Accurate and continuous identification of individual cattle is crucial to precision farming in recent years.It is also the prerequisite to monitor the individual feed intake and feeding time of beef cattle at medium t...Accurate and continuous identification of individual cattle is crucial to precision farming in recent years.It is also the prerequisite to monitor the individual feed intake and feeding time of beef cattle at medium to long distances over different cameras.However,beef cattle can tend to frequently move and change their feeding position during feeding.Furthermore,the great variations in their head direction and complex environments(light,occlusion,and background)can also lead to some difficulties in the recognition,particularly for the bio-similarities among individual cattle.Among them,AlignedReID++model is characterized by both global and local information for image matching.In particular,the dynamically matching local information(DMLI)algorithm has been introduced into the local branch to automatically align the horizontal local information.In this research,the AlignedReID++model was utilized and improved to achieve the better performance in cattle re-identification(ReID).Initially,triplet attention(TA)modules were integrated into the BottleNecks of ResNet50 Backbone.The feature extraction was then enhanced through cross-dimensional interactions with the minimal computational overhead.Since the TA modules in AlignedReID++baseline model increased the model size and floating point operations(FLOPs)by 0.005 M and 0.05 G,the rank-1 accuracy and mean average precision(mAP)were improved by 1.0 percentage points and 2.94 percentage points,respectively.Specifically,the rank-1 accuracies were outperformed by 0.86 percentage points and 0.12 percentage points,respectively,compared with the convolution block attention module(CBAM)and efficient channel attention(ECA)modules,although 0.94 percentage points were lower than that of squeeze-and-excitation(SE)modules.The mAP metric values were exceeded by 0.22,0.86 and 0.12 percentage points,respectively,compared with the SE,CBAM,and ECA modules.Additionally,the Cross-Entropy Loss function was replaced with the CosFace Loss function in the global branch of baseline model.CosFace Loss and Hard Triplet Loss were jointly employed to train the baseline model for the better identification on the similar individuals.AlignedReID++with CosFace Loss was outperformed the baseline model by 0.24 and 0.92 percentage points in the rank-1 accuracy and mAP,respectively,whereas,AlignedReID++with ArcFace Loss was exceeded by 0.36 and 0.56 percentage points,respectively.The improved model with the TA modules and CosFace Loss was achieved in a rank-1 accuracy of 94.42%,rank-5 accuracy of 98.78%,rank-10 accuracy of 99.34%,mAP of 63.90%,FLOPs of 5.45 G,frames per second(FPS)of 5.64,and model size of 23.78 M.The rank-1 accuracies were exceeded by 1.84,4.72,0.76 and 5.36 percentage points,respectively,compared with the baseline model,part-based convolutional baseline(PCB),multiple granularity network(MGN),and relation-aware global attention(RGA),while the mAP metrics were surpassed 6.42,5.86,4.30 and 7.38 percentage points,respectively.Meanwhile,the rank-1 accuracy was 0.98 percentage points lower than TransReID,but the mAP metric was exceeded by 3.90 percentage points.Moreover,the FLOPs of improved model were only 0.05 G larger than that of baseline model,while smaller than those of PCB,MGN,RGA,and TransReID by 0.68,6.51,25.4,and 16.55 G,respectively.The model size of improved model was 23.78 M,which was smaller than those of the baseline model,PCB,MGN,RGA,and TransReID by 0.03,2.33,45.06,14.53 and 62.85 M,respectively.The inference speed of improved model on a CPU was lower than those of PCB,MGN,and baseline model,but higher than TransReID and RGA.The t-SNE feature embedding visualization demonstrated that the global and local features were achieve in the better intra-class compactness and inter-class variability.Therefore,the improved model can be expected to effectively re-identify the beef cattle in natural environments of breeding farm,in order to monitor the individual feed intake and feeding time.展开更多
The aim of this study was to study the distribution of Selenium （Se） and Mercury （Hg） in feed and drinking water in Heilongjiang Province and the effect on body of beef cattle. The experiment selected four areas o...The aim of this study was to study the distribution of Selenium （Se） and Mercury （Hg） in feed and drinking water in Heilongjiang Province and the effect on body of beef cattle. The experiment selected four areas of Qiqihar, Harbin, Jixi and Hegang Cities in Heilongjiang Province. In each area, a pasture was selected. Five beef cattle from each ranch were collected. At the same time, blood, liver, muscle, kidney, urine and faece of the cattle were collected, as well as drinking water, feed and formula feed from the ranch. The contents of Se and Hg in the collected samples were detected by inductively coupled plasma mass spectrometry. The results showed that the contents of Se in liver, kidney, urine and blood of beef cattle were increased with the increase of Se contents in drinking water, while the contents of Se in muscle tissue and manure were decreased. When the contents of Se in feed increased, the contents of them in muscle, manure and liver of beef cattle were increased frst and then decreased, while the contents of Se in kidney, urine and blood were decreased frst and then increased. When Hg contents in drinking water were increased, the contents of them in beef cattle tissue, blood and manure were increased frst and then decreased, and the contents of Se in urine were increased frst and them decreased. And when Hg contents in feed increased, the contents of Se and Me were also increased. In conclusion, Se and Hg contents in these areas were within the safety standards, meanwhile, the contents of Se and Hg in body tissues of beef cattle were affected to varying degrees by the contents of selenium and mercury in feed.展开更多
In this study,the effects of two types of premixed materials with different combinations of trace elements on the production performance and antioxidant capacity of simmental beef cattle were examined.Fifteen healthy ...In this study,the effects of two types of premixed materials with different combinations of trace elements on the production performance and antioxidant capacity of simmental beef cattle were examined.Fifteen healthy simmental beef cattle of similar weight(approximately 330 kg),the same age(12 months),without castration,and a good physique were divided into three groups,with five beef cattle in each group.Food of Group Ⅰ beef cattle was supplemented with a commercially marketed 5% compound trace element premixture for fine beef cattle.Food of Group Ⅱ beef cattle was supplemented with a 5% compound microelement premixture for beef cattle that was designed to address local nutrient deficiencies and surpluses.In the blank control group,the beef cattle were not fed a premixture.The pretest period was 15 days,and the test period was divided into prefattening(45 days)and postfattening(45 days)stages.Body weight and body size indices were recorded at 1,2 and 3 months,and blood samples were collected regularly.In Group Ⅰ,the daily weight gain increased significantly by 15.7% compared with that of the control group.The largest daily weight gain was in Group Ⅱ,which increased by 31.6% compared with that in the control.During the test period of 90 days,the body size indices of the three different groups increased in different months,with significant increases in the indices for both test groups compared with those of the control.In Group Ⅰ,the activity of CP,the total activity of SOD and Cu-Zn-SOD increased significantly(p<0.05)compared with those in the control group,with a highly significant increase observed in GSH-PX activity(p<0.01).In Group Ⅱ,the increases in the activity of CP and the total activity of SOD and Cu-Zn-SOD were highly significant compared with those in the control group(p<0.01).In addition,a significant increase was observed in GSH-PX activity(p<0.05).Based on pretest results,the concentrations of Cu,Zn,Mo,Mn,Se and Co in the blood of experimental beef cattle were lower than those of the normal range.After feeding for 90 days,the concentrations of Cu,Zn,Mo,Mn,Se and Co in the blood of Groups Ⅰ and Ⅱ were significantly higher than those in the control group(p<0.05).The concentrations of elements in the blood of Group Ⅱ were close to the appropriate levels.Thus,the effects of the specifically designed compound microelement premixture on the prevention of nutrient imbalances and control of beef cattle nutrition metabolism and the production of fattened beef cattle were significant.展开更多
基金National Key Research and Development Program(2023YFD1301801)National Natural Science Foundation of China(32272931)+1 种基金Shaanxi Province Agricultural Key Core Technology Project(2024NYGG005)Shaanxi Province Key R&D Program(2024NC-ZDCYL-05-12)。
文摘Accurate and continuous identification of individual cattle is crucial to precision farming in recent years.It is also the prerequisite to monitor the individual feed intake and feeding time of beef cattle at medium to long distances over different cameras.However,beef cattle can tend to frequently move and change their feeding position during feeding.Furthermore,the great variations in their head direction and complex environments(light,occlusion,and background)can also lead to some difficulties in the recognition,particularly for the bio-similarities among individual cattle.Among them,AlignedReID++model is characterized by both global and local information for image matching.In particular,the dynamically matching local information(DMLI)algorithm has been introduced into the local branch to automatically align the horizontal local information.In this research,the AlignedReID++model was utilized and improved to achieve the better performance in cattle re-identification(ReID).Initially,triplet attention(TA)modules were integrated into the BottleNecks of ResNet50 Backbone.The feature extraction was then enhanced through cross-dimensional interactions with the minimal computational overhead.Since the TA modules in AlignedReID++baseline model increased the model size and floating point operations(FLOPs)by 0.005 M and 0.05 G,the rank-1 accuracy and mean average precision(mAP)were improved by 1.0 percentage points and 2.94 percentage points,respectively.Specifically,the rank-1 accuracies were outperformed by 0.86 percentage points and 0.12 percentage points,respectively,compared with the convolution block attention module(CBAM)and efficient channel attention(ECA)modules,although 0.94 percentage points were lower than that of squeeze-and-excitation(SE)modules.The mAP metric values were exceeded by 0.22,0.86 and 0.12 percentage points,respectively,compared with the SE,CBAM,and ECA modules.Additionally,the Cross-Entropy Loss function was replaced with the CosFace Loss function in the global branch of baseline model.CosFace Loss and Hard Triplet Loss were jointly employed to train the baseline model for the better identification on the similar individuals.AlignedReID++with CosFace Loss was outperformed the baseline model by 0.24 and 0.92 percentage points in the rank-1 accuracy and mAP,respectively,whereas,AlignedReID++with ArcFace Loss was exceeded by 0.36 and 0.56 percentage points,respectively.The improved model with the TA modules and CosFace Loss was achieved in a rank-1 accuracy of 94.42%,rank-5 accuracy of 98.78%,rank-10 accuracy of 99.34%,mAP of 63.90%,FLOPs of 5.45 G,frames per second(FPS)of 5.64,and model size of 23.78 M.The rank-1 accuracies were exceeded by 1.84,4.72,0.76 and 5.36 percentage points,respectively,compared with the baseline model,part-based convolutional baseline(PCB),multiple granularity network(MGN),and relation-aware global attention(RGA),while the mAP metrics were surpassed 6.42,5.86,4.30 and 7.38 percentage points,respectively.Meanwhile,the rank-1 accuracy was 0.98 percentage points lower than TransReID,but the mAP metric was exceeded by 3.90 percentage points.Moreover,the FLOPs of improved model were only 0.05 G larger than that of baseline model,while smaller than those of PCB,MGN,RGA,and TransReID by 0.68,6.51,25.4,and 16.55 G,respectively.The model size of improved model was 23.78 M,which was smaller than those of the baseline model,PCB,MGN,RGA,and TransReID by 0.03,2.33,45.06,14.53 and 62.85 M,respectively.The inference speed of improved model on a CPU was lower than those of PCB,MGN,and baseline model,but higher than TransReID and RGA.The t-SNE feature embedding visualization demonstrated that the global and local features were achieve in the better intra-class compactness and inter-class variability.Therefore,the improved model can be expected to effectively re-identify the beef cattle in natural environments of breeding farm,in order to monitor the individual feed intake and feeding time.
基金Supported by"Beef Cattle Safety Production Technology Innovation Integration and Demonstration"(2014BAD13B03-1)from the National Science and Technology Support Program"Beef Safety Production Technology Integration and Demonstration"
文摘The aim of this study was to study the distribution of Selenium （Se） and Mercury （Hg） in feed and drinking water in Heilongjiang Province and the effect on body of beef cattle. The experiment selected four areas of Qiqihar, Harbin, Jixi and Hegang Cities in Heilongjiang Province. In each area, a pasture was selected. Five beef cattle from each ranch were collected. At the same time, blood, liver, muscle, kidney, urine and faece of the cattle were collected, as well as drinking water, feed and formula feed from the ranch. The contents of Se and Hg in the collected samples were detected by inductively coupled plasma mass spectrometry. The results showed that the contents of Se in liver, kidney, urine and blood of beef cattle were increased with the increase of Se contents in drinking water, while the contents of Se in muscle tissue and manure were decreased. When the contents of Se in feed increased, the contents of them in muscle, manure and liver of beef cattle were increased frst and then decreased, while the contents of Se in kidney, urine and blood were decreased frst and then increased. When Hg contents in drinking water were increased, the contents of them in beef cattle tissue, blood and manure were increased frst and then decreased, and the contents of Se in urine were increased frst and them decreased. And when Hg contents in feed increased, the contents of Se and Me were also increased. In conclusion, Se and Hg contents in these areas were within the safety standards, meanwhile, the contents of Se and Hg in body tissues of beef cattle were affected to varying degrees by the contents of selenium and mercury in feed.
基金Supported by the National Science and Technology Support Program Project(2011BAD47B04)
文摘In this study,the effects of two types of premixed materials with different combinations of trace elements on the production performance and antioxidant capacity of simmental beef cattle were examined.Fifteen healthy simmental beef cattle of similar weight(approximately 330 kg),the same age(12 months),without castration,and a good physique were divided into three groups,with five beef cattle in each group.Food of Group Ⅰ beef cattle was supplemented with a commercially marketed 5% compound trace element premixture for fine beef cattle.Food of Group Ⅱ beef cattle was supplemented with a 5% compound microelement premixture for beef cattle that was designed to address local nutrient deficiencies and surpluses.In the blank control group,the beef cattle were not fed a premixture.The pretest period was 15 days,and the test period was divided into prefattening(45 days)and postfattening(45 days)stages.Body weight and body size indices were recorded at 1,2 and 3 months,and blood samples were collected regularly.In Group Ⅰ,the daily weight gain increased significantly by 15.7% compared with that of the control group.The largest daily weight gain was in Group Ⅱ,which increased by 31.6% compared with that in the control.During the test period of 90 days,the body size indices of the three different groups increased in different months,with significant increases in the indices for both test groups compared with those of the control.In Group Ⅰ,the activity of CP,the total activity of SOD and Cu-Zn-SOD increased significantly(p<0.05)compared with those in the control group,with a highly significant increase observed in GSH-PX activity(p<0.01).In Group Ⅱ,the increases in the activity of CP and the total activity of SOD and Cu-Zn-SOD were highly significant compared with those in the control group(p<0.01).In addition,a significant increase was observed in GSH-PX activity(p<0.05).Based on pretest results,the concentrations of Cu,Zn,Mo,Mn,Se and Co in the blood of experimental beef cattle were lower than those of the normal range.After feeding for 90 days,the concentrations of Cu,Zn,Mo,Mn,Se and Co in the blood of Groups Ⅰ and Ⅱ were significantly higher than those in the control group(p<0.05).The concentrations of elements in the blood of Group Ⅱ were close to the appropriate levels.Thus,the effects of the specifically designed compound microelement premixture on the prevention of nutrient imbalances and control of beef cattle nutrition metabolism and the production of fattened beef cattle were significant.
