Search

Simple Summary: Through gesture recognition and detection of sika deer, farmers can observe the gestures of sika deer without physical contact, providing data and technical support for the intelligent and welfare-oriented breeding of sika deer. This study is based on the YOLOv8 network model. By optimizing the convolution module, incorporating the attention mechanism, and enhancing the detection head module, a new method for detecting sika deer poses was developed. The method was assessed using four behavioral datasets, which included standing, lying, eating, and attacking. The pose-recognition accuracy of sika deer significantly improved to an average of 91.6%, laying a foundation for the health assessment and information management of sika deer. As the sika deer breeding industry flourishes on a large scale, accurately assessing the health of these animals is of paramount importance. Implementing posture recognition through target detection serves as a vital method for monitoring the well-being of sika deer. This approach allows for a more nuanced understanding of their physical condition, ensuring the industry can maintain high standards of animal welfare and productivity. In order to achieve remote monitoring of sika deer without interfering with the natural behavior of the animals, and to enhance animal welfare, this paper proposes a sika deer individual posture recognition detection algorithm GFI-YOLOv8 based on YOLOv8. Firstly, this paper proposes to add the iAFF iterative attention feature fusion module to the C2f of the backbone network module, replace the original SPPF module with AIFI module, and use the attention mechanism to adjust the feature channel adaptively. This aims to enhance granularity, improve the model's recognition, and enhance understanding of sika deer behavior in complex scenes. Secondly, a novel convolutional neural network module is introduced to improve the efficiency and accuracy of feature extraction, while preserving the model's depth and diversity. In addition, a new attention mechanism module is proposed to expand the receptive field and simplify the model. Furthermore, a new pyramid network and an optimized detection head module are presented to improve the recognition and interpretation of sika deer postures in intricate environments. The experimental results demonstrate that the model achieves 91.6% accuracy in recognizing the posture of sika deer, with a 6% improvement in accuracy and a 4.6% increase in mAP50 compared to YOLOv8n. Compared to other models in the YOLO series, such as YOLOv5n, YOLOv7-tiny, YOLOv8n, YOLOv8s, YOLOv9, and YOLOv10, this model exhibits higher accuracy, and improved mAP50 and mAP50-95 values. The overall performance is commendable, meeting the requirements for accurate and rapid identification of the posture of sika deer. This model proves beneficial for the precise and real-time monitoring of sika deer posture in complex breeding environments and under all-weather conditions. [ABSTRACT FROM AUTHOR]

Simple Summary: Through the non-destructive recognition and tracking algorithm of multi-objective behaviors of beef cattle, practitioners are able to obtain beef cattle feeding information in an all-round way, which lays the foundation for intelligent farming. This study is based on the deep learning recognition algorithm YOLOv8 and tracking algorithm Deep SORT. Through optimizing the convolution module, introducing the attention mechanism, improving the re-identification network, and the trajectory generation and matching process, a new method for the non-destructive identification and tracking of multi-target behaviors of beef cattle is constructed. The average accuracy of nine behaviors can be up to 96.5%, and the accuracy of multi-target tracking is up to 92.1%, which can provide technical support for beef cattle management. The method proposed in this paper provides theoretical and practical support for the intelligent recognition and management of beef cattle. Accurate identification and tracking of beef cattle behaviors are essential components of beef cattle production management. Traditional beef cattle identification and tracking methods are time-consuming and labor-intensive, which hinders precise cattle farming. This paper utilizes deep learning algorithms to achieve the identification and tracking of multi-object behaviors in beef cattle, as follows: (1) The beef cattle behavior detection module is based on the YOLOv8n algorithm. Initially, a dynamic snake convolution module is introduced to enhance the ability to extract key features of beef cattle behaviors and expand the model's receptive field. Subsequently, the BiFormer attention mechanism is incorporated to integrate high-level and low-level feature information, dynamically and sparsely learning the behavioral features of beef cattle. The improved YOLOv8n_BiF_DSC algorithm achieves an identification accuracy of 93.6% for nine behaviors, including standing, lying, mounting, fighting, licking, eating, drinking, working, and searching, with average 50 and 50:95 precisions of 96.5% and 71.5%, showing an improvement of 5.3%, 5.2%, and 7.1% over the original YOLOv8n. (2) The beef cattle multi-object tracking module is based on the Deep SORT algorithm. Initially, the detector is replaced with YOLOv8n_BiF_DSC to enhance detection accuracy. Subsequently, the re-identification network model is switched to ResNet18 to enhance the tracking algorithm's capability to gather appearance information. Finally, the trajectory generation and matching process of the Deep SORT algorithm is optimized with secondary IOU matching to reduce ID mismatching errors during tracking. Experimentation with five different complexity levels of test video sequences shows improvements in IDF1, IDS, MOTA, and MOTP, among other metrics, with IDS reduced by 65.8% and MOTA increased by 2%. These enhancements address issues of tracking omission and misidentification in sparse and long-range dense environments, thereby facilitating better tracking of group-raised beef cattle and laying a foundation for intelligent detection and tracking in beef cattle farming. [ABSTRACT FROM AUTHOR]

Simple Summary: In the sorting process of Chinese softshell turtles, it is necessary to classify them based on their weight and accurately identify their plastron and carapace. This process requires heavy manual labor and complex mechanical processing methods. To improve processing efficiency and reduce costs, this article introduces machine vision technology, and a new image processing method is proposed. This method can estimate the weight of Chinese softshell turtles and accurately locate the positions of their plastron and carapace. The automation level of aquaculture can be greatly enhanced, and hardware costs can be reduced through software optimization through this approach. With the rapid development of the turtle breeding industry in China, the demand for automated turtle sorting is increasing. The automatic sorting of Chinese softshell turtles mainly consists of three parts: visual recognition, weight prediction, and individual sorting. This paper focuses on two aspects, i.e., visual recognition and weight prediction, and a novel method for the object detection and weight prediction of Chinese softshell turtles is proposed. In the individual sorting process, computer vision technology is used to estimate the weight of Chinese softshell turtles and classify them by weight. For the visual recognition of the body parts of Chinese softshell turtles, a color space model is proposed in this paper to separate the turtles from the background effectively. By applying multiple linear regression analysis for modeling, the relationship between the weight and morphological parameters of Chinese softshell turtles is obtained, which can be used to estimate the weight of turtles well. An improved deep learning object detection network is used to extract the features of the plastron and carapace of the Chinese softshell turtles, achieving excellent detection results. The mAP of the improved network reached 96.23%, which can meet the requirements for the accurate identification of the body parts of Chinese softshell turtles. [ABSTRACT FROM AUTHOR]

Simple Summary: In the process of large-scale cage chicken breeding, using inspection robots instead of manual detection can solve the problems of large workload and low detection efficiency. However, poor driving stability of an inspection robot will lead to low inspection accuracy. In order to ensure high efficiency, accuracy, and stability of detection, this study takes the stability of visual navigation for inspection robots as the optimization goal, and designs an efficient and accurate road extraction algorithm and a navigation line fitting algorithm with better robustness. The experimental results show that the algorithm proposed in this study can improve the stability of detection, achieve a faster running speed, and achieve a better detection effect and a higher detection efficiency while keeping the detection effect unchanged. The navigation algorithm can accelerate the automation process of large-scale cage chicken breeding and promote the realization of fast and accurate monitoring. The speed and accuracy of navigation road extraction and driving stability affect the inspection accuracy of cage chicken coop inspection robots. In this paper, a new grayscale factor (4B-3R-2G) was proposed to achieve fast and accurate road extraction, and a navigation line fitting algorithm based on the road boundary features was proposed to improve the stability of the algorithm. The proposed grayscale factor achieved 92.918% segmentation accuracy, and the speed was six times faster than the deep learning model. The experimental results showed that at the speed of 0.348 m/s, the maximum deviation of the visual navigation was 4 cm, the average deviation was 1.561 cm, the maximum acceleration was 1.122 m/s2, and the average acceleration was 0.292 m/s2, with the detection number and accuracy increased by 21.125% and 1.228%, respectively. Compared with inertial navigation, visual navigation can significantly improve the navigation accuracy and stability of the inspection robot and lead to better inspection effects. The visual navigation system proposed in this paper has better driving stability, higher inspection efficiency, better inspection effect, and lower operating costs, which is of great significance to promote the automation process of large-scale cage chicken breeding and realize rapid and accurate monitoring. [ABSTRACT FROM AUTHOR]

Simple Summary: The Amur tiger is an endangered species in the world, and effective statistics on its individuals and population through re-identification will contribute to ecological diversity investigation and assessment. Due to the fact that the fur texture features of the Amur tiger contain genetic information, the main method of identifying Amur tigers is to distinguish their fur and facial features. In summary, this paper proposes a serial multi-scale feature fusion and enhancement network for Amur tiger re-identification, and designs a global inverted pyramid multi-scale feature fusion module and a local dual-domain attention feature enhancement module. We aim to enhance the learning of fine-grained features and differences in fur texture by better fusing and enhancing global and local features. Our proposed network and module have achieved excellent results on the public dataset of the ATRW. The Amur tiger is an important endangered species in the world, and its re-identification (re-ID) plays an important role in regional biodiversity assessment and wildlife resource statistics. This paper focuses on the task of Amur tiger re-ID based on visible light images from screenshots of surveillance videos or camera traps, aiming to solve the problem of low accuracy caused by camera perspective, noisy background noise, changes in motion posture, and deformation of Amur tiger body patterns during the re-ID process. To overcome this challenge, we propose a serial multi-scale feature fusion and enhancement re-ID network of Amur tiger for this task, in which global and local branches are constructed. Specifically, we design a global inverted pyramid multi-scale feature fusion method in the global branch to effectively fuse multi-scale global features and achieve high-level, fine-grained, and deep semantic feature preservation. We also design a local dual-domain attention feature enhancement method in the local branch, further enhancing local feature extraction and fusion by dividing local feature blocks. Based on the above model structure, we evaluated the effectiveness and feasibility of the model on the public dataset of the Amur Tiger Re-identification in the Wild (ATRW), and achieved good results on mAP, Rank-1, and Rank-5, demonstrating a certain competitiveness. In addition, since our proposed model does not require the introduction of additional expensive annotation information and does not incorporate other pre-training modules, it has important advantages such as strong transferability and simple training. [ABSTRACT FROM AUTHOR]

Simple Summary: Researching and developing an automated and intelligent method to monitor the pangolin breeding process can effectively help human observation, analysis, breeding and daily behavior studies of pangolins, and has significant implications for the protection and breeding research of pangolin populations. In this paper, a pangolin breeding attention and temporal relative network (PBATn) was used to monitor and identify the breeding and daily behaviors of pangolins. This study demonstrates that the deep learning system can accurately observe pangolin breeding behavior, rendering it useful for analyzing the behavior of these animals. With declining populations in the wild, captive rescue and breeding have become one of the most important ways to protect pangolins from extinction. At present, the success rate of artificial breeding is low, due to the insufficient understanding of the breeding behavior characteristics of pangolins. The automatic recognition method based on machine vision not only monitors for 24 h but also reduces the stress response of pangolins. This paper aimed to establish a temporal relation and attention mechanism network (Pangolin breeding attention and transfer network, PBATn) to monitor and recognize pangolin behaviors, including breeding and daily behavior. There were 11,476 videos including breeding behavior and daily behavior that were divided into training, validation, and test sets. For the training set and validation set, the PBATn network model had an accuracy of 98.95% and 96.11%, and a loss function value of 0.1531 and 0.1852. The model is suitable for a 2.40 m × 2.20 m (length × width) pangolin cage area, with a nest box measuring 40 cm × 30 cm × 30 cm (length × width × height) positioned either on the left or right side inside the cage. A spherical night-vision monitoring camera was installed on the cage wall at a height of 2.50 m above the ground. For the test set, the mean Average Precision (mAP), average accuracy, average recall, average specificity, and average F1 score were found to be higher than SlowFast, X3D, TANet, TSN, etc., with values of 97.50%, 99.17%, 97.55%, 99.53%, and 97.48%, respectively. The recognition accuracies of PBATn were 94.00% and 98.50% for the chasing and mounting breeding behaviors, respectively. The results showed that PBATn outperformed the baseline methods in all aspects. This study shows that the deep learning system can accurately observe pangolin breeding behavior and it will be useful for analyzing the behavior of these animals. [ABSTRACT FROM AUTHOR]

Simple Summary: Welfare farming of pigs is a kind of farming method that pays attention to the welfare of animals, which is of great significance to the health and production performance of pigs. The estimation of pig weight based on computer vision can avoid direct contact with pigs, reduce the loss caused by contact or pressure, and ultimately improve the overall breeding efficiency and economic benefits. In this paper, we proposed a new pig weight estimation method based on Mask R-CNN and machine learning methods. Our new method extracted features from a new perspective to solve the problem of illumination and body bending.The experimental results show that our method can accurately predict the weight of pigs. Using computer vision technology to estimate pig live weight is an important method to realize pig welfare. But there are two key issues that affect pigs' weight estimation: one is the uneven illumination, which leads to unclear contour extraction of pigs, and the other is the bending of the pig body, which leads to incorrect pig body information. For the first one, Mask R-CNN was used to extract the contour of the pig, and the obtained mask image was converted into a binary image from which we were able to obtain a more accurate contour image. For the second one, the body length, hip width and the distance from the camera to the pig back were corrected by XGBoost and actual measured information. Then we analyzed the rationality of the extracted features. Three feature combination strategies were used to predict pig weight. In total, 1505 back images of 39 pigs obtained using Azure kinect DK were used in the numerical experiments. The highest prediction accuracy is XGBoost, with an MAE of 0.389, RMSE of 0.576, MAPE of 0.318% and R 2 of 0.995. We also recommend using the Mask R-CNN + RFR method because it has fairly high precision in each strategy. The experimental results show that our proposed method has excellent performance in live weight estimation of pigs. [ABSTRACT FROM AUTHOR]

Simple Summary: Managing fish feeding well is important for both making fish farming better and keeping aquatic environments healthy. By looking at the sounds fish make, this study suggests a new way to learn about how they eat. We turn these sounds into pictures and use advanced computer methods to figure out the different ways people eat. Our method uses a strong deep learning model that can correctly group the eating habits of a certain type of fish, which helps us figure out how much and how often they eat. With a 97% success rate, this method shows a lot of promise for better running fish farms and protecting marine ecosystems. In the future, researchers might be able to add more types of data to this method, which could give us even more information about how to farm fish sustainably and manage ecosystems. Understanding the feeding dynamics of aquatic animals is crucial for aquaculture optimization and ecosystem management. This paper proposes a novel framework for analyzing fish feeding behavior based on a fusion of spectrogram-extracted features and deep learning architecture. Raw audio waveforms are first transformed into Log Mel Spectrograms, and a fusion of features such as the Discrete Wavelet Transform, the Gabor filter, the Local Binary Pattern, and the Laplacian High Pass Filter, followed by a well-adapted deep model, is proposed to capture crucial spectral and spectral information that can help distinguish between the various forms of fish feeding behavior. The Involutional Neural Network (INN)-based deep learning model is used for classification, achieving an accuracy of up to 97% across various temporal segments. The proposed methodology is shown to be effective in accurately classifying the feeding intensities of Oplegnathus punctatus, enabling insights pertinent to aquaculture enhancement and ecosystem management. Future work may include additional feature extraction modalities and multi-modal data integration to further our understanding and contribute towards the sustainable management of marine resources. [ABSTRACT FROM AUTHOR]

Simple Summary: Simple Summary: Pig tracking provides strong support for refined management in pig farms and can assist in realizing customized, automated, and intellectualized management. However, there are many complex factors in actual production that result in pigs not being tracked consistently over time. To address this issue, we proposed a long-term video tracking method for group-housed pigs based on improved StrongSORT. The experimental results proved that our study demonstrates high practicality, catering to the needs of practical production. It improved the efficiency of farming personnel and lays the foundation for the automated monitoring of pigs. Additionally, it is worth mentioning that we have also released a dataset specifically designed for long-term pig tracking in this paper. Pig tracking provides strong support for refined management in pig farms. However, long and continuous multi-pig tracking is still extremely challenging due to occlusion, distortion, and motion blurring in real farming scenarios. This study proposes a long-term video tracking method for group-housed pigs based on improved StrongSORT, which can significantly improve the performance of pig tracking in production scenarios. In addition, this research constructs a 24 h pig tracking video dataset, providing a basis for exploring the effectiveness of long-term tracking algorithms. For object detection, a lightweight pig detection network, YOLO v7-tiny_Pig, improved based on YOLO v7-tiny, is proposed to reduce model parameters and improve detection speed. To address the target association problem, the trajectory management method of StrongSORT is optimized according to the characteristics of the pig tracking task to reduce the tracking identity (ID) switching and improve the stability of the algorithm. The experimental results show that YOLO v7-tiny_Pig ensures detection applicability while reducing parameters by 36.7% compared to YOLO v7-tiny and achieving an average video detection speed of 435 frames per second. In terms of pig tracking, Higher-Order Tracking Accuracy (HOTA), Multi-Object Tracking Accuracy (MOTP), and Identification F1 (IDF1) scores reach 83.16%, 97.6%, and 91.42%, respectively. Compared with the original StrongSORT algorithm, HOTA and IDF1 are improved by 6.19% and 10.89%, respectively, and Identity Switch (IDSW) is reduced by 69%. Our algorithm can achieve the continuous tracking of pigs in real scenarios for up to 24 h. This method provides technical support for non-contact pig automatic monitoring. [ABSTRACT FROM AUTHOR]

Simple Summary: Currently, smart devices for cows on the market are mainly leg rings and collars, but the behavioral data provided by these devices do not well reflect the real behavior of cows. Therefore, a cow-behavior-detection device based on a wearable device is proposed. It is a set of equipment that collects data on the daily behavior (eating, rumination, other behavior) of cows, which can help people monitor the health status of cows more accurately. This paper proposes for the first time an electronic device worn on the nose of a cow to record real-time behavioral data of the cow. Through these data, the daily behavior of cows can be analyzed, such as the time spent eating and ruminating that day, the number of rumination chews, etc., which can better help farm managers understand the health status of cows, reduce the occurrence of diseases, and thereby improve the overall health of the cows' welfare. The wearing position of the device has no adverse effects on the normal life of the cows and is suitable for long-term wearing. This equipment helps improve the welfare of dairy cows and has far-reaching value for the dairy farming industry. This study introduces a novel device designed to monitor dairy cow behavior, with a particular focus on feeding, rumination, and other behaviors. This study investigates the association between the cow behaviors and acceleration data collected using a three-axis, nose-mounted accelerometer, as well as the feasibility of improving the behavioral classification accuracy through machine learning. A total of 11 cows were used. We utilized three-axis acceleration sensors that were fixed to the cow's nose, and these devices provided detailed and unique data corresponding to their activity; in particular, a recorder was installed on each nasal device to obtain acceleration data, which were then used to calculate activity levels and changes. In addition, we visually observed the behavior of the cattle. The characteristic acceleration values during feeding, rumination, and other behavior were recorded; there were significant differences in the activity levels and changes between different behaviors. The results indicated that the nose ring device had the potential to accurately differentiate between eating and rumination behaviors, thus providing an effective method for the early detection of health problems and cattle management. The eating, rumination, and other behaviors of cows were classified with high accuracy using the machine learning technique, which can be used to calculate the activity levels and changes in cattle based on the data obtained from the nose-mounted, three-axis accelerometer. [ABSTRACT FROM AUTHOR]

Simple Summary: In response to the quantitative demand for the practical deployment of applications and the need to enhance the detection accuracy of wildlife in complex field environments in southwest China and neighboring regions, we have refined the wildlife detection algorithm based on re-parameterized convolution. This refinement is specifically targeted at addressing the challenges posed by the low quality of wildlife images captured by camera traps and the limitations of traditional object detection algorithms in feature extraction capability. To address these issues, we have introduced a series of improvement schemes. As a result of these enhancements, there has been a noteworthy improvement in both the accuracy of wildlife detection and the speed of model inference. This advancement offers a convenient and efficient method for the preliminary detection in the context of automated wildlife monitoring. To autonomously detect wildlife images captured by camera traps on a platform with limited resources and address challenges such as filtering out photos without optimal objects, as well as classifying and localizing species in photos with objects, we introduce a specialized wildlife object detector tailored for camera traps. This detector is developed using a dataset acquired by the Saola Working Group (SWG) through camera traps deployed in Vietnam and Laos. Utilizing the YOLOv6-N object detection algorithm as its foundation, the detector is enhanced by a tailored optimizer for improved model performance. We deliberately introduce asymmetric convolutional branches to enhance the feature characterization capability of the Backbone network. Additionally, we streamline the Neck and use CIoU loss to improve detection performance. For quantitative deployment, we refine the RepOptimizer to train a pure VGG-style network. Experimental results demonstrate that our proposed method empowers the model to achieve an 88.3% detection accuracy on the wildlife dataset in this paper. This accuracy is 3.1% higher than YOLOv6-N, and surpasses YOLOv7-T and YOLOv8-N by 5.5% and 2.8%, respectively. The model consistently maintains its detection performance even after quantization to the INT8 precision, achieving an inference speed of only 6.15 ms for a single image on the NVIDIA Jetson Xavier NX device. The improvements we introduce excel in tasks related to wildlife image recognition and object localization captured by camera traps, providing practical solutions to enhance wildlife monitoring and facilitate efficient data acquisition. Our current work represents a significant stride toward a fully automated animal observation system in real-time in-field applications. [ABSTRACT FROM AUTHOR]

Simple Summary: Hair tubes provide a non-invasive method for determining the presence and activity of small mammals by evaluating hair left in hair tubes. Data can be converted into activity indices. In this study, a specially adapted program was developed to semi-automatically determine hair density as a proxy of activity. Adhesive tape with hair from a field experiment was processed, scanned, and analyzed by the program to obtain a quantitative measure of hair density. The validation of hair tubes with wildlife cameras in the field showed a moderate-to-strong positive correlation between hair tube data and recorded rodents. The program is simple but effective and does not require a large amount of deep learning data. Due to its reduced complexity, it facilitates error detection and fine-tuning. The use of hair tubes in combination with this program should provide an easy-to-use, non-invasive method to determine small mammal activity. Activity indices are used to determine the presence and activity of small mammals, such as the hair index derived from the use of hair tubes. In contrast to trapping animals, hair tubes are non-invasive and less labor-intensive, and appear to be a suitable alternative in appropriate settings. We developed a method to calculate hair density semi-automatically. In addition, hair tube data were validated with field data using wildlife cameras for the small mammal community in grassland, wheat crops, and hedges to assess how well data from hair tubes match data from wildlife cameras. Adhesive tape with hair from hair tubes was processed and scanned. The resulting images were analyzed using a newly developed computer program that enables background and adhesive tape to be automatically distinguished from hair, providing a quantitative measure of hair density. Based on validation with wildlife cameras, hair tubes seem to be a suitable tool to estimate small mammal activity at the community level in several habitats. There was a moderate-to-strong positive correlation of the hair tube index with the sum of voles and Apodemus individuals (activity index) recorded in grasslands (Spearman's correlation coefficient 0.43), hedges (0.79), and wheat (0.44). The newly developed computer program allows the automatic calculation of hair density, making it easier to assess the activity of small mammals. [ABSTRACT FROM AUTHOR]

Simple Summary: Blurry scenarios often affect the clarity of fish images, posing significant challenges to deep learning models in terms of the accurate recognition of fish species. A method based on deep learning with a diffusion model and an attention mechanism, DiffusionFR, is proposed herein to improve the accuracy of fish species recognition in blurry scenarios caused by light reflections and water ripple noise. Using a self-constructed dataset, BlurryFish, extensive experiments were conducted and the results showed that the proposed two-stage diffusion network model can restore the clarity of blurry fish images to some extent and the proposed learnable attention module is effective in improving the accuracy of fish species recognition. Blurry scenarios, such as light reflections and water ripples, often affect the clarity and signal-to-noise ratio of fish images, posing significant challenges for traditional deep learning models in accurately recognizing fish species. Firstly, deep learning models rely on a large amount of labeled data. However, it is often difficult to label data in blurry scenarios. Secondly, existing deep learning models need to be more effective for the processing of bad, blurry, and otherwise inadequate images, which is an essential reason for their low recognition rate. A method based on the diffusion model and attention mechanism for fish image recognition in blurry scenarios, DiffusionFR, is proposed to solve these problems and improve the performance of species recognition of fish images in blurry scenarios. This paper presents the selection and application of this correcting technique. In the method, DiffusionFR, a two-stage diffusion network model, TSD, is designed to deblur bad, blurry, and otherwise inadequate fish scene pictures to restore clarity, and a learnable attention module, LAM, is intended to improve the accuracy of fish recognition. In addition, a new dataset of fish images in blurry scenarios, BlurryFish, was constructed and used to validate the effectiveness of DiffusionFR, combining bad, blurry, and otherwise inadequate images from the publicly available dataset Fish4Knowledge. The experimental results demonstrate that DiffusionFR achieves outstanding performance on various datasets. On the original dataset, DiffusionFR achieved the highest training accuracy of 97.55%, as well as a Top-1 accuracy test score of 92.02% and a Top-5 accuracy test score of 95.17%. Furthermore, on nine datasets with light reflection noise, the mean values of training accuracy reached a peak at 96.50%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 90.96% and 94.12%, respectively. Similarly, on three datasets with water ripple noise, the mean values of training accuracy reached a peak at 95.00%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 89.54% and 92.73%, respectively. These results demonstrate that the method showcases superior accuracy and enhanced robustness in handling original datasets and datasets with light reflection and water ripple noise. [ABSTRACT FROM AUTHOR]

Simple Summary: Dairy cow behavior detection is of great significance for cattle health management. Through the detection of the four behaviors of dairy cows—standing, lying, eating, and drinking—we can gain valuable insights into the well-being of cows. For example, hoof disease can increase the amount of time a cow lies down, and digestive system issues can cause a decrease in food intake. Visual inspection of cow behavior can keep track of changes in cow behavior, and non-invasive detection can reduce cow discomfort and improve animal welfare. In this study, we employed computer vision-based deep learning techniques for the detection of cow behavior, and experimental results demonstrated its promising application in real farm settings. Dairy cow behavior carries important health information. Timely and accurate detection of behaviors such as drinking, feeding, lying, and standing is meaningful for monitoring individual cows and herd management. In this study, a model called Res-DenseYOLO is proposed for accurately detecting the individual behavior of dairy cows living in cowsheds. Specifically, a dense module was integrated into the backbone network of YOLOv5 to strengthen feature extraction for actual cowshed environments. A CoordAtt attention mechanism and SioU loss function were added to enhance feature learning and training convergence. Multi-scale detection heads were designed to improve small target detection. The model was trained and tested on 5516 images collected from monitoring videos of a dairy cowshed. The experimental results showed that the performance of Res-DenseYOLO proposed in this paper is better than that of Fast-RCNN, SSD, YOLOv4, YOLOv7, and other detection models in terms of precision, recall, and mAP metrics. Specifically, Res-DenseYOLO achieved 94.7% precision, 91.2% recall, and 96.3% mAP, outperforming the baseline YOLOv5 model by 0.7%, 4.2%, and 3.7%, respectively. This research developed a useful solution for real-time and accurate detection of dairy cow behaviors with video monitoring only, providing valuable behavioral data for animal welfare and production management. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study, a Common Objects in Context dataset of ovine pulmonary adenocarcinoma pathological images was constructed based on 7167 annotated typical lesions from 61,063 lung pathological images of ovine pulmonary adenocarcinoma. This study aimed to develop a mask regional convolutional neural network model for the localization and pathological diagnosis of ovine pulmonary adenocarcinoma lesions. The model achieved a mean average specificity of 0.573 and an average sensitivity of 0.745, with consistency rates of 100% for junior pathologists and 96.5% for senior pathologists in the diagnosis of ovine pulmonary adenocarcinoma. The successful development of this model not only facilitates the rapid diagnosis of ovine pulmonary adenocarcinoma by different personnel in practical applications but also lays a foundation for the transition from traditional pathology to digital pathology in the livestock industry. Ovine pulmonary adenocarcinoma (OPA) is a contagious lung tumour caused by the Jaagsiekte Sheep Retrovirus (JSRV). Histopathological diagnosis is the gold standard for OPA diagnosis. However, interpretation of traditional pathology images is complex and operator dependent. The mask regional convolutional neural network (Mask R-CNN) has emerged as a valuable tool in pathological diagnosis. This study utilized 54 typical OPA whole slide images (WSI) to extract 7167 typical lesion images containing OPA to construct a Common Objects in Context (COCO) dataset for OPA pathological images. The dataset was categorized into training and test sets (8:2 ratio) for model training and validation. Mean average specificity (mASp) and average sensitivity (ASe) were used to evaluate model performance. Six WSI-level pathological images (three OPA and three non-OPA images), not included in the dataset, were used for anti-peeking model validation. A random selection of 500 images, not included in the dataset establishment, was used to compare the performance of the model with assessment by pathologists. Accuracy, sensitivity, specificity, and concordance rate were evaluated. The model achieved a mASp of 0.573 and an ASe of 0.745, demonstrating effective lesion detection and alignment with expert annotation. In Anti-Peeking verification, the model showed good performance in locating OPA lesions and distinguished OPA from non-OPA pathological images. In the random 500-image diagnosis, the model achieved 92.8% accuracy, 100% sensitivity, and 88% specificity. The agreement rates between junior and senior pathologists were 100% and 96.5%, respectively. In conclusion, the Mask R-CNN-based OPA diagnostic model developed for OPA facilitates rapid and accurate diagnosis in practical applications. [ABSTRACT FROM AUTHOR]

Simple Summary: This study addresses the significance of animal sounds as valuable indicators of both behavior and health in animals, emphasizing the challenges involved in collecting datasets for deep learning models. Particularly, in the context of classifying pig vocalization and non-vocalization, it is identified as laborious and time-consuming when relying on human efforts. In response to these challenges, the research proposes a new approach utilizing a deep learning model to automatically classify pig vocalization and non-vocalization with high accuracy. The success of this method not only provides an efficient means of collecting pig sound datasets but also presents a promising avenue for improving the classification of pig vocalization and non-vocalization in deep learning models, thereby contributing to advancements in animal behavior research and health monitoring. Since pig vocalization is an important indicator of monitoring pig conditions, pig vocalization detection and recognition using deep learning play a crucial role in the management and welfare of modern pig livestock farming. However, collecting pig sound data for deep learning model training takes time and effort. Acknowledging the challenges of collecting pig sound data for model training, this study introduces a deep convolutional neural network (DCNN) architecture for pig vocalization and non-vocalization classification with a real pig farm dataset. Various audio feature extraction methods were evaluated individually to compare the performance differences, including Mel-frequency cepstral coefficients (MFCC), Mel-spectrogram, Chroma, and Tonnetz. This study proposes a novel feature extraction method called Mixed-MMCT to improve the classification accuracy by integrating MFCC, Mel-spectrogram, Chroma, and Tonnetz features. These feature extraction methods were applied to extract relevant features from the pig sound dataset for input into a deep learning network. For the experiment, three datasets were collected from three actual pig farms: Nias, Gimje, and Jeongeup. Each dataset consists of 4000 WAV files (2000 pig vocalization and 2000 pig non-vocalization) with a duration of three seconds. Various audio data augmentation techniques are utilized in the training set to improve the model performance and generalization, including pitch-shifting, time-shifting, time-stretching, and background-noising. In this study, the performance of the predictive deep learning model was assessed using the k-fold cross-validation (k = 5) technique on each dataset. By conducting rigorous experiments, Mixed-MMCT showed superior accuracy on Nias, Gimje, and Jeongeup, with rates of 99.50%, 99.56%, and 99.67%, respectively. Robustness experiments were performed to prove the effectiveness of the model by using two farm datasets as a training set and a farm as a testing set. The average performance of the Mixed-MMCT in terms of accuracy, precision, recall, and F1-score reached rates of 95.67%, 96.25%, 95.68%, and 95.96%, respectively. All results demonstrate that the proposed Mixed-MMCT feature extraction method outperforms other methods regarding pig vocalization and non-vocalization classification in real pig livestock farming. [ABSTRACT FROM AUTHOR]

Simple Summary: Technological advancements have revolutionized dairy cattle management through digital and precision approaches. This study conducts a bibliometric analysis of these technologies, identifying emerging patterns, research themes, and author collaborations. It reveals top journals of interest and emerging technologies such as machine learning and computer vision. These tools are crucial for decisions enhancing health and efficiency in milk production, promoting more sustainable practices. It highlights the evolution of precision livestock farming and introduces digital livestock farming, demonstrating how advanced digital tools transform dairy herd management. This shift not only boosts productivity but also redefines cattle management, emphasizing its impact on the sustainability and efficiency of milk production. The advancement of technology has significantly transformed the livestock landscape, particularly in the management of dairy cattle, through the incorporation of digital and precision approaches. This study presents a bibliometric analysis focused on these technologies involving dairy farming to explore and map the extent of research in the scientific literature. Through this review, it was possible to investigate academic production related to digital and precision livestock farming and identify emerging patterns, main research themes, and author collaborations. To carry out this investigation in the literature, the entire timeline was considered, finding works from 2008 to November 2023 in the scientific databases Scopus and Web of Science. Next, the Bibliometrix (version 4.1.3) package in R (version 4.3.1) and its Biblioshiny software extension (version 4.1.3) were used as a graphical interface, in addition to the VOSviewer (version 1.6.19) software, focusing on filtering and creating graphs and thematic maps to analyze the temporal evolution of 198 works identified and classified for this research. The results indicate that the main journals of interest for publications with identified affiliations are "Computers and Electronics in Agriculture" and "Journal of Dairy Science". It has been observed that the authors focus on emerging technologies such as machine learning, deep learning, and computer vision for behavioral monitoring, dairy cattle identification, and management of thermal stress in these animals. These technologies are crucial for making decisions that enhance health and efficiency in milk production, contributing to more sustainable practices. This work highlights the evolution of precision livestock farming and introduces the concept of digital livestock farming, demonstrating how the adoption of advanced digital tools can transform dairy herd management. Digital livestock farming not only boosts productivity but also redefines cattle management through technological innovations, emphasizing the significant impact of these trends on the sustainability and efficiency of dairy production. [ABSTRACT FROM AUTHOR]

Simple Summary: In the process of calf rearing, it is inevitable to encounter issues of illness and death among calves. Often, due to the inability to detect sicknesses such as diarrhoea in a timely fashion, these sicknesses lead to the calves' demise. This research starts from the practical application needs, and proposes the development of a monitoring system using deep learning technology to monitor the daily standing and lying behaviour of calves to predict their condition and adaptation to the environment. By analysing the standing and lying time of calves, the system can provide early warnings about calves' condition and health status. This research helps to promptly grasp calves' condition and growth status, thereby improving their welfare and management, enhancing the health condition of reared calves, ensuring the quality and safety of meat and milk, and reducing production costs. This research method also offers a new idea for the construction of smart ranches, as the construction of precision and smart ranches is not only a demand of consumers but also an inevitable direction for the development of the breeding industry. Standing and lying are the fundamental behaviours of quadrupedal animals, and the ratio of their durations is a significant indicator of calf health. In this study, we proposed a computer vision method for non-invasively monitoring of calves' behaviours. Cameras were deployed at four viewpoints to monitor six calves on six consecutive days. YOLOv8n was trained to detect standing and lying calves. Daily behavioural budget was then summarised and analysed based on automatic inference on untrained data. The results show a mean average precision of 0.995 and an average inference speed of 333 frames per second. The maximum error in the estimated daily standing and lying time for a total of 8 calf-days is less than 14 min. Calves with diarrhoea had about 2 h more daily lying time (p < 0.002), 2.65 more daily lying bouts (p < 0.049), and 4.3 min less daily lying bout duration (p = 0.5) compared to healthy calves. The proposed method can help in understanding calves' health status based on automatically measured standing and lying time, thereby improving their welfare and management on the farm. [ABSTRACT FROM AUTHOR]

Simple Summary: A pig inventory is an important part of realizing accurate and large-scale farming. Distinguishing from the current, mostly overhead scene or static map counting, this study proposes a video-based dynamic counting method through which pigs can be counted automatically and continuously in complex scenes. The improved model effectively reduces the counting error and improves the operation efficiency, which provides data and experimental references for the study of automated pig counting, and it also provides technical support to improve the management efficiency of pig farms, reducing the cost and promoting the intelligent transformation of the animal husbandry industry. A pig inventory is a crucial component of achieving precise and large-scale farming. In complex pigsty environments, due to pigs' stress reactions and frequent obstructions, it is challenging to count them accurately and automatically. This difficulty contrasts with most current deep learning studies, which rely on overhead views or static images for counting. This research proposes a video-based dynamic counting method, combining YOLOv7 with DeepSORT. By utilizing the YOLOv7 network structure and optimizing the second and third 3 × 3 convolution operations in the head network ELAN-W with PConv, the model reduces the computational demand and improves the inference speed without sacrificing accuracy. To ensure that the network acquires accurate position perception information at oblique angles and extracts rich semantic information, we introduce the coordinate attention (CA) mechanism before the three re-referentialization paths (REPConv) in the head network, enhancing robustness in complex scenarios. Experimental results show that, compared to the original model, the improved model increases the mAP by 3.24, 0.05, and 1.00 percentage points for oblique, overhead, and all pig counting datasets, respectively, while reducing the computational cost by 3.6 GFLOPS. The enhanced YOLOv7 outperforms YOLOv5, YOLOv4, YOLOv3, Faster RCNN, and SSD in target detection with mAP improvements of 2.07, 5.20, 2.16, 7.05, and 19.73 percentage points, respectively. In dynamic counting experiments, the improved YOLOv7 combined with DeepSORT was tested on videos with total pig counts of 144, 201, 285, and 295, yielding errors of -3, -3, -4, and -26, respectively, with an average accuracy of 96.58% and an FPS of 22. This demonstrates the model's capability of performing the real-time counting of pigs in various scenes, providing valuable data and references for automated pig counting research. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study, deep learning combined with udder ultrasonography of buffalo was used for the detection of mastitis for the first time, with the aim of establishing an accurate, rapid, and inexpensive method to detect buffalo mastitis instead of routine laboratory examination. This method provides a basis for mastitis detection in buffaloes mostly raised by small farmers and has the opportunity to be used in a variety of dairy animals in the future. Mastitis is one of the most predominant diseases with a negative impact on ranch products worldwide. It reduces milk production, damages milk quality, increases treatment costs, and even leads to the premature elimination of animals. In addition, failure to take effective measures in time will lead to widespread disease. The key to reducing the losses caused by mastitis lies in the early detection of the disease. The application of deep learning with powerful feature extraction capability in the medical field is receiving increasing attention. The main purpose of this study was to establish a deep learning network for buffalo quarter-level mastitis detection based on 3054 ultrasound images of udders from 271 buffaloes. Two data sets were generated with thresholds of somatic cell count (SCC) set as 2 × 105 cells/mL and 4 × 105 cells/mL, respectively. The udders with SCCs less than the threshold value were defined as healthy udders, and otherwise as mastitis-stricken udders. A total of 3054 udder ultrasound images were randomly divided into a training set (70%), a validation set (15%), and a test set (15%). We used the EfficientNet_b3 model with powerful learning capabilities in combination with the convolutional block attention module (CBAM) to train the mastitis detection model. To solve the problem of sample category imbalance, the PolyLoss module was used as the loss function. The training set and validation set were used to develop the mastitis detection model, and the test set was used to evaluate the network's performance. The results showed that, when the SCC threshold was 2 × 105 cells/mL, our established network exhibited an accuracy of 70.02%, a specificity of 77.93%, a sensitivity of 63.11%, and an area under the receiver operating characteristics curve (AUC) of 0.77 on the test set. The classification effect of the model was better when the SCC threshold was 4 × 105 cells/mL than when the SCC threshold was 2 × 105 cells/mL. Therefore, when SCC ≥ 4 × 105 cells/mL was defined as mastitis, our established deep neural network was determined as the most suitable model for farm on-site mastitis detection, and this network model exhibited an accuracy of 75.93%, a specificity of 80.23%, a sensitivity of 70.35%, and AUC 0.83 on the test set. This study established a 1/4 level mastitis detection model which provides a theoretical basis for mastitis detection in buffaloes mostly raised by small farmers lacking mastitis diagnostic conditions in developing countries. [ABSTRACT FROM AUTHOR]

Simple Summary: Shoulder lesions present a significant welfare concern, particularly among breeding sows. They are frequently linked to decreased mobility and loss of body condition during lactation. This research explores using RGB cameras and the potential of different computer vision methods for detecting and estimating their size. Findings indicate that these techniques hold promise in effectively identifying and quantifying lesion size. This could empower producers to proactively monitor sow welfare, facilitating timely detection and intervention for these lesions. Shoulder sores predominantly arise in breeding sows and often result in untimely culling. Reported prevalence rates vary significantly, spanning between 5% and 50% depending upon the type of crate flooring inside a farm, the animal's body condition, or an existing injury that causes lameness. These lesions represent not only a welfare concern but also have an economic impact due to the labor needed for treatment and medication. The objective of this study was to evaluate the use of computer vision techniques in detecting and determining the size of shoulder lesions. A Microsoft Kinect V2 camera captured the top-down depth and RGB images of sows in farrowing crates. The RGB images were collected at a resolution of 1920 × 1080. To ensure the best view of the lesions, images were selected with sows lying on their right and left sides with all legs extended. A total of 824 RGB images from 70 sows with lesions at various stages of development were identified and annotated. Three deep learning-based object detection models, YOLOv5, YOLOv8, and Faster-RCNN, pre-trained with the COCO and ImageNet datasets, were implemented to localize the lesion area. YOLOv5 was the best predictor as it was able to detect lesions with an mAP@0.5 of 0.92. To estimate the lesion area, lesion pixel segmentation was carried out on the localized region using traditional image processing techniques like Otsu's binarization and adaptive thresholding alongside DL-based segmentation models based on U-Net architecture. In conclusion, this study demonstrates the potential of computer vision techniques in effectively detecting and assessing the size of shoulder lesions in breeding sows, providing a promising avenue for improving sow welfare and reducing economic losses. [ABSTRACT FROM AUTHOR]