytic indices in pigs given lairage was affected by the presence or absence of toys.We conclude from this pilot study that in local commercial conditions,from the point of view of animal welfare and meat quality,lairage time of 3 h after short travel was beneficial.Pigs resting showed increased relief from stress and a recovery in immune competence.Holding pigs in lairage with toys for a few hours after arrival at the abattoir may be beneficial for the animal’s well-being.展开更多
Background： Play behavior has been proposed as a new potential indicator of animal welfare. Animals play only if they are in a relaxed state. Play may improve adaptability to challenging environments which may be of ...Background： Play behavior has been proposed as a new potential indicator of animal welfare. Animals play only if they are in a relaxed state. Play may improve adaptability to challenging environments which may be of interest in the breeding objective. Little information is available on play behavior in livestock species. The aim of the present study is to investigate whether play behavior in post-weaned piglets can be induced instantly in the presence of additional space and whether play markers are body weight, sex, and litter dependent, it is investigated whether playfulness is elicited by the moment or if this measure is consistent over different days. Methods： Thirty two piglets from four litters were released into a corridor and video recorded for eight min at 37, 41, 44 and 48 d of age. The first test was considered as an adjustment period and was not included in the analysis. In the second to the fourth test, joyful brusque movements （jumping, turning and running） were recorded with a camera and total number of movements （JOY#） and total time （JOYtime） were estimated individually. Animals were weighed at 41 d of age. Results： Females had higher scores of JOY# and JOYtime than males but this was significant only for JOY# at 41 d of age （P 〈 0.05）. The effect of age was highly significant both for JOY# and JOYtime （P 〈 0.01）. Animals with a higher JOY# and JOYtime also expressed a higher JOY# and JOYtime in the other tests, but this was significant only between 44 and 48 d of age （P〈 0.01）. Body weight at 41 d of age was not significantly related to JOY# and JQYtime in any of the tests. Conclusions： Locomotor play was induced instantly by the provision of increased space allowance. Litter origin had a significant effect on play behavior. In addition, locomotor play scores were consistent between two of the three tests.展开更多
China's extensive development model of pig industry gives rise to serious resource and environment bottleneck restriction,it is urgent to transform the existing development model into ecological farming model. In ...China's extensive development model of pig industry gives rise to serious resource and environment bottleneck restriction,it is urgent to transform the existing development model into ecological farming model. In this process,farmers' behavior will play a key role. On the basis of summarizing development connotation and characteristics of ecological agriculture,using survey data of 323 pig farmers in 6 provinces,based on the Theory of Planned Behavior( TPB) it introduced individual characteristics and external environment constraint variables,and made an empirical analysis on factors influencing intention and behavior of pig farmers' ecological farming using the Structural Equation Model( SEM). Results indicate:( i) ecological farming intention of pig farmers has the largest direct effect on their ecological farming behavior;( ii)ecological farming cognition of pig farmers has significant positive effect on their ecological farming behavior;( iii) external environment has the largest indirect effect on their ecological farming behavior,followed by the overall effect,and external environment has significant positive effect on ecological farming attitude and cognition of pig farmers;( iv) individual characteristics( educational level and income level) of pig farmers influence ecological farming behavior of pig farmers through their ecological farming attitude and intention,but the degree of influence is limited.展开更多
基于视频的生猪行为跟踪和识别对于实现精细化养殖具有重要价值。为了应对群养生猪多目标跟踪任务中由猪只外观相似、遮挡交互等因素带来的挑战,研究提出了基于PigsTrack跟踪器的群养生猪多目标跟踪方法。PigsTrack跟踪器利用高性能YOLO...基于视频的生猪行为跟踪和识别对于实现精细化养殖具有重要价值。为了应对群养生猪多目标跟踪任务中由猪只外观相似、遮挡交互等因素带来的挑战,研究提出了基于PigsTrack跟踪器的群养生猪多目标跟踪方法。PigsTrack跟踪器利用高性能YOLOX网络降低目标误检与漏检率,采用Transformer模型获取具有良好区分特性的目标外观特征;基于OC-SORT(observation-centric sort)的思想,通过集成特征匹配、IoU匹配和遮挡恢复匹配策略实现群养生猪的准确跟踪。基于PBVD(pigs behaviours video dataset)数据集的试验结果表明,PigsTrack跟踪器的HOTA(higher order tracking accuracy),MOTA(multiple object tracking accuracy)和IDF1得分(identification F1 score)分别为85.66%、98.59%和99.57%,相较于现有算法的最高精度,分别提高了3.71、0.03和2.05个百分点,证明了PigsTrack跟踪器在解决外观相似和遮挡交互引起的跟踪过程中身份跳变问题方面的有效性。随后,利用Slowfast网络对PigsTrack跟踪器的跟踪结果进行了典型行为统计,结果显示PigsTrack在群养生猪个体行为统计方面更准确。此外,通过在ABVD(aggressive-behavior video)数据集上的试验,PigsTrack跟踪器的HOTA、MOTA和IDF1得分分别为69.14%、94.82%和90.11%,相对于现有算法的最高精度,提高了5.33、0.57和8.60个百分点,验证了PigsTrack跟踪器在群养生猪跟踪任务中的有效性。总而言之,PigsTrack跟踪器能够有效应对外观相似和遮挡交互等挑战,实现了准确的生猪多目标跟踪,并在行为统计方面展现出更高的准确性,为生猪养殖领域的研究和实际应用提供了有价值的指导。展开更多
针对传统的群养猪行为观察方法的缺点,提出了1种疑似病猪行为自动监测系统。系统基于ARM平台,利用安装于猪舍排泄区的嵌入式监控设备对群养猪的排泄行为进行24h监控,通过1种改进的运动目标检测算法和基于像素块对称特征的图像识别算法...针对传统的群养猪行为观察方法的缺点,提出了1种疑似病猪行为自动监测系统。系统基于ARM平台,利用安装于猪舍排泄区的嵌入式监控设备对群养猪的排泄行为进行24h监控,通过1种改进的运动目标检测算法和基于像素块对称特征的图像识别算法定位具有异常行为的疑似病猪,并将报警图像通过通用分组无线服务(general packet radio service)网络传送至监控中心。对一栏10头大约克夏猪的试验结果表明,病猪检测正确率为78.38%,基本达到了预期的目标。因此,该文设计的方法对我国的养殖业实施自动化监测具有一定的借鉴意义。展开更多
在利用视频监控技术对群养猪只进行自动行为监测时,对猪只准确定位并辨别其头尾位置对提高监测水平至关重要,基于此提出一种基于YOLO v3(You only look once v3)模型与图结构模型(Pictorial structure models)的猪只头尾辨别方法。首先...在利用视频监控技术对群养猪只进行自动行为监测时,对猪只准确定位并辨别其头尾位置对提高监测水平至关重要,基于此提出一种基于YOLO v3(You only look once v3)模型与图结构模型(Pictorial structure models)的猪只头尾辨别方法。首先,利用基于深度卷积神经网络的YOLO v3目标检测模型,训练猪只整体及其头部和尾部3类目标的检测器,从而在输入图像中获得猪只整体及头尾部所有的检测结果;然后,引入图结构模型,描述猪只的头尾结构特征,对每个猪只整体检测矩形框内的头尾部位组合计算匹配得分,选择最优的部位组合方式;对部分部位漏检的情况,采取阈值分割与前景椭圆拟合的方法,根据椭圆长轴推理出缺失部位。在实际猪场环境下,通过俯拍获得猪舍监控视频,建立了图像数据集,并进行了检测实验。实验结果表明,与直接利用YOLO v3模型相比,本文方法对头尾定位的精确率和召回率均有一定提高。本文方法对猪只头尾辨别精确率达到96.22%,与其他方法相比具有明显优势。展开更多
基金supported by the Natural Science Foundation of Fujian Province(2022J011178)the young and middle-aged teachers education research project of Fujian Province(JAT210422)the Sanming College Scientific Research Development Fund(B202103).
文摘Purpose-The livestock industry is undergoing a critical transition to intensive,large-scale farming.Intelligent monitoring technologies are essential for improving epidemic early warning systems,reducing breeding costs,and promoting sustainable production.This study aimed to develop a novel pig behavior recognition method using advanced computer vision technology to support intelligent livestock farming.Design/methodology/approach-The YOLOv5 model was utilized to achieve contactless and efficient monitoring of daily pig activities.The study enhanced the YOLOv5 model by improving its input mechanism,backbone network and by incorporating the shuffle attention module.These modifications significantly improved the ability of the model to capture and interpret the spatiotemporal features of pig behavior.Findings-The experimental results demonstrate that compared with the original YOLOv5 model,the Precision,Recall,mAP@0.5 and mAp@0.5:0.95 of the proposed model has improved by 3.0%,2.3%,2.6%and 10.5%,respectively.These findings showcase the model’s effectiveness and potential for real-world applications in intelligent livestock farming,and highlight the feasibility of employing advanced computer vision models to enhance monitoring and management in animal farming environments.Originality/value-This study presents a novel approach to pig behavior recognition by integrating cutting-edge computer vision techniques with YOLOv5 enhancements.This study contributes to the field by addressing the challenges of spatiotemporal feature extraction and demonstrating the practical application of these methods in intelligent livestock farming.Future research directions include generalization to other animal species,integration with other sensor data,teal-time monitoring and decision support and application in wildlife and laboratory animal research,thus further advancing the intelligent breeding industry.
基金funded by Major Science and Technology Projects for National Water Pollution Control and Management(No.2008ZX07425-002)Programs Supported by National Key Basic Research and Development Plan(2011CB111607)+3 种基金Key Programs of Ministry of Agriculture's Introduction of International Advanced Agricultural Science and Technology(2011-G25)Provincial Development and Reform Programs(Fujian Development,Reform and Investment#[2008]762)Provincial Science and Technology Plan Programs(2009S0089)Fujian Finance Special Fund(No.STIF-Y03)
文摘[Objective] This experiment aimed to compare piglets behavior under microbial fermentation bed breeding mode and traditional rearing mode. [Method] Pig behavior＇s statistical analysis under both microbial fermentation bed pig breeding mode and traditional rearing mode was se lected to study the effect of different breeding environment on pig＇s growth [ Result] The results showed that the duration of piglets lying and sleeping behavior accounted for the highest proportion of tested behavior, up to more than 70% ,followed by feeding and drinking which reached 15.96% （under microbial fermentation bed breeding mode） and 9.33% （under traditional rearing mode） respectively. Compared with traditional intensive rearing mode, piglet exploratory behavior＇s occurrence probability and duration increased significantly, by 28.62% and 12.21% respectively. Fighting behavior＇s occurrence probability and duration decreased significantly, by 49.83% and 91.26% respectively. Nutrient index and health index were introduced to evaluate piglet＇s general heath condition under microbial fermentation bed breeding mode, and results indicated that the health index of piglets under microbial fermentation bed breeding mode had slight difference from that under traditional mode, namely 10.83 and 10.03 respectively. But health index of piglets under microbial fermentation bed breeding mode was 245.12, much higher than 21.96 under traditional mode. [ Conclusion] Piglets would be healthier under microbial fermentation bed breeding mode.
基金the National Pork Board and the Pork Checkoff, USA, for partial financial support of the project
文摘Previous studies suggested that pigs prefer lower environmental temperatures during nighttime compared to daytime. So reducing nocturnal temperature in nursery barns may not jeopardize performance or welfare of pigs, but can save energy for heating the barn. A study was conducted to investigate growth performance and behavioral response of nursery pigs to reduced nocturnal temperature. This study was conducted in four replicates, each utilizing 270 newly weaned pigs and lasting for 5 wk. Temperature setpoint in the control room （CON） was started at 30℃ and decreased by 2℃ per week. In the treatment room （RNT）, temperature setpoint was maintained same as in CON between 7：00 h and 19：00 h, and reduced by 8~C between 19：00 h and 7：00 h starting from d 5. Growth performance （15 pens/room, 9 pigs/pen, BW=（6.3±0.61） kg） was monitored for 5 wk, and behaviors in 6 pens in each room were video-recorded for 24 h 3 d after being exposed to the experimental temperature. Instantaneous scan sampling was performed to determine time budgets for standing, sitting, eating, drinking, belly nosing, three postures of lying, and huddling. Two focal pigs were continuously viewed to record duration and occurrence of eating and drinking. Reduced nocturnal temperature did not affect the growth performance of the pigs, time spent standing, sitting, total lying and eating or duration and frequencies of eating and drinking （all P〉0.10）. However, RNT increased time spent lying sternal （83 vs. 72%, P〈0.001） and number of pigs that were huddling （70 vs. 50% of lying pigs, P〈0.001）, and decreased time spent lying laterally （0.8 vs. 4.6%, P〈0.001）, lying half laterally （5.3 vs. 11.0%, P〈0.001）, and belly nosing （0.9 vs. 1.7%, P=0.01） during nighttime. These results indicate that nursery pigs adopted the posture of lying sternal and huddled together to reduce heat loss from their body surface to maintain thermal balance and growth performance in RNT. Such mild reduction in nocturnal temperature in the nursery barn can save energy for heating the barn without negative effects on performance and behavior of nursery pigs.
基金financially supported by the National Natural Science Foundation of China (No. 51674054)the Open Foundation of State Key Laboratory of Vanadium and Titanium Resources Comprehensive Utilization of China
文摘The use of iron ores bearing titanium as a raw material is an effective measure to prevent hearth erosion and prolong the life of a blast furnace. In this research, the effect of titanium content on the precipitation behaviors of high-melting phases of carbon-saturated molten pig iron were studied by confocal scanning laser microscopy. The results showed that, when the titanium content was less than 0.25 wt%,Fe_3C was precipitated as a single phase from the molten carbon-saturated iron. The growth rate of the precipitated Fe_3C crystals was very high, reaching 7387 μm^2/s. When the titanium content in the molten pig iron was greater than 0.47 wt%, TiC crystals precipitated first. The shape and size of the precipitated TiC crystals did not obviously change. After TiC was precipitated, the fluidity of the molten pig iron worsened. With a decrease in temperature, Fe_3C was also precipitated but the growth rate of Fe_3C was limited by the presence of the first precipitated TiC phase. The crystal size of the precipitated Fe_3C was much smaller than that of pure Fe_3C.
基金supported financially by the project‘Research and Development on Technology and Key Equipment for New Type of Industrialized and Healthy Animal Husbandry'funded by the Chinese Ministry of Science and Technology(2006BAD 14B02-6)11th Five Years Key Programs for Science and Technology Development of China(2006BAD01A08-07)+1 种基金Hubei Province Key Project of Science and Technology (2006AA201B24)Wuhan City Key Project of Industrialization(200720112026)
文摘A total of 60 crossbred(Large White×Landrace) pigs of halothane genotype NN(castrated males and females) were allotted to three treatments:3 h lairage with toys,3 h lairage and 0 h lairage in a randomized complete block design and used to evaluate the influence of lairage conditions on behavior, biochemical indicators and meat quality for finishing pigs at slaughter.Behavior of the pigs was scored subjectively during lairage.Blood samples were taken at exsanguination s to measure blood temperature, plasma Cortisol,ACTH,glucose,lactate,plasma enzymes and hematological indices.Post-mortem meat quality measurements included muscle colour value(MCV),electrical conductivity(EC),pH at 45 min and 24 h from Longissimus thoracis(LM) and Semimembranosus(SM) mucles and drip loss from LM. The results showed that 3 h lairage group with toys demonstrated significantly improved behavior than the group without toys at 3 sampling times.All the pigs showed increasing calmness as the time of lairage progressed.The omission of lairage increased plasma Cortisol,ACTH,glucose and lactate(P【0.05),and decreased plasma lactate dehydrogenase(LDH),and creatine kinase(CK)(P【0.05).No biochemical index was influenced by the presence or absence of toys during lairage(P【0.05).Muscle colour value, electrical conductivity,pH at 45 min and 24 h from LM and SM and drip loss were not affected by any treatment(P【0.05).Pigs provided 3 h lairage,with or without toys,exhibited lower red blood cell(RBC), hemoglobin(HGB),and haematocrit(HCT) when compared to 0 h lairage.3 h lairage with or without toys resulted in higher white blood cell(WBC) and lymphocyte(W-SCC) levels than 0 h lairage.None of the hemocytic indices in pigs given lairage was affected by the presence or absence of toys.We conclude from this pilot study that in local commercial conditions,from the point of view of animal welfare and meat quality,lairage time of 3 h after short travel was beneficial.Pigs resting showed increased relief from stress and a recovery in immune competence.Holding pigs in lairage with toys for a few hours after arrival at the abattoir may be beneficial for the animal’s well-being.
基金financed by a Marie Curie International Reintegration Grant from the European Union,project no.PIRG08-GA-2010-277031 "SelectionForWelfare"
文摘Background： Play behavior has been proposed as a new potential indicator of animal welfare. Animals play only if they are in a relaxed state. Play may improve adaptability to challenging environments which may be of interest in the breeding objective. Little information is available on play behavior in livestock species. The aim of the present study is to investigate whether play behavior in post-weaned piglets can be induced instantly in the presence of additional space and whether play markers are body weight, sex, and litter dependent, it is investigated whether playfulness is elicited by the moment or if this measure is consistent over different days. Methods： Thirty two piglets from four litters were released into a corridor and video recorded for eight min at 37, 41, 44 and 48 d of age. The first test was considered as an adjustment period and was not included in the analysis. In the second to the fourth test, joyful brusque movements （jumping, turning and running） were recorded with a camera and total number of movements （JOY#） and total time （JOYtime） were estimated individually. Animals were weighed at 41 d of age. Results： Females had higher scores of JOY# and JOYtime than males but this was significant only for JOY# at 41 d of age （P 〈 0.05）. The effect of age was highly significant both for JOY# and JOYtime （P 〈 0.01）. Animals with a higher JOY# and JOYtime also expressed a higher JOY# and JOYtime in the other tests, but this was significant only between 44 and 48 d of age （P〈 0.01）. Body weight at 41 d of age was not significantly related to JOY# and JQYtime in any of the tests. Conclusions： Locomotor play was induced instantly by the provision of increased space allowance. Litter origin had a significant effect on play behavior. In addition, locomotor play scores were consistent between two of the three tests.
基金Supported by Project of National Natural Science Foundation(41171436)Key Project of National Social Science Foundation(14AZD002)
文摘China's extensive development model of pig industry gives rise to serious resource and environment bottleneck restriction,it is urgent to transform the existing development model into ecological farming model. In this process,farmers' behavior will play a key role. On the basis of summarizing development connotation and characteristics of ecological agriculture,using survey data of 323 pig farmers in 6 provinces,based on the Theory of Planned Behavior( TPB) it introduced individual characteristics and external environment constraint variables,and made an empirical analysis on factors influencing intention and behavior of pig farmers' ecological farming using the Structural Equation Model( SEM). Results indicate:( i) ecological farming intention of pig farmers has the largest direct effect on their ecological farming behavior;( ii)ecological farming cognition of pig farmers has significant positive effect on their ecological farming behavior;( iii) external environment has the largest indirect effect on their ecological farming behavior,followed by the overall effect,and external environment has significant positive effect on ecological farming attitude and cognition of pig farmers;( iv) individual characteristics( educational level and income level) of pig farmers influence ecological farming behavior of pig farmers through their ecological farming attitude and intention,but the degree of influence is limited.
文摘基于视频的生猪行为跟踪和识别对于实现精细化养殖具有重要价值。为了应对群养生猪多目标跟踪任务中由猪只外观相似、遮挡交互等因素带来的挑战,研究提出了基于PigsTrack跟踪器的群养生猪多目标跟踪方法。PigsTrack跟踪器利用高性能YOLOX网络降低目标误检与漏检率,采用Transformer模型获取具有良好区分特性的目标外观特征;基于OC-SORT(observation-centric sort)的思想,通过集成特征匹配、IoU匹配和遮挡恢复匹配策略实现群养生猪的准确跟踪。基于PBVD(pigs behaviours video dataset)数据集的试验结果表明,PigsTrack跟踪器的HOTA(higher order tracking accuracy),MOTA(multiple object tracking accuracy)和IDF1得分(identification F1 score)分别为85.66%、98.59%和99.57%,相较于现有算法的最高精度,分别提高了3.71、0.03和2.05个百分点,证明了PigsTrack跟踪器在解决外观相似和遮挡交互引起的跟踪过程中身份跳变问题方面的有效性。随后,利用Slowfast网络对PigsTrack跟踪器的跟踪结果进行了典型行为统计,结果显示PigsTrack在群养生猪个体行为统计方面更准确。此外,通过在ABVD(aggressive-behavior video)数据集上的试验,PigsTrack跟踪器的HOTA、MOTA和IDF1得分分别为69.14%、94.82%和90.11%,相对于现有算法的最高精度,提高了5.33、0.57和8.60个百分点,验证了PigsTrack跟踪器在群养生猪跟踪任务中的有效性。总而言之,PigsTrack跟踪器能够有效应对外观相似和遮挡交互等挑战,实现了准确的生猪多目标跟踪,并在行为统计方面展现出更高的准确性,为生猪养殖领域的研究和实际应用提供了有价值的指导。
文摘针对传统的群养猪行为观察方法的缺点,提出了1种疑似病猪行为自动监测系统。系统基于ARM平台,利用安装于猪舍排泄区的嵌入式监控设备对群养猪的排泄行为进行24h监控,通过1种改进的运动目标检测算法和基于像素块对称特征的图像识别算法定位具有异常行为的疑似病猪,并将报警图像通过通用分组无线服务(general packet radio service)网络传送至监控中心。对一栏10头大约克夏猪的试验结果表明,病猪检测正确率为78.38%,基本达到了预期的目标。因此,该文设计的方法对我国的养殖业实施自动化监测具有一定的借鉴意义。
文摘在利用视频监控技术对群养猪只进行自动行为监测时,对猪只准确定位并辨别其头尾位置对提高监测水平至关重要,基于此提出一种基于YOLO v3(You only look once v3)模型与图结构模型(Pictorial structure models)的猪只头尾辨别方法。首先,利用基于深度卷积神经网络的YOLO v3目标检测模型,训练猪只整体及其头部和尾部3类目标的检测器,从而在输入图像中获得猪只整体及头尾部所有的检测结果;然后,引入图结构模型,描述猪只的头尾结构特征,对每个猪只整体检测矩形框内的头尾部位组合计算匹配得分,选择最优的部位组合方式;对部分部位漏检的情况,采取阈值分割与前景椭圆拟合的方法,根据椭圆长轴推理出缺失部位。在实际猪场环境下,通过俯拍获得猪舍监控视频,建立了图像数据集,并进行了检测实验。实验结果表明,与直接利用YOLO v3模型相比,本文方法对头尾定位的精确率和召回率均有一定提高。本文方法对猪只头尾辨别精确率达到96.22%,与其他方法相比具有明显优势。
