Automated Cow Body Condition Scoring Using Multiple 3D Cameras and Convolutional Neural Networks.

Body condition scoring is an objective scoring method used to evaluate the health of a cow by determining the amount of subcutaneous fat in a cow. Automated body condition scoring is becoming vital to large commercial dairy farms as it helps farmers score their cows more often and more consistently compared to manual scoring. A common approach to automated body condition scoring is to utilise a CNN-based model trained with data from a depth camera. The approaches presented in this paper make use of three depth cameras placed at different positions near the rear of a cow to train three independent CNNs. Ensemble modelling is used to combine the estimations of the three individual CNN models. The paper aims to test the performance impact of using ensemble modelling with the data from three separate depth cameras. The paper also looks at which of these three cameras and combinations thereof provide a good balance between computational cost and performance. The results of this study show that utilising the data from three depth cameras to train three separate models merged through ensemble modelling yields significantly improved automated body condition scoring accuracy compared to a single-depth camera and CNN model approach. This paper also explored the real-world performance of these models on embedded platforms by comparing the computational cost to the performance of the various models.

Relation of Automated Body Condition Scoring System and Inline Biomarkers (Milk Yield, ß-Hydroxybutyrate, Lactate Dehydrogenase and Progesterone in Milk) with Cow's Pregnancy Success.

The aim of the current study was to evaluate the relation of automatically determined body condition score (BCS) and inline biomarkers such as ß-hydroxybutyrate (BHB), milk yield (MY), lactate dehydrogenase (LDH), and progesterone (mP4) with the pregnancy success of cows. The cows (n = 281) had 2.1 ± 0.1. lactations on average, were 151.6 ± 0.06 days postpartum, and were once tested with "Easy scan" ultrasound (IMV imaging, Scotland) at 30-35 d post-insemination. According to their reproductive status, cows were grouped into two groups: non-pregnant (n = 194 or 69.0% of cows) and pregnant (n = 87 or 31.0% of cows). Data concerning their BCS, mP4, MY, BHB, and LDH were collected each day from the day of insemination for 7 days. The BCS was collected with body condition score camera (DeLaval Inc., Tumba, Sweden); mP4, MY, BHB, and LDH were collected with the fully automated real-time analyzer Herd Navigator™ (Lattec I/S, Hillerød, Denmark) in combination with a DeLaval milking robot (DeLaval Inc., Tumba, Sweden). Of all the biomarkers, three differences between groups were significant. The body condition score (BCS) of the pregnant cows was higher (+0.49 score), the milk yield (MY) was lower (-4.36 kg), and milk progesterone in pregnant cows was (+6.11 ng/mL) higher compared to the group of non-pregnant cows (p < 0.001). The pregnancy status of the cows was associated with their BCS assessment (p < 0.001). We estimated that cows with BCS > 3.2 were 22 times more likely to have reproductive success than cows with BCS ≤ 3.2.

Validation and utility of a body condition scoring system for chimpanzees (Pan troglodytes).

Obesity is a problem in captive chimpanzee colonies that can lead to increased risk for disease; therefore, implementation of effective weight management strategies is imperative. To properly implement a weight management program, captive managers should be able to noninvasively identify and assess overweight or obese individuals. Traditional means of categorizing obese individuals involve sedating the animals to obtain body weights or skin fold measurements. The current study aimed to validate a noninvasive, subjective body condition score (BCS) system for captive chimpanzees. The system utilizes a 10-point scale, with one rated as "emaciated," five as "normal," and 10 as "extremely obese." Between 2013 and 2014, 158 chimpanzees were weighed and scored using this system (a) while sedated and (b) while awake in their social group within 1-3 days of sedation ("In-group" ratings). We found high inter-rater reliability between In-group raters, as well as between sedated and In-group scores. BCSs, which require observation only, were significantly positively correlated with weight (an objective measure of obesity often requiring anesthetization), supporting the scale's validity. The BCS system identified 36 individuals as "overweight," while the use of weights alone identified only 26 individuals as "overweight." Furthermore, the BCS system was able to classify individuals of the same sex and weight as having different BCSs, ranging from normal to overweight. Lastly, using focal animal behavioral observations from 2016 to 2018 (N = 120), we found that In-group BCS predicted individual levels of inactive behavior more than 2 years later, demonstrating the predictive validity of the scale. These results illustrate the utility of the BCS system as a noninvasive, reliable, and valid technique that may be more sensitive than traditional methods in identifying and quantifying obesity in chimpanzees. This system can be a useful tool for captive managers to monitor and manage the weight of chimpanzees and other nonhuman primates.

A reliable scoring system after major liver resection in mice.

BACKGROUND: Posthepatectomy liver failure and its transplant counterpart, small-for-size syndrome, remain significant limitations for liver resections and segmental liver transplantation. Partial hepatectomy in mice is one of the most commonly used models to study liver regeneration, but blood and tissue sampling necessary to collect data can affect outcomes or even require euthanasia. We therefore developed a quantitative observational system to predict death from hepatectomy during the first 24 postoperative hours. MATERIALS AND METHODS: A total of 100 female, 10 to 12-week-old C57BL/6 mice underwent two-thirds hepatectomy and were monitored for up to 7 d. Our scoring system was based on five categories, each assigned 0-2 points: activity level, body posture, fur condition, respiratory status, and eye appearance. Seventy-five mice were scored 6 h, 12 h, 24 h, 2 d, 3 d, 5 d, and 7 d after surgery. The remaining 25 mice were scored similarly, but underwent, in addition, blood sampling for serum alanine aminotransferase, total bilirubin, interleukin-6, tumor necrosis factor-alpha, or euthanasia with liver sampling for conventional hematoxylin-eosin and Ki-67 staining. RESULTS: Retrospective analysis indicated that body condition scores ≤5 on two consecutive time points within the first 24 postoperative hours accurately predicted eventual death. Animals in the low scoring group also had significantly higher serum alanine aminotransferase, total bilirubin, interleukin-6, tumor necrosis factor-alpha, more hepatocyte necrosis in hematoxylin-eosin, and fewer Ki-67 positive hepatocytes. CONCLUSIONS: Our scoring system accurately predicts survival, hepatocyte damage, liver regeneration, and systemic inflammation in a mouse hepatectomy model, within the first 24 hours of surgery. This could be useful in evaluating posthepatectomy interventions for their effect on survival and liver regeneration.

Development of automatic body condition scoring using a low-cost 3-dimensional Kinect camera.

Body condition scoring (BCS) is a farm-management tool for estimating dairy cows' energy reserves. Today, BCS is performed manually by experts. This paper presents a 3-dimensional algorithm that provides a topographical understanding of the cow's body to estimate BCS. An automatic BCS system consisting of a Kinect camera (Microsoft Corp., Redmond, WA) triggered by a passive infrared motion detector was designed and implemented. Image processing and regression algorithms were developed and included the following steps: (1) image restoration, the removal of noise; (2) object recognition and separation, identification and separation of the cows; (3) movie and image selection, selection of movies and frames that include the relevant data; (4) image rotation, alignment of the cow parallel to the x-axis; and (5) image cropping and normalization, removal of irrelevant data, setting the image size to 150×200 pixels, and normalizing image values. All steps were performed automatically, including image selection and classification. Fourteen individual features per cow, derived from the cows' topography, were automatically extracted from the movies and from the farm's herd-management records. These features appear to be measurable in a commercial farm. Manual BCS was performed by a trained expert and compared with the output of the training set. A regression model was developed, correlating the features with the manual BCS references. Data were acquired for 4 d, resulting in a database of 422 movies of 101 cows. Movies containing cows' back ends were automatically selected (389 movies). The data were divided into a training set of 81 cows and a test set of 20 cows; both sets included the identical full range of BCS classes. Accuracy tests gave a mean absolute error of 0.26, median absolute error of 0.19, and coefficient of determination of 0.75, with 100% correct classification within 1 step and 91% correct classification within a half step for BCS classes. Results indicated good repeatability, with all standard deviations under 0.33. The algorithm is independent of the background and requires 10 cows for training with approximately 30 movies of 4 s each.

Development and validation of a visual body condition scoring system for dairy goats with picture-based training.

Body condition scoring (BCS) is the most widely used method to assess changes in body fat reserves, which reflects its high potential to be included in on-farm welfare assessment protocols. Currently used scoring systems in dairy goats require animal restraint for body palpation. In this study, the Animal Welfare Indicators project (AWIN) proposes to overcome this constraint by developing a scoring system based only on visual assessment. The AWIN visual body condition scoring system highlights representative animals from 3 categories: very thin, normal, and very fat, and was built from data sets with photographs of animals scored by a commonly used 6-point scoring system that requires palpation in 2 anatomical regions. Development of the AWIN scoring system required 3 steps: (1) identification and validation of a body region of interest; (2) sketching the region from photographs; and (3) creation of training material. The scoring system's reliability was statistically confirmed. An initial study identified features in the rump region from which we could compute a set of body measurements (i.e., measures based on anatomical references of the rump region) that showed a strong correlation with the assigned BCS. To validate the result, we collected a final data set from 171 goats. To account for variability in animal size and camera position, we mapped a subset of features to a standard template and aligned all the rump images before computing the body measurements. Scientific illustrations were created from the aligned images of animals identified as representative of each category to increase clarity and reproducibility. For training material, we created sketches representing the threshold between consecutive categories. Finally, we conducted 2 field reliability studies. In the first test, no training was given to 4 observers, whereas in the second, training using the threshold images was delivered to the same observers. In the first experiment, interobserver results was substantial, showing that the visual scoring system is clear and unambiguous. Moreover, results improved after training, reaching almost perfect agreement for the very fat category. The visual body condition scoring system is not only a practical tool for BCS in dairy goats but also shows potential to be fully automated, which would enhance its use in welfare assessment schemes and farm management.

Comparison of manual and automated body condition scoring of commercial dairy cattle.

BACKGROUND: Body condition scoring of dairy cows estimates their body reserves. Automation allows increased data availability and reduced labour costs. The aim of this study was to compare an automated (AUT) body condition score (BCS) system to manual observers on a single commercial dairy farm in south-west England. METHODS: Three practising veterinary surgeons performed body condition scoring of 315 dairy cows using the agriculture and horticulture development board (AHDB) Body Condition Scorecard. AUT BCSs were obtained from two 3D cameras and compared to the BCSs recorded by the three operators. RESULTS: The AUT system only agreed with manual scorers at a BCS of 3. The system failed to detect cows classified as underconditioned (BCS ≤ 2.25) by any of the operators (sensitivity 0%). It also systematically underestimated the BCS of cows classified as overconditioned (BCS ≥ 3.5) by the operators. For overconditioned cows, the sensitivity of the AUT system ranged from 30.7% to 48.8% when compared with the manual operators. The AUT system also had weaker agreement with operators for Jersey cows, with Cohen's weighted kappa values of 0.28 for Jersey animals and 0.40 for Holsteins. LIMITATIONS: This study used a convenience sample of animals on a single farm at a single time point, so the extent to which the findings can be more widely generalised is unclear. CONCLUSIONS: The AUT system failed to detect animals classified as underconditioned by the operators and underestimated the condition of cows classified as overconditioned by the operators. Currently, without improvements to the algorithm, the clinical usefulness of such an AUT system for body condition scoring is limited.

Development of an automatic cow body condition scoring using body shape signature and Fourier descriptors.

Body condition evaluation is a common tool to assess energy reserves of dairy cows and to estimate their fatness or thinness. This study presents a computer-vision tool that automatically estimates cow's body condition score. Top-view images of 151 cows were collected on an Israeli research dairy farm using a digital still camera located at the entrance to the milking parlor. The cow's tailhead area and its contour were segmented and extracted automatically. Two types of features of the tailhead contour were extracted: (1) the angles and distances between 5 anatomical points; and (2) the cow signature, which is a 1-dimensional vector of the Euclidean distances from each point in the normalized tailhead contour to the shape center. Two methods were applied to describe the cow's signature and to reduce its dimension: (1) partial least squares regression, and (2) Fourier descriptors of the cow signature. Three prediction models were compared with manual scores of an expert. Results indicate that (1) it is possible to automatically extract and predict body condition from color images without any manual interference; and (2) Fourier descriptors of the cow's signature result in improved performance (R(2)=0.77).

Reproducibility of the body condition score assessment in Silesian horses, using the 9-point BCS scale.

Control of body condition is an important aspect of horse management. Its correct evaluation, and the possibility of using universal indicators are of key importance for preserving the animals' wellbeing and for providing them with proper care. The objective of this study was to evaluate the agreement between body condition scores assessed by teams and individuals, using the 9-point Body Condition Score scale created by Henneke. The evaluation of a herd of 49 healthy adult Silesian horses was conducted by veterinary medicine students with adequate training in body condition assessment. Group assessments made by each of two teams and then assessments made by two individuals were compared to determine the repeatability of the results. While significant differences were found between the assessments made by the individuals, there were no significant differences between assessments made by the teams or between the individuals and the teams. The results are indicative of the method's repeatability.

Factors Affecting Weigh Tape Reading in the Measurement of Equine Body Weight.

Accurate measurement of equine body weight is important for evaluating medication dosages and feed quantities. Different methods exist for measuring body weight, including weigh tapes (WT), though accuracy varies. Measurements could be affected by external variables, such as time of day, human error, or uneven surfaces, and also horse-based variables, such as height and body condition score (BCS). The aim of this study was to investigate how different horse-based variables affect WT reading. A retrospective analysis was performed using anonymised data from feed company nutrition consultations (Baileys Horse Feeds). Data included a range of horse-based variables, a WT reading, and true body weight measured on a weighbridge. All horses were over two years of age. Likelihood ratio tests were used to assess whether adding different horse-based variables significantly improved the fit of the quadratic regression model. The variables included were height, BCS, breed, muscle top-line score, and bone type. Exploratory analysis showed that the WT generally underestimated body weight, particularly for horses with higher body weight. Adding height and muscle top-line scores did not significantly improve the fit of the model, suggesting no influence on WT reading over and above actual body weight. Adding breed groupings, BCS, and bone density did improve the fit. Each 0.5 unit increase in BCS increased the WT estimate by 1.24 kg (p < 0.001). These results confirm that a WT does not provide accurate body weight measurements, and generally underestimates body weight, though more so for heavier horses, being more accurate in pony breeds.

Rate of obesity within a mixed-breed group of horses in Ireland and their owners' perceptions of body condition and useability of an equine body condition scoring scale.

BACKGROUND: Equine obesity is a significant health and welfare concern. The proportion of domestic horse populations that are overweight are as high as 45%. As the primary decision-makers for their horses' care, owners are theoretically ideally placed to identify whether their horses are appropriately conditioned, however, research in other countries has shown that many owners are unable to accurately judge their horse's body condition. In this study, through the comparison of body condition scoring (BCS) performed by an expert and the horse owners and interviews with owners, we aimed to identify the proportion of horses that were overweight or obese, to assess the accuracy of horse owners' BCS assessment both prior to and after receiving information and instructions on body condition scoring, and to identify common themes amongst owners' views regarding BCS assessment and the Henneke BCS system. RESULTS: Forty-five percent of the horses in this study were overweight or obese. The agreement between the owners and an equine veterinarian regarding the horses' BCS was fair to good both prior to (κ = .311, P < 0.001; ICC = .502, P < 0.001) and after (κ = .381, P < 0.001; ICC = .561, P < 0.001) receiving information and instructions on scoring. Three quarters of the owners who took part in the study did not use any method of monitoring their horse's body condition. Thematic analysis of owner responses was varied, with the most common theme being an awareness of the need to monitor or make changes to their horse's condition with responses in this theme split between owners who felt in control and those who did not. Owner feedback on the utility and useability of the scorning system was that it was useful however parts are too technical or need improvement. CONCLUSIONS: Equine obesity is a significant problem in this population in Ireland. Horse owners' ability to accurately judge their horse's condition does not improve with provision of instructions on body condition scoring. These results combined with owners' feedback on the Henneke BCS system indicate that it is not a tool that can be reliably used by owners.

Monitoring of Body Condition in Dairy Cows to Assess Disease Risk at the Individual and Herd Level.

A retrospective longitudinal study assessing the explanatory and predictive capacity of body condition score (BCS) in dairy cows on disease risk at the individual and herd level was carried out. Data from two commercial grazing herds from the Argentinean Pampa were gathered (Herd A = 2100 and herd B = 2600 milking cows per year) for 4 years. Logistic models were used to assess the association of BCS indicators with the odds for anestrus at the cow and herd level. Population attributable fraction (AFP) was estimated to assess the anestrus rate due to BCS indicators. We found that anestrus risk decreased in cows calving with BCS ≥ 3 and losing ≤ 0.5 (OR: 0.07-0.41), and that anestrus rate decreased in cohorts with a high frequency of cows with proper BCS (OR: 0.22-0.45). Despite aggregated data having a good explanatory power, their predictive capacity for anestrus rate at the herd level is poor (AUC: 0.574-0.679). The AFP varied along the study in both herds and tended to decrease every time the anestrous rate peaked. We conclude that threshold-based models with BCS indicators as predictors are useful to understand disease risk (e.g., anestrus), but conversely, they are useless to predict such multicausal disease events at the herd level.

Parasitological survey to address major risk factors threatening alpacas in Andean extensive farms (Arequipa, Peru).

Extensive alpaca farming in the Colca Valley (Arequipa, Peru) is the most important resource for farmers who live in this remote area of the country. Grazing is the major available source of food, whereas forage production and supply are limited. Food availability is low during the dry season predisposing animals to parasitic diseases and reproduction failure. In this study, we looked into gaining an overview about flock health management and nutritional and parasitological status of different age groups in medium-large alpaca farms at the beginning of the dry season. A total of 20 herds were included in the survey and 288 fecal samples were collected and analyzed to determine prevalence and oocysts/eggs output level of the most common gastro-intestinal parasites that affect alpacas. Body condition scoring (BCS), was used to determine the nutritional status of sampled animals, belonging to different physiological classes (i.e. crias, tuis, lactating females, non-lactating females, males). Coccidiosis was the parasitic disease with the highest prevalence and output level. It was the most relevant parasitic disease in all classes and especially in young pre-breeding animals. Higher burdens were found in subjects with lower BCS. More specifically, the farms with higher cria mortality rates showed also a tendency to have higher prevalence values of Eimeria macusaniensis. An improved management of nutritional aspects and parasite control, in particular regarding the weaning phase, is expected to enhance the farming reproductive and productive performances of the alpacas in this region.

Non-Invasive Assessment of Body Condition and Stress-Related Fecal Glucocorticoid Metabolite Concentrations in African Elephants (Loxodonta africana) Roaming in Fynbos Vegetation.

Fynbos is a unique endemic vegetation type belonging to the Cape Floral Kingdom in the Western Cape Province of South Africa, representing the smallest of the six floral kingdoms in the world. Nowadays, only a few game reserves in this region support populations of African elephants (Loxodonta africana), and thus, little information exists regarding the suitability of the nutritionally poor Fynbos vegetation for these megaherbivores. Using already established non-invasive methods, the monitoring of individual body conditions and fecal glucocorticoid metabolite (fGCM) concentrations, as a measure of physiological stress, was performed to examine a herd of 13 elephants in a Western Cape Province Private Game Reserve, during two monitoring periods (April and June 2018), following a severe drought. The results indicate that overall median body condition scores (April and June: 3.0, range 2.0-3.0) and fGCM concentrations (April: 0.46 µg/g dry weight (DW), range 0.35-0.66 µg/g DW; June: 0.61 µg/g DW, range 0.22-1.06 µg/g DW) were comparable to those of other elephant populations previously studied utilizing the same techniques. These findings indicate that the individuals obtain sufficient nutrients from the surrounding Fynbos vegetation during the months monitored. However, a frequent assessment of body conditions and stress-associated fGCM concentrations in these animals would assist conservation management authorities and animal welfare practitioners in determining ways to manage this species in environments with comparably poorer nutritional vegetation.

A Study of Traveller Horse Owners' Attitudes to Horse Care and Welfare Using an Equine Body Condition Scoring System.

Traveller horses are often perceived to be exposed to poor welfare due to Travellers' traditional way of horsemanship. However, few studies have investigated Traveller horse welfare. Hence, the present study aims to explore Traveller horse owners' attitudes to horse care and welfare. Semi-structured interviews and discussion groups examined 14 Irish Traveller horse owners' attitudes and approach to horse ownership. Additionally, a body condition scoring (BCS) instrument was assessed for its accuracy and ease of use when applied by Traveller horse owners. Additionally, the BCS system was used to assess 18 horses. Results show that Travellers have a good understanding of horses' natural behaviours and environment, which is reflected in their management practices. However, barriers to improved welfare are land availability, since landowners are often reluctant to lease to Travellers, and the impoundment of horses as a consequence of fly grazing, under the Control of Horses Act 1996 (Ireland). Furthermore, Travellers regarded the BCS as a useful tool, but would require training to apply the scoring successfully. The results suggest that attitudes and management practices are favourable, but Travellers have limited means to overcome barriers. Therefore, it is necessary to increase capacity building and assist with the acquisition of land.

The effect of position on the precision of dual-energy X-ray absorptiometry and correlation with body condition score in dogs and cats.

Dual-energy X-ray absorptiometry (DEXA) has been used to assess body composition in dogs and cats in several studies, but studies are difficult to compare for several reasons. The aim of the present study was to evaluate whether positioning of dogs or cats in either dorsal or ventral recumbency during DEXA scanning influences results. Dogs and cats that were brought to the University Hospital for Companion Animals for euthanasia during the period 15 September-6 November 2015 were consecutively recruited if owners signed a written consent. Following euthanasia and before rigor mortis, the animals were body condition scored (BCS, nine-point scale) and DEXA scanned. DEXA measurements of total body mass (TBM), bone mineral content (BMC), bone mineral density (BMD), lean soft tissue mass (LSTM) and body fat (BF) were performed five times in ventral and two times in dorsal recumbency on each animal. Differences between positioning were analysed using Student's t test or Wilcoxon's test depending on normality of the data. A total of thirteen dogs and seven cats of different breeds, size, sexes and age were included. The CV for DEXA parameters in ventral or dorsal recumbency were, for dogs, TBM ≤ 0·1 %, BMC ≤ 1·63 %, BMD ≤ 1·29 %, LSTM ≤ 0·89 % and BF ≤ 1·52 %; and, for cats, TBM ≤ 0·08 %, BMC ≤ 0·61 %, BMD ≤ 0·49 %, LSTM ≤ 0·45 % and BF ≤ 0·88 %. In both positions, a good correlation was found for dogs (r 0·84-0·85; P < 0·0003) and cats (r 0·89-0·90; P < 0·0081) between the nine-point BCS system and BF percentage measured by DEXA. Ventral and dorsal recumbency provides comparable results, except that BMD measures were higher in dorsal recumbency (P < 0·0004).

In vitro culture of oocytes and granulosa cells collected from normal, obese, emaciated and metabolically stressed ewes.

The present study was undertaken to investigate the oocyte morphology, its fertilizing capacity and granulosa cell functions in ewes (obese, normal, metabolic stressed and emaciated). Ewes (Ovis aries) of approximately 3 years of age (Bellary breed) from a local village were screened, chosen and categorized into a) normal b) obese but not metabolically stressed, c) Emaciated but not metabolically stressed d) Metabolically stressed based on body condition scoring and blood markers. Oocytes and granulosa cells were collected from ovaries of the ewes of all categories after slaughter and were classified into good (oocytes with more than three layers of cumulus cells and homogenous ooplasm), fair (oocytes one or two layers of cumulus cells and homogenous ooplasm) and poor (denuded oocytes or with dark ooplasm). The good and fair quality oocytes were in vitro matured and cultured with fresh semen present and the fertilization, cleavage and blastocyst development were observed. The granulosa cells were cultured for evaluation of metabolic activity by use of the MTT assay, and cell viability, cell number as well as estrogen and progesterone production were assessed. It was observed that the good and fair quality oocytes had greater metabolic activity when collected from normal and obese ewes compared with those from emaciated and metabolically stressed ewes. No significant difference was observed in oocyte quality and maturation amongst the oocytes collected from normal and obese ewes. The cleavage and blastocyst production rates were different for the various body condition classifications and when ranked were: normal>obese>metabolically stressed>emaciated. Lesser metabolic activity was observed in granulosa cells obtained from ovaries of emaciated ewes. However, no changes were observed in viability and cell number of granulosa cells obtained from ewes with the different body condition categories. Estrogen and progesterone production from cultured granulosa cells were not different in normal and obese ewes. Estrogen and progesterone secretions were less from granulosa cells recovered from metabolically stressed and emaciated ewes. The results suggested that oocyte morphology, fertilizing capacity and granulosa cell growth were dependent on body condition and feeding status of the animals.

Camelid wellness.

Wellness management and environmental enrichment of New World camelids is multifaceted and should include everything from how they are fed and housed to how they are interacted with and handled. Camelid feeding regimens should be based on sound nutritional concepts, designed for specific animal groups, and begin with an appropriate forage base. Provide housing, shelter, substrate, and feeders designed for the needs and behaviors of camelids. Herd management should include regularly obtaining weights and body condition scores. Handling and training should be of a positive nature, in keeping with the natural history and temperament of the animal.