Search

Simple Summary: The use of computer vision technology has improved the effectiveness of individual sheep identification, but existing methods face challenges such as large parameter sizes, slow recognition speeds, and difficult deployment. To address this issue, we have made improvements and optimizations based on the Retinaface face recognition model to create a balanced speed-accuracy sheep face recognition model. The optimized model has fewer parameters, simpler computations, faster inference speeds, and higher recognition accuracy, making it well-suited for deployment on resource-constrained edge devices. This research is expected to promote the application of deep learning-based sheep face recognition methods in production. The recognition of sheep faces based on computer vision has improved the efficiency and effectiveness of individual sheep identification, providing technical support for the development of smart farming. However, current recognition models have problems such as large parameter sizes, slow recognition speed, and difficult deployment. Therefore, this paper proposes an efficient and fast basic module called Eblock and uses it to build a lightweight sheep face recognition model called SheepFaceNet, which achieves the best balance between speed and accuracy. SheepFaceNet includes two modules: SheepFaceNetDet for detection and SheepFaceNetRec for recognition. SheepFaceNetDet uses Eblock to construct the backbone network to enhance feature extraction capability and efficiency, designs a bidirectional FPN layer (BiFPN) to enhance geometric location ability, and optimizes the network structure, which affects inference speed, to achieve fast and accurate sheep face detection. SheepFaceNetRec uses Eblock to construct the feature extraction network, uses ECA channel attention to improve the effectiveness of feature extraction, and uses multi-scale feature fusion to achieve fast and accurate sheep face recognition. On our self-built sheep face dataset, SheepFaceNet recognized 387 sheep face images per second with an accuracy rate of 97.75%, achieving an advanced balance between speed and accuracy. This research is expected to further promote the application of deep-learning-based sheep face recognition methods in production. [ABSTRACT FROM AUTHOR]

Simple Summary: Constructing a contactless pig mass estimation method through computer vision technology can help us to adjust our pig breeding program to improve production efficiency. Due to the complexity of the actual production environment, there are few reports on pig mass estimation in an unconstrained environment. In this study, we constructed a pig mass estimate model based on deep learning without constraint. The experimental results proved that the pig body mass estimation model constructed in this paper can quickly and accurately obtain the body mass of pigs. The model can evaluate the body quality of sows in real-time in an unconstrained environment, thereby providing data support for grading and adjusting breeding plans, and has broad application prospects. The body mass of pigs is an essential indicator of their growth and health. Lately, contactless pig body mass estimation methods based on computer vision technology have gained attention thanks to their potential to improve animal welfare and ensure breeders' safety. Nonetheless, current methods require pigs to be restrained in a confinement pen, and no study has been conducted in an unconstrained environment. In this study, we develop a pig mass estimation model based on deep learning, capable of estimating body mass without constraints. Our model comprises a Mask R-CNN-based pig instance segmentation algorithm, a Keypoint R-CNN-based pig keypoint detection algorithm and an improved ResNet-based pig mass estimation algorithm that includes multi-branch convolution, depthwise convolution, and an inverted bottleneck to improve accuracy. We constructed a dataset for this study using images and body mass data from 117 pigs. Our model achieved an RMSE of 3.52 kg on the test set, which is lower than that of the pig body mass estimation algorithm with ResNet and ConvNeXt as the backbone network, and the average estimation speed was 0.339 s·frame−1 Our model can evaluate the body quality of pigs in real-time to provide data support for grading and adjusting breeding plans, and has broad application prospects. [ABSTRACT FROM AUTHOR]

Simple Summary: Aggressive behavior can cause severe harm to pigs, especially in poor housing conditions, leading to disease and even death, which causes significant losses for the pig farm. Therefore, the automatic and accurate recognition of aggressive behavior of commercially housed pigs is important for pig farm production management. In this study, we proposed a video behavior recognition method based on the temporal shift module (TSM) that can detect whether aggressive behavior occurred in pig groups automatically. TSM is a convolutional neural network module to process video sequence data. Experimental results demonstrated that the method can recognize pig aggression effectively, which helps improve the use of automated management techniques in pig farming. Aggressive behavior among pigs is a significant social issue that has severe repercussions on both the profitability and welfare of pig farms. Due to the complexity of aggression, recognizing it requires the consideration of both spatial and temporal features. To address this problem, we proposed an efficient method that utilizes the temporal shift module (TSM) for automatic recognition of pig aggression. In general, TSM is inserted into four 2D convolutional neural network models, including ResNet50, ResNeXt50, DenseNet201, and ConvNext-t, enabling the models to process both spatial and temporal features without increasing the model parameters and computational complexity. The proposed method was evaluated on the dataset established in this study, and the results indicate that the ResNeXt50-T (TSM inserted into ResNeXt50) model achieved the best balance between recognition accuracy and model parameters. On the test set, the ResNeXt50-T model achieved accuracy, recall, precision, F1 score, speed, and model parameters of 95.69%, 95.25%, 96.07%, 95.65%, 29 ms, and 22.98 M, respectively. These results show that the proposed method can effectively improve the accuracy of recognizing pig aggressive behavior and provide a reference for behavior recognition in actual scenarios of smart livestock farming. [ABSTRACT FROM AUTHOR]

Simple Summary: The accurate identification of individual animals is an important step in precision breeding. However, the traditional identification methods have large defects. With the continuous development of computer vision and deep learning technologies, it is possible to establish accurate biological recognition models. In this study, we built a lightweight sheep face recognition model using convolutional neural networks (CNNs) to face the challenges in sheep identity recognition. The model not only achieved high accuracy in recognition tasks but also was friendly for edge devices. The research results indicate that the proposed recognition model can identify sheep accurately and can be further deployed on the mobile end. The accurate identification of sheep is crucial for breeding, behavioral research, food quality tracking, and disease prevention on modern farms. As a result of the time-consuming, expensive, and unreliable problems of traditional sheep-identification methods, relevant studies have built sheep face recognition models to recognize sheep through facial images. However, the existing sheep face recognition models face problems such as high computational costs, large model sizes, and weak practicality. In response to the above issues, this study proposes a lightweight sheep face recognition model named LSR-YOLO. Specifically, the ShuffleNetv2 module and Ghost module were used to replace the feature extraction module in the backbone and neck of YOLOv5s to reduce floating-point operations per second (FLOPs) and parameters. In addition, the coordinated attention (CA) module was introduced into the backbone to suppress non-critical information and improve the feature extraction ability of the recognition model. We collected facial images of 63 small-tailed Han sheep to construct a sheep face dataset and further evaluate the proposed method. Compared to YOLOv5s, the FLOPs and parameters of LSR-YOLO decreased by 25.5% and 33.4%, respectively. LSR-YOLO achieved the best performance on the sheep face dataset, and the mAP@0.5 reached 97.8% when the model size was only 9.5 MB. The experimental results show that LSR-YOLO has significant advantages in recognition accuracy and model size. Finally, we integrated LSR-YOLO into mobile devices and further developed a recognition system to achieve real-time recognition. The results show that LSR-YOLO is an effective method for identifying sheep. The method has high recognition accuracy and fast recognition speed, which gives it a high application value in mobile recognition and welfare breeding. [ABSTRACT FROM AUTHOR]

Simple Summary: The disappearance of many reptiles and amphibian species is directly and indirectly connected with habitat modification, introducing invasive species, disease, pollution, and climate change. Monitoring endangered species is essential for conservation action to mitigate the predominant threats to endangered species. According to wildlife researchers, visual information provides definitive evidence of an animal's distribution patterns and activity within an environmental context. At the Department of Biology and The Ingram School of Engineering at Texas State University and Texas A&M University, we collaborated on a camera trap project to monitor species from images in Texas, USA. We developed a framework to analyze the acquired images using artificial intelligence-driven technology and computer vision methods. The project aims to classify three broad groups of herpetofaunal species (i.e., toads/frogs, lizards, and snakes) from camera trap images with deep learning architectures. The experiment includes balancing the imbalanced dataset, investigating several image preprocessing techniques, and augmentation procedures. The classification results present tremendous prospects for automated species identification from challenging biological image data. The research outcome is essential to the academic community and wildlife researchers for conservation and monitoring purpose. Accurate identification of animal species is necessary to understand biodiversity richness, monitor endangered species, and study the impact of climate change on species distribution within a specific region. Camera traps represent a passive monitoring technique that generates millions of ecological images. The vast numbers of images drive automated ecological analysis as essential, given that manual assessment of large datasets is laborious, time-consuming, and expensive. Deep learning networks have been advanced in the last few years to solve object and species identification tasks in the computer vision domain, providing state-of-the-art results. In our work, we trained and tested machine learning models to classify three animal groups (snakes, lizards, and toads) from camera trap images. We experimented with two pretrained models, VGG16 and ResNet50, and a self-trained convolutional neural network (CNN-1) with varying CNN layers and augmentation parameters. For multiclassification, CNN-1 achieved 72% accuracy, whereas VGG16 reached 87%, and ResNet50 attained 86% accuracy. These results demonstrate that the transfer learning approach outperforms the self-trained model performance. The models showed promising results in identifying species, especially those with challenging body sizes and vegetation. [ABSTRACT FROM AUTHOR]

Simple Summary: Real-time and automatic detection of chickens such as laying hens and broilers is the cornerstone of precision poultry farming. For laying hens, it is more challenging under cage-free conditions comparing to caged systems. In this study, we developed a deep learning model (YOLOv5x-hens) to monitor hens' behaviors in cage-free facilities. More than 1000 images were used to train the model and an additional 200 images were adopted to test it. The newly developed YOLOv5x-hens was tested with stable performances in detecting birds under different lighting intensities, angles, and ages over 8 weeks. According to further data analysis, the model performed efficiently in real-time detection with an overall accuracy more than 95%, which is the key step for the tracking of individual birds for evaluation of production and welfare. However, there are still some limitations of the current version of the model. Error detections were caused by highly overlapped stock, uneven light intensity, and images occluded by equipment (i.e., drinking lines and feeders). Future research is needed to address those issues for a higher detection rate. The current study provides technical basis for developing a machine vision system for tracking individual birds for evaluation of animals' behaviors and welfare status in commercial cage-free houses. Real-time and automatic detection of chickens (e.g., laying hens and broilers) is the cornerstone of precision poultry farming based on image recognition. However, such identification becomes more challenging under cage-free conditions comparing to caged hens. In this study, we developed a deep learning model (YOLOv5x-hens) based on YOLOv5, an advanced convolutional neural network (CNN), to monitor hens' behaviors in cage-free facilities. More than 1000 images were used to train the model and an additional 200 images were adopted to test it. One-way ANOVA and Tukey HSD analyses were conducted using JMP software (JMP Pro 16 for Mac, SAS Institute, Cary, North Caronia) to determine whether there are significant differences between the predicted number of hens and the actual number of hens under various situations (i.e., age, light intensity, and observational angles). The difference was considered significant at p < 0.05. Our results show that the evaluation metrics (Precision, Recall, F1 and mAP@0.5) of the YOLOv5x-hens model were 0.96, 0.96, 0.96 and 0.95, respectively, in detecting hens on the litter floor. The newly developed YOLOv5x-hens was tested with stable performances in detecting birds under different lighting intensities, angles, and ages over 8 weeks (i.e., birds were 8–16 weeks old). For instance, the model was tested with 95% accuracy after the birds were 8 weeks old. However, younger chicks such as one-week old birds were harder to be tracked (e.g., only 25% accuracy) due to interferences of equipment such as feeders, drink lines, and perches. According to further data analysis, the model performed efficiently in real-time detection with an overall accuracy more than 95%, which is the key step for the tracking of individual birds for evaluation of production and welfare. However, there are some limitations of the current version of the model. Error detections came from highly overlapped stock, uneven light intensity, and images occluded by equipment (i.e., drinking line and feeder). Future research is needed to address those issues for a higher detection. The current study established a novel CNN deep learning model in research cage-free facilities for the detection of hens, which provides a technical basis for developing a machine vision system for tracking individual birds for evaluation of the animals' behaviors and welfare status in commercial cage-free houses. [ABSTRACT FROM AUTHOR]