Search

Within the current process of large-scale dairy-cattle breeding, to address the problems of low recognition-accuracy and significant recognition-error associated with existing visual methods, we propose a method for recognizing the feeding behavior of dairy cows, one based on an improved RefineMask instance-segmentation model, and using high-quality detection and segmentation results to realize the recognition of the feeding behavior of dairy cows. Firstly, the input features are better extracted by incorporating the convolutional block attention module into the residual module of the feature extraction network. Secondly, an efficient channel attention module is incorporated into the neck design to achieve efficient integration of feature extraction while avoiding the surge of parameter volume computation. Subsequently, the GIoU loss function is used to increase the area of the prediction frame to optimize the convergence speed of the loss function, thus improving the regression accuracy. Finally, the logic of using mask information to recognize foraging behavior was designed, and the accurate recognition of foraging behavior was achieved according to the segmentation results of the model. We constructed, trained, and tested a cow dataset consisting of 1000 images from 50 different individual cows at peak feeding times. The method's effectiveness, robustness, and accuracy were verified by comparing it with example segmentation algorithms such as MSRCNN, Point_Rend, Cascade_Mask, and ConvNet_V2. The experimental results show that the accuracy of the improved RefineMask algorithm in recognizing the bounding box and accurately determining the segmentation mask is 98.3%, which is higher than that of the benchmark model by 0.7 percentage points; for this, the model parameter count size was 49.96 M, which meets the practical needs of local deployment. In addition, the technologies under study performed well in a variety of scenarios and adapted to various light environments; this research can provide technical support for the analysis of the relationship between cow feeding behavior and feed intake during peak feeding periods. [ABSTRACT FROM AUTHOR]

Behavior is one of the important factors reflecting the health status of dairy cows, and when dairy cows encounter health problems, they exhibit different behavioral characteristics. Therefore, identifying dairy cow behavior not only helps in assessing their physiological health and disease treatment but also improves cow welfare, which is very important for the development of animal husbandry. The method of relying on human eyes to observe the behavior of dairy cows has problems such as high labor costs, high labor intensity, and high fatigue rates. Therefore, it is necessary to explore more effective technical means to identify cow behaviors more quickly and accurately and improve the intelligence level of dairy cow farming. Automatic recognition of dairy cow behavior has become a key technology for diagnosing dairy cow diseases, improving farm economic benefits and reducing animal elimination rates. Recently, deep learning for automated dairy cow behavior identification has become a research focus. However, in complex farming environments, dairy cow behaviors are characterized by multiscale features due to large scenes and long data collection distances. Traditional behavior recognition models cannot accurately recognize similar behavior features of dairy cows, such as those with similar visual characteristics, i.e., standing and walking. The behavior recognition method based on 3D convolution solves the problem of small visual feature differences in behavior recognition. However, due to the large number of model parameters, long inference time, and simple data background, it cannot meet the demand for real-time recognition of dairy cow behaviors in complex breeding environments. To address this, we developed an effective yet lightweight model for fast and accurate dairy cow behavior feature learning from video data. We focused on four common behaviors: standing, walking, lying, and mounting. We recorded videos of dairy cow behaviors at a dairy farm containing over one hundred cows using surveillance cameras. A robust model was built using a complex background dataset. We proposed a two-pathway X3DFast model based on spatiotemporal behavior features. The X3D and fast pathways were laterally connected to integrate spatial and temporal features. The X3D pathway extracted spatial features. The fast pathway with R(2 + 1)D convolution decomposed spatiotemporal features and transferred effective spatial features to the X3D pathway. An action model further enhanced X3D spatial modeling. Experiments showed that X3DFast achieved 98.49% top-1 accuracy, outperforming similar methods in identifying the four behaviors. The method we proposed can effectively identify similar dairy cow behaviors while improving inference speed, providing technical support for subsequent dairy cow behavior recognition and daily behavior statistics. [ABSTRACT FROM AUTHOR]

The mounting behaviour of dairy cows is driven by oestrus and is also related to their welfare. To improve the accuracy and speed of the detection of mounting of dairy cows in dense scenes, a detection model for the mounting behaviour of dairy cows was developed in this study based on the feature enhancement module. Firstly, an improved attention module (C3GC-3) based on global context information and convolution was proposed to capture long-distance dependence. Then, a feature enhancement module based on atrous spatial pyramid pooling and the C3GC-3 was designed to realise the multiscale fusion of high-level semantic information and improve the feature extraction ability of the model for dense dairy cows images. Finally, the K-means clustering algorithm was used to obtain new anchors for the mounting behaviour of dairy cows, and CIoU was used to optimise the loss function. A camera was installed on a farm containing 200 dairy cows for data collection. The mosaic method was used to expand the 2668 images of the mounting behaviour of dairy cows to train the model, and the remaining 675 images were used to test the model. The experimental results showed that the proposed model had a high inference speed of 61 fps, and the detection time for each image was 16.3 ms, which met the real-time performance requirements for detecting mounting in dairy cows. The mean average precision of the model was 94.3%, which was 5.9% higher than that of YOLOv5l. The proposed model showed promising results regarding the mounting of dairy cows and might be used in any weather. • A mounting behaviour dataset of group-raised dairy cows in dense scenes was proposed.. • ASPP can improve the accuracy of multi-scale object detection. • Attention mechanism can improve the feature extraction ability of the model. • Mean average precision model was 94.3%, which is 5.9% higher than that of YOLOv5l. [ABSTRACT FROM AUTHOR]

Cow recognition forms the foundation of smart livestock management. Current closed-set cow recognition models can exclusively identify cows within their training set and are ill-equipped to recognize other subjects in the open world. Additionally, there is a dearth of comprehensive research on open-set cow recognition. Existing open-set recognition models not only exhibit suboptimal accuracy but also impose a substantial burden on hardware resources due to their extensive parameterization. These challenges hinder the practical deployment of cow recognition models. This study introduces an innovative open-set metric learning-based recognition framework for cow-back patterns, aiming to rectify a significant limitation of individual cow recognition models, which is their inability to identify cows not included in the training set. The proposed framework combines various loss functions, metric methods, and backbone networks. This integration enables the open-set recognition of cow back pattern images, thereby facilitating the identification of cows previously unrecognized by the model. To mitigate hardware resource consumption, we have devised a novel ultra-lightweight backbone network known as LightCowsNet. This network draws inspiration from existing lightweight backbone networks such as MobileFaceNet, MobileViT, and EfficientNetV2. Its purpose is to extract features from cow back pattern images efficiently. LightCowsNet employs attention mechanisms, inverted residual structures, and depthwise separable convolutions. LightCowsNet first uses attention mechanisms, inverted residual structures, and depthwise separable convolutions to design multiple new feature extraction modules. These modules, which have different structures, are subsequently placed to extract different levels of image information, which enables complete extraction of the textural information of the cows' back patterns. The present study reorganized the Cows2021 dataset to render it suitable for open-set recognition of cow-back patterns, with the test set comprising image pairs. The results revealed that using A-SoftMax as the loss function and Euclidean distance as the metric method enabled LightCowsNet to achieve the highest accuracy of 94.26 %, with a model weight space occupation of only 4.06 MB. Compared to MobileFaceNet, MobileViT, and EfficientNetV2, LightCowsNet achieved 6.24 %, 8.82 %, and 2.3 % greater accuracy on the test set, respectively. Its weight also decreased by 0.71 MB, 0.24 MB, and 4.3 MB, respectively. These results demonstrate that the proposed model achieved both accuracy improvement and model lightweightness, and these findings could serve as reference solutions for intelligent farming on cow farms. [ABSTRACT FROM AUTHOR]

Natural breeding scenes have the characteristics of a large number of cows, complex lighting, and a complex background environment, which presents great difficulties for the detection of dairy cow estrus behavior. However, the existing research on cow estrus behavior detection works well in ideal environments with a small number of cows and has a low inference speed and accuracy in natural scenes. To improve the inference speed and accuracy of cow estrus behavior in natural scenes, this paper proposes a cow estrus behavior detection method based on the improved YOLOv5. By improving the YOLOv5 model, it has stronger detection ability for complex environments and multi-scale objects. First, the atrous spatial pyramid pooling (ASPP) module is employed to optimize the YOLOv5l network at multiple scales, which improves the model's receptive field and ability to perceive global contextual multiscale information. Second, a cow estrus behavior detection model is constructed by combining the channel-attention mechanism and a deep-asymmetric-bottleneck module. Last, K-means clustering is performed to obtain new anchors and complete intersection over union (CIoU) is used to introduce the relative ratio between the predicted box of the cow mounting and the true box of the cow mounting to the regression box prediction function to improve the scale invariance of the model. Multiple cameras were installed in a natural breeding scene containing 200 cows to capture videos of cows mounting. A total of 2668 images were obtained from 115 videos of cow mounting events from the training set, and 675 images were obtained from 29 videos of cow mounting events from the test set. The training set is augmented by the mosaic method to increase the diversity of the dataset. The experimental results show that the average accuracy of the improved model was 94.3%, that the precision was 97.0%, and that the recall was 89.5%, which were higher than those of mainstream models such as YOLOv5, YOLOv3, and Faster R-CNN. The results of the ablation experiments show that ASPP, new anchors, C3SAB, and C3DAB designed in this study can improve the accuracy of the model by 5.9%. Furthermore, when the ASPP dilated convolution was set to (1,5,9,13) and the loss function was set to CIoU, the model had the highest accuracy. The class activation map function was utilized to visualize the model's feature extraction results and to explain the model's region of interest for cow images in natural scenes, which demonstrates the effectiveness of the model. Therefore, the model proposed in this study can improve the accuracy of the model for detecting cow estrus events. Additionally, the model's inference speed was 71 frames per second (fps), which meets the requirements of fast and accurate detection of cow estrus events in natural scenes and all-weather conditions. [ABSTRACT FROM AUTHOR]

Enterocytozoon bieneusi , an obligate intracellular pathogen, can infect various hosts. In this study, 3527 dairy cattle fecal specimens were collected from different geographic locations in China (including 673 from Shandong province, 1,440 from Guangdong province and 1,414 from Gansu province) and examined for the presence of E. bieneusi using polymerase chain reactions targeting the ribosomal internal transcribed spacer (ITS). The dominant genotypes identified were further subtyped by multilocus sequence typing. The overall prevalence of E. bieneusi was 14.2% (501/3527), with a significant difference in prevalence among the different geographical locations (P < 0.001). Our logistic regression analysis showed that all four variables (farming model, location, age, and clinical manifestations) had strong effects on the risk of contracting E. bieneusi. Sequence analysis revealed 11 genotypes: eight known genotypes (J, I, BEB4, BEB10, D, EbpC, CM19, and CM21) and three novel genotypes (named here as CGC1, CGC2, and CGC3). Genotypes J and I, the commonest, were found on all farms across the three provinces. Our linkage disequilibrium analysis showed a clonal population structure in the E. bieneusi dairy cattle population but the ITS genotypes had different population structures. Phylogenetic and haplotype network analysis showed the absence of geographical segregation in the E. bieneusi dairy cattle populations. Instead, they revealed the presence of host adaptation to the E. bieneusi populations in various animals. Our findings augment the current understanding of E. bieneusi transmission dynamics. [ABSTRACT FROM AUTHOR]

Enteric methane (CH 4) is primarily produced by methanogens during microbial fermentation in the rumen and is subsequently eructated through the oral and nasal passages of ruminants. As such, the present study hypothesized that the rates and daily amounts of CH 4 emission may be closely associated with CH 4 eructation peaks. To test this hypothesis, 12 dairy cows (6 lactating and 6 non-lactating) were selected as experimental animals with contrasting daily enteric CH 4 emissions. The experiment was conducted in two phases, with six non-lactating dairy cows in phase 1 and six lactating dairy cows in phase 2. For each phase, CH 4 eructation peaks were monitored every 2 h interval to calculate diurnal CH 4 emissions, with 12 time points scattered in four consecutive days by an automated head-chamber (AHC) system. The measurements were repeated, and total period of measurements lasted for 16 consecutive day. The results showed that compared with non-lactating dairy cows, lactating dairy cows exhibited greater diurnal CH 4 emissions and rates of CH 4 emission, together with higher peak frequency (P = 0.002), peak height (P < 0.001) and peak area integral (P < 0.001). Moreover, the rates of CH 4 emission was not constant and exhibited a fast increments after feeding, and had a positive correlation (R2 ≥ 0.54, P < 0.001) with peak height of CH 4 eructation. In conclusion, these findings indicate that the varied rates of CH 4 emission among dairy cows can be caused by altering peak frequency and peak area integral of CH 4 eructation, while a diurnal change in rates of CH 4 emission is associated with peak area integral through altering the peak height of CH 4 eructation. • Dairy cows exhibit variation in the daily amount and diurnal rate of CH 4 emission. • Lactating dairy cows exhibit greater CH 4 eructation peak frequency and peak area integral. • Diurnal change in rates of CH 4 emission is caused by altering CH 4 eructation peak height. [ABSTRACT FROM AUTHOR]

The objective of this study was to investigate differences in fermentation and methanogen communities in samples collected from 3 sites in the rumen of dairy cows. The study involved 3 ruminally cannulated nonlactating Chinese Holstein dairy cows fed a diet of 40% forage and 60% concentrate feeds. Four handfuls of whole ruminal contents were collected from the cranial sac, middle of the ventral sac, and caudodorsal blind sac of the rumen of the cows at 0, 2.5, and 6 h after the morning feeding. Concentrations of VFA, ammonia, and dissolved methane and hydrogen were analyzed. Methanogen populations and communities were analyzed targeting 16s rRNA genes. Dissolved methane concentration and pH were highest in samples from the cranial rumen. Ruminal fluid from the cranial rumen also had greater copy numbers of the Methanobrevibacter and higher Simpson indexes compared with samples from middle of the ventral rumen. In summary, cranial rumen had higher dissolved CH4 concentration than middle and hind rumen, which might be caused by the greater population of Methanobrevibacter with higher ruminal pH. [ABSTRACT FROM AUTHOR]

• The most of eating visits had duration larger than 24 s (99.0 %). • The most of non-eating visits had duration less than 24 s (65.3 %). • Setting immediate response in monitoring system helps to get actual feed intake, but can obtain a lot of non-eating visits. • Increasing response time helps to decrease the recording of non-eating visits, but can overestimate feed intake. The monitoring system can automatically collect the quantitative data of the feeding behavior and feed intake of individual cattle, and the immediate response system always records many non-eating visits. Increasing response time of trigger helps to decrease recording non-eating visits, but may also miss some small periods of recording feed intake. This study was to evaluate the effect of response time in monitoring system on the accuracy of recording individual feeding behavior and feed intake in dairy cows. The first experiment was to investigate the distribution of 10-h feeding behaviors of 8 Holstein dairy cows after morning feeding by using infra-red camera. The second experiment was to investigate accuracy of feed intake recorded by the monitoring system with different response times (0.3, 3, 6, 12 and 24 s) in comparison with direct weighting. The third experiment was to investigate effect of excluding the data of time interval after response time on feed intake and visiting behaviors recorded by the monitoring system, when response time was set as 0.3 s. The results showed that the most of eating and non-eating visits had duration larger than 24 s (99.0 %) and less than 24 s (65.3 %), respectively. Comparing with actual feed intake obtained by direct weighting, increasing response time greatly increased the recorded feed intake, with the greatest difference occurring at 6 s of response time (P = 0.001). Although increasing time interval after response time linearly increased mean, median feed intake per visit and 10-h feed intake (P < 0.01), it had little influence on 10-h feed intake (< 0.1 %) and eating visit (< 5%). In summary, setting 0.3 s of response time in monitoring system helps to get actual feed intake, but can obtain a lot of non-eating visits. Increasing response time helps to decrease the recording of non-eating visits, but can overestimate feed intake. [ABSTRACT FROM AUTHOR]

Cryptosporidium spp. and Giardia duodenalis are common gastrointestinal parasites with a broad range of hosts, including humans, livestock, and wildlife. To examine the infection status and assess the zoonotic potential of Cryptosporidium spp. and G. duodenalis in dairy cattle in Gansu, China, a total of 1414 fecal samples were collected from the rectum, with one sample collected from each individual animal. All the samples were tested using nested PCR based on the small subunit ribosomal RNA (SSU rRNA) gene of Cryptosporidium spp. and G. duodenalis. The overall infection rates of Cryptosporidium spp. and Giardia duodenalis were 4.2% (n = 59) and 1.0% (n = 14), respectively. Four Cryptosporidium species were identified: C. andersoni (n = 42), C. parvum (n = 12), C. bovis (n = 5), and C. ryanae (n = 1). In further analyses of subtypes of C. parvum isolates based on the 60 kDa glycoprotein (gp60) gene, five were successfully subtyped as IIdA19G1 (n = 4) and IIdA15G1 (n = 1). All 14 G. duodenalis isolates were identified as assemblage E using the triosephosphate isomerase (tpi) gene. The relatively low positive rates of Cryptosporidium spp. and G. duodenalis detected here and the predominance of non-human pathogenic species/assemblages of these parasites indicated their unique transmission dynamics in this area and the low level of threat posed to public health. However, continuous monitoring and further studies of these parasites should be conducted for the prevention and control of these pathogens.