Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments.

Ensuring precise calving time prediction necessitates the adoption of an automatic and precisely accurate cattle tracking system. Nowadays, cattle tracking can be challenging due to the complexity of their environment and the potential for missed or false detections. Most existing deep-learning tracking algorithms face challenges when dealing with track-ID switch cases caused by cattle occlusion. To address these concerns, the proposed research endeavors to create an automatic cattle detection and tracking system by leveraging the remarkable capabilities of Detectron2 while embedding tailored modifications to make it even more effective and efficient for a variety of applications. Additionally, the study conducts a comprehensive comparison of eight distinct deep-learning tracking algorithms, with the objective of identifying the most optimal algorithm for achieving precise and efficient individual cattle tracking. This research focuses on tackling occlusion conditions and track-ID increment cases for miss detection. Through a comparison of various tracking algorithms, we discovered that Detectron2, coupled with our customized tracking algorithm (CTA), achieves 99% in detecting and tracking individual cows for handling occlusion challenges. Our algorithm stands out by successfully overcoming the challenges of miss detection and occlusion problems, making it highly reliable even during extended periods in a crowded calving pen.

Cow detection and tracking system utilizing multi-feature tracking algorithm.

In modern cattle farm management systems, video-based monitoring has become important in analyzing the high-level behavior of cattle for monitoring their health and predicting calving for providing timely assistance. Conventionally, sensors have been used for detecting and tracking their activities. As the body-attached sensors cause stress, video cameras can be used as an alternative. However, identifying and tracking individual cattle can be difficult, especially for black and brown varieties that are so similar in appearance. Therefore, we propose a new method of using video cameras for recognizing cattle and tracking their whereabouts. In our approach, we applied a combination of deep learning and image processing techniques to build a robust system. The proposed system processes images in separate stages, namely data pre-processing, cow detection, and cow tracking. Cow detection is performed using a popular instance segmentation network. In the cow tracking stage, for successively associating each cow with the corresponding one in the next frame, we employed the following three features: cow location, appearance features, as well as recent features of the cow region. In doing so, we simply exploited the distance between two gravity center locations of the cow regions. As color and texture suitably define the appearance of an object, we analyze the most appropriate color space to extract color moment features and use a Co-occurrence Matrix (CM) for textural representation. Deep features are extracted from recent cow images using a Convolutional Neural Network (CNN features) and are also jointly applied in the tracking process to boost system performance. We also proposed a robust Multiple Object Tracking (MOT) algorithm for cow tracking by employing multiple features from the cow region. The experimental results proved that our proposed system could handle the problems of MOT and produce reliable performance.

Prediction of 24-h and 6-h Periods before Calving Using a Multimodal Tail-Attached Device Equipped with a Thermistor and 3-Axis Accelerometer through Supervised Machine Learning.

In this study, we developed calving prediction models for 24-h and 6-h periods before calving using data on physiological (tail skin temperature) and behavioral (activity intensity, lying time, posture change, and tail raising) parameters obtained using a multimodal tail-attached device (tail sensor). The efficiencies of the models were validated under tethering (tie-stall) and untethering (free-stall and individual pen) conditions. Data were collected from 33 and 30 pregnant cattle under tethering and untethering conditions, respectively, from approximately 15 days before the expected calving date. Based on pre-calving changes, 40 features (8 physiological and 32 behavioral) were extracted from the sensor data, and one non-sensor-based feature (days to the expected calving date) was added to develop models using a support vector machine. Cross-validation showed that calving within the next 24 h under tethering and untethering conditions was predicted with a sensitivity of 97% and 93% and precision of 80% and 76%, respectively, while calving within the next 6 h was predicted with a sensitivity of 91% and 90% and precision of 88% and 90%, respectively. Calving prediction models based on the tail sensor data with supervised machine learning have the potential to achieve effective calving prediction, irrespective of the cattle housing conditions.

Theileria-free grazing of dairy heifers on grassland in Kyushu, Japan where T. orientalis was epidemic before a 7-year vacancy.

This study aimed to produce a Theileria-free grazing system for Holstein heifers reared on a dairy farm in the Hita area, Kyushu, Japan. In the grazing area, spreading of T. orientalis infection was confirmed in 2009. To eradicate the T. orientalis infection, four measures were conducted: 1) 7-year deferred grazing; 2) grazing only T. orientalis-uninfected heifers; 3) anemia check by red blood cell parameters at least once per month; and 4) protecting heifers from blood-sucking T. orientalis-infected ticks. Grazing was restarted in 2017 in the same area and continued to 2021. During last 2 years of pasturing (2020-2021) all of the 129 heifers were confirmed to be T. orientalis-free. In summary, it is possible to establish a T. orientalis-free grazing system by conducting appropriate measures.

Effects of Theileria orientalis Infection on Health Status and Productivity of Dairy Cows Reared inside Barns.

The objective of the present study was to investigate the effects of Theileria orientalis on the severity of anemia, the prevalence of disease within 21 days after calving and productivity in cows raised inside barns. This longitudinal observational study, which was conducted on a commercial dairy farm in Japan, involved 627 Holstein cows subjected to PCR analysis for T. orientalis. In study 1, we collected blood samples from 156 sick cows within 21 days after calving, and we found the prevalence of T. orientalis infection to be 65.4%. In study 2, we randomly selected 471 cows during the dry period and collected blood samples to conduct PCR analysis for T. orientalis and determined the prevalence of T. orientalis infection to be 69.0%. Compared with the values for the T. orientalis-uninfected group, the T. orientalis-infected cows had significantly decreased hemoglobin concentrations and hematocrit, but there were no differences in the other complete blood count indexes between the two groups. In addition, there were no differences in productivity and the prevalence of major diseases between the T. orientalis-infected and uninfected cows. In summary, T. orientalis had few effects on anemia, productivity and the health of cows raised inside a barn.

A large-scale survey of Theileria orientalis infection in grazing dairy heifers in Kyushu, Japan.

The objective of the present study was to investigate the prevalence of Theileria orientalis infection and the influence of this disease on dairy grazing heifers in Kyushu by monitoring red blood cell (RBC) indexes, and to evaluate the efficacy of diminazene diaceturate treatment of T. orientalis-infected animals. A monthly epidemiological survey was conducted for Holstein heifers, which were reared from 10 to 16 months of age on a large commercial dairy farm and grazed on eight independent grasslands from April to November, 2009. During the survey, a total of 2,803 blood samples were collected from the 891 grazing heifers, in which the prevalence of T. orientalis infection was 52.4%. Compared with the heifers before infection, heifers with high parasitemia (more than 100 parasites per 104 RBC) had significantly decreased RBC indexes, such as RBC count, hemoglobin concentration, and hematocrit (P<0.05), whereas heifers with low parasitemia (less than 100 parasites per 104 RBC) had similar RBC indexes as those before infection. Treatment with diminazene diaceturate had lower efficacy in heifers with high parasitemia than those with low parasitemia (40.7% and 73.2% became negative, respectively, P<0.05). In summary, T. orientalis infection is a potentially serious problem in Kyushu, and it is important to routinely implement control programs for heifers that are grazed on grasslands in this region.

Epidemiological study to investigate the incidence and prevalence of clinical mastitis, peracute mastitis, metabolic disorders and peripartum disorders, on a dairy farm in a temperate zone in Japan.

BACKGROUND: Our aim was to investigate the incidence and prevalence of clinical mastitis, peracute mastitis, metabolic disorders, and peripartum disorders, and to examine factors affecting the prevalence of each disease in cows raised on a large dairy farm in a temperate climate in Japan. The present study was performed on a large commercial dairy farm with approximately 2500 Holstein cows. Data were collected from 2014 to 2018, and involved 9663 calving records for 4256 cows. RESULTS: The incidence rate on the farm was 21.9% for clinical mastitis, 10.4% for peracute mastitis, 2.9% for metabolic disorders, and 3.2% for peripartum disorders. The prevalence rates for clinical mastitis, peracute mastitis, metabolic disorders, and peripartum disorders were 28.0, 13.3, 3.7, and 4.0%, respectively. In all four diseases, the probability of time to occurrence for each disease was associated with parity and calving season (P < 0.05). Regarding metabolic disorders and peripartum disorders, the probability of occurrence decreased during the first 10 days after calving. CONCLUSIONS: Our results showed that clinical mastitis occurred most often in this temperate zone, and that metabolic disorders and peripartum disorders occurred from calving to day 10 post-calving.

Technical note: Calving prediction in dairy cattle based on continuous measurements of ventral tail base skin temperature using supervised machine learning.

In this study, we developed a calving prediction model based on continuous measurements of ventral tail base skin temperature (ST) with supervised machine learning and evaluated the predictive ability of the model in 2 dairy farms with distinct cattle management practices. The ST data were collected at 2- or 10-min intervals from 105 and 33 pregnant cattle (mean ± standard deviation: 2.2 ± 1.8 parities) reared in farms A (freestall barn, in a temperate climate) and B (tiestall barn, in a subarctic climate), respectively. After extracting maximum hourly ST, the change in values was expressed as residual ST (rST = actual hourly ST - mean ST for the same hour on the previous 3 d) and analyzed. In both farms, rST decreased in a biphasic manner before calving. Briefly, an ambient temperature-independent gradual decrease occurred from around 36 to 16 h before calving, and an ambient temperature-dependent sharp decrease occurred from around 6 h before until calving. To make a universal calving prediction model, training data were prepared from pregnant cattle under different ambient temperatures (10 data sets were randomly selected from each of the 3 ambient temperature groups: <15°C, ≥15°C to <25°C, and ≥25°C in farm A). An hourly calving prediction model was then constructed with the training data by support vector machine based on 15 features extracted from sensing data (indicative of pre-calving rST changes) and 1 feature from non-sensor-based data (days to expected calving date). When the prediction model was applied to the data that were not part of the training process, calving within the next 24 h was predicted with sensitivities and precisions of 85.3% and 71.9% in farm A (n = 75), and 81.8% and 67.5% in farm B (n = 33), respectively. No differences were observed in means and variances of intervals from the calving alerts to actual calving between farms (12.7 ± 5.8 and 13.0 ± 5.6 h in farms A and B, respectively). Above all, a calving prediction model based on continuous measurement of ST with supervised machine learning has the potential to achieve effective calving prediction, irrespective of the rearing condition in dairy cattle.

Exploration of factors determining milk production by Holstein cows raised on a dairy farm in a temperate climate area.

In this study, we examined factors that affected milk production by cows raised in a temperate climate area. We conducted this study on a large dairy farm containing approximately 2000 Holstein cows, located in a temperate climate area. We collected 7803 calving records for 4069 cows from 2012 to 2016. We then assessed the effect of hot weather on milk yield by examining three climate factors: season, maximum temperature (MAX), and the temperature and humidity index (THI). We found that increases in heat stress caused linear decreases in milk yield (P < 0.05). Additionally, the effects of the three climate factors on milk yield varied depending on cow parity and days open (P < 0.05). Thus, management procedures should consider cow parity and lactating stage to minimize the negative effects of heat stress on milk production. We also found that the lowest Akaike information criterion value was obtained in our model when using THI for 305-day milk yield. This suggests that THI is a more accurate variable for evaluating heat stress than MAX or season.

Cattle with the BoLA class II DRB3*0902 allele have significantly lower bovine leukemia proviral loads.

The bovine MHC (BoLA) class II DRB3 alleles are associated with polyclonal expansion of lymphocytes caused by bovine leukemia virus (BLV) infection in cattle. To examine whether the DRB3*0902 allele, one of the resistance-associated alleles, is associated with the proviral load, we measured BLV proviral load of BLV-infected cattle and clarified their DRB3 alleles. Fifty-seven animals with DRB3*0902 were identified out of 835 BLV-infected cattle and had significantly lower proviral load (P<0.000001) compared with the rest of the infected animals, in both Japanese Black and Holstein cattle. This result strongly indicates that the BoLA class II DRA/DRB3*0902 molecule plays an important immunological role in suppressing viral replication, resulting in resistance to the disease progression.

Evaluation of the natural perinatal transmission of bovine leukaemia virus.

The perinatal transmission of bovine leukaemia virus (BLV) plays a critical role in the spread and persistence of BLV infection in cattle herds. The purpose of this study was to examine the frequency of perinatal infections in an area in Japan and investigate some risk factors associated with infection. Altogether, 129 calves born to BLV-infected cows in a herd in Japan were tested for infection immediately after birth and again at one month of age using nested PCR. Twenty-four calves (18.6 per cent) were infected with BLV, of which 14 (10.8 per cent) and 10 (7.7 per cent) calves were infected via the transplacental and the birth canal routes, respectively. Maternal viral loads, breed, the presence or absence of assistance during parturition and the number of births per dam were evaluated to investigate risk factors associated with infection. Maternal viral load was significantly correlated with the frequency of perinatal infection, and more than 40 per cent of newborn calves born to dams with high viral loads were infected with BLV. The results of this study could contribute towards developing effective eradication programmes by providing necessary data for replacement of breeding cow in the field.

Serum paraoxonase-1 as biomarker for improved diagnosis of fatty liver in dairy cows.

BACKGROUND: Fatty liver is a major metabolic disorder in dairy cows and is believed to result in major economic losses in dairy farming due to decreased health status, reproductive performance and fertility. Currently, the definitive means for diagnosing fatty liver is determining the fat content of hepatic tissue by liver biopsy, which is an invasive and costly procedure, making it poorly suited to dairy farms. Therefore, the key aim of this study was to investigate the measurement of serum paraoxonase-1 (PON1), an enzyme exclusively synthesized by the liver, as a sensitive noninvasive biomarker for diagnosis of fatty liver in dairy cows. RESULTS: A comparative cohort study using serum specimens from Holstein-Friesian dairy cows (46 healthy and 46 fatty liver cases) was conducted. Serum PON1 (paraoxonase, lactonase and arylesterase) activity and other biochemical and hematological parameters were measured. We found that serum PON1 activity was lower (P<0.001) in cows suffering from fatty liver. The area under the receiver operating characteristic curve (AUC-ROC) of PON1 activity for diagnosis of fatty liver was 0.973-0.989 [95% confidence interval (CI) 0.941, 1.000] which was higher than the AUC-ROC of aspartate aminotransferase (AST), lecithin-cholesterol acyltransferase (LCAT), alkaline phosphatase (ALP), non-esterified fatty acids (NEFA), beta-hydroxybutyrate (BHBA), total cholesterol, high-density lipoprotein (HDL) and low-density lipoprotein (LDL). We found that adding serum PON1 measurement to different batteries of serum diagnostic panels showed a combination of high sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (+LR), negative likelihood ratio (-LR), diagnostic odd ratio (DOR) and overall diagnostic accuracy in diagnosing fatty liver. CONCLUSIONS: The present results indicate that addition of serum PON1 activity measurement to the biochemical profile could improve the diagnosis of fatty liver in dairy cows, which would have a considerable clinical impact and lead to greater profitability in the dairy industry.