Search

Simple Summary: Identifying wildlife species is crucial in various wildlife monitoring tasks. In this paper, a wildlife image recognition approach is implemented based on deep learning with a joint adaptation network. This paper presents a joint adversarial learning approach and a cross-domain local and global representation learning approach. Utilizing the two approaches, a Deep Joint Adaptation Network model for wildlife image recognition is designed. The proposed model can yield high accuracy in wildlife image recognition and is beneficial to improve the generalization ability in complex environments. Our research is of the utmost importance for wildlife recognition and wildlife biodiversity monitoring. Wildlife recognition is of utmost importance for monitoring and preserving biodiversity. In recent years, deep-learning-based methods for wildlife image recognition have exhibited remarkable performance on specific datasets and are becoming a mainstream research direction. However, wildlife image recognition tasks face the challenge of weak generalization in open environments. In this paper, a Deep Joint Adaptation Network (DJAN) for wildlife image recognition is proposed to deal with the above issue by taking a transfer learning paradigm into consideration. To alleviate the distribution discrepancy between the known dataset and the target task dataset while enhancing the transferability of the model's generated features, we introduce a correlation alignment constraint and a strategy of conditional adversarial training, which enhance the capability of individual domain adaptation modules. In addition, a transformer unit is utilized to capture the long-range relationships between the local and global feature representations, which facilitates better understanding of the overall structure and relationships within the image. The proposed approach is evaluated on a wildlife dataset; a series of experimental results testify that the DJAN model yields state-of-the-art results, and, compared to the best results obtained by the baseline methods, the average accuracy of identifying the eleven wildlife species improves by 3.6 percentage points. [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: 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: Currently, more and more people keep dogs, and the gastrointestinal diseases of pet dogs have brought great losses to families. However, the condition of the dog's feces is closely related to the health of its stomach and intestines. We can know the intestinal condition of dogs in advance by scoring dog feces, and implement measures such as food adjustments. The PURINA FECAL SCORING CHART and the WALTHAM™ Faeces Scoring System are good at scoring dog feces visually, but some scoring experience is required. Therefore, this paper proposes an artificial intelligence method to automatically classify the condition of dog feces by combining their classification criteria with the assistance of animal experts. This method can achieve an accuracy of 88.27%, improving the diagnostic efficiency of veterinarians. In a natural environment, factors such as weathering and sun exposure will degrade the characteristics of dog feces; disturbances such as decaying wood and dirt are likely to make false detections; the recognition distinctions between different kinds of feces are slight. To address these issues, this paper proposes a fine-grained image classification approach for dog feces using MC-SCMNet under complex backgrounds. First, a multi-scale attention down-sampling module (MADM) is proposed. It carefully retrieves tiny feces feature information. Second, a coordinate location attention mechanism (CLAM) is proposed. It inhibits the entry of disturbance information into the network's feature layer. Then, an SCM-Block containing MADM and CLAM is proposed. We utilized the block to construct a new backbone network to increase the efficiency of fecal feature fusion in dogs. Throughout the network, we decrease the number of parameters using depthwise separable convolution (DSC). In conclusion, MC-SCMNet outperforms all other models in terms of accuracy. On our self-built DFML dataset, it achieves an average identification accuracy of 88.27% and an F 1 value of 88.91%. The results of the experiments demonstrate that it is more appropriate for dog fecal identification and maintains stable results even in complex backgrounds, which may be applied to dog gastrointestinal health checks. [ABSTRACT FROM AUTHOR]

Simple Summary: Thermal imaging is gaining popularity in poultry, swine, and dairy animal husbandry for detecting disease and distress. In this study, we present a depthwise separable inception subnetwork (DISubNet) for classifying pig treatments, offering two versions: DISubNetV1 and DISubNetV2. These lightweight models are compared to other deep learning models used for image classification. A forward-looking infrared (FLIR) camera captures thermal data for model training. Experimental results show the proposed models outperform others in classifying pig treatments using thermal images, achieving 99.96–99.98% accuracy with fewer parameters, potentially improving animal welfare and promoting sustainable production. Thermal imaging is increasingly used in poultry, swine, and dairy animal husbandry to detect disease and distress. In intensive pig production systems, early detection of health and welfare issues is crucial for timely intervention. Using thermal imaging for pig treatment classification can improve animal welfare and promote sustainable pig production. In this paper, we present a depthwise separable inception subnetwork (DISubNet), a lightweight model for classifying four pig treatments. Based on the modified model architecture, we propose two DISubNet versions: DISubNetV1 and DISubNetV2. Our proposed models are compared to other deep learning models commonly employed for image classification. The thermal dataset captured by a forward-looking infrared (FLIR) camera is used to train these models. The experimental results demonstrate that the proposed models for thermal images of various pig treatments outperform other models. In addition, both proposed models achieve approximately 99.96–99.98% classification accuracy with fewer parameters. [ABSTRACT FROM AUTHOR]

Simple Summary: The study focused on improving the detection of clinical bovine mastitis, the inflammation of the udder in cows as a response to intramammary infection, which can be identified by the presence of clots in the milk. Currently, automated milking systems do not detect this important disease very accurately. To address this, we developed a clots detection program using a neural network. This neural network was trained to recognize clots in milk samples from dairy cows by using a large number of pictures of milk filter socks, some with and some without clots. These pictures were divided into different sets for training, validating, and testing the program, respectively. The settings of the neural network were optimized using a genetic algorithm. The program's interpretations were explained using a method called integrated gradients. The program was found to be 100% accurate in identifying clots in the test pictures. This suggests that the method could be very useful for automatically checking for clinical mastitis on dairy farms, although further field validation through integration into the existing systems is needed. Automated milking systems (AMSs) already incorporate a variety of milk monitoring and sensing equipment, but the sensitivity, specificity, and positive predictive value of clinical mastitis (CM) detection remain low. A typical symptom of CM is the presence of clots in the milk during fore-stripping. The objective of this study was the development and evaluation of a deep learning model with image recognition capabilities, specifically a convolutional neural network (NN), capable of detecting such clots on pictures of the milk filter socks of the milking system, after the phase in which the first streams of milk have been discarded. In total, 696 pictures were taken with clots and 586 pictures without. These were randomly divided into 60/20/20 training, validation, and testing datasets, respectively, for the training and validation of the NN. A convolutional NN with residual connections was trained, and the hyperparameters were optimized based on the validation dataset using a genetic algorithm. The integrated gradients were calculated to explain the interpretation of the NN. The accuracy of the NN on the testing dataset was 100%. The integrated gradients showed that the NN identified the clots. Further field validation through integration into AMS is necessary, but the proposed deep learning method is very promising for the inline detection of CM on AMS farms. [ABSTRACT FROM AUTHOR]

Simple Summary: Cattle identification is necessary for precision feeding and management. Cattle muzzles have unique patterns, which can be used as a biometric identification key. This study aimed to identify cattle via a deep learning model based on muzzle images. Muzzle patterns were cropped from images using the YOLO v8-based image cropping model. Various artificial intelligence models based on neural networks were studied through transfer learning cropped images for cattle recognition with four optimizers. Several models showed a high prediction accuracy of over 97 percent, implicating the possibility for real farm usage. The objective of this study was to identify Hanwoo cattle via a deep-learning model using muzzle images. A total of 9230 images from 336 Hanwoo were used. Images of the same individuals were taken at four different times to avoid overfitted models. Muzzle images were cropped by the YOLO v8-based model trained with 150 images with manual annotation. Data blocks were composed of image and national livestock traceability numbers and were randomly selected and stored as train, validation test data. Transfer learning was performed with the tiny, small and medium versions of Efficientnet v2 models with SGD, RMSProp, Adam and Lion optimizers. The small version using Lion showed the best validation accuracy of 0.981 in 36 epochs within 12 transfer-learned models. The top five models achieved the best validation accuracy and were evaluated with the training data for practical usage. The small version using Adam showed the best test accuracy of 0.970, but the small version using RMSProp showed the lowest repeated error. Results with high accuracy prediction in this study demonstrated the potential of muzzle patterns as an identification key for individual cattle. [ABSTRACT FROM AUTHOR]

Simple Summary: Enabling the public to easily recognize water birds at hand has a positive effect on wetland bird conservation. An attention mechanism-based deep convolution neural network model (AM-CNN) is developed for water bird recognition. The model employs an effective strategy that enhances the perception of shallow image features in convolutional layers, and achieves up to 86.4% classification accuracy on our self-constructed image dataset of 548 global water bird species. The model is implemented as the mobile app of EyeBirds for smart phones. The app offers three main functions of bird image recognition, bird information and bird field survey to users. Overall, EyeBirds is useful to assist the public to easily recognize water birds and acquire bird knowledge. Enabling the public to easily recognize water birds has a positive effect on wetland bird conservation. However, classifying water birds requires advanced ornithological knowledge, which makes it very difficult for the public to recognize water bird species in daily life. To break the knowledge barrier of water bird recognition for the public, we construct a water bird recognition system (Eyebirds) by using deep learning, which is implemented as a smartphone app. Eyebirds consists of three main modules: (1) a water bird image dataset; (2) an attention mechanism-based deep convolution neural network for water bird recognition (AM-CNN); (3) an app for smartphone users. The waterbird image dataset currently covers 48 families, 203 genera and 548 species of water birds worldwide, which is used to train our water bird recognition model. The AM-CNN model employs attention mechanism to enhance the shallow features of bird images for boosting image classification performance. Experimental results on the North American bird dataset (CUB200-2011) show that the AM-CNN model achieves an average classification accuracy of 85%. On our self-built water bird image dataset, the AM-CNN model also works well with classification accuracies of 94.0%, 93.6% and 86.4% at three levels: family, genus and species, respectively. The user-side app is a WeChat applet deployed in smartphones. With the app, users can easily recognize water birds in expeditions, camping, sightseeing, or even daily life. In summary, our system can bring not only fun, but also water bird knowledge to the public, thus inspiring their interests and further promoting their participation in bird ecological conservation. [ABSTRACT FROM AUTHOR]