Search

Simple Summary: The aim of this study was to improve the hatching efficiency of duck eggs by automatically assessing the hatching characteristics of early hatching eggs. The timely and accurate detection of fertile and infertile eggs is an important research topic in the breeder egg hatching industry. Detecting infertile eggs early in the hatching process not only improves the hatching efficiency of duck eggs, but also brings benefits to hatching companies. In recent years, the rapid development of deep learning and computer vision technology has brought us new ideas. We propose a lightweight multi-target detection method based on deep learning to evaluate the hatching characteristics of duck eggs. The results show that the method could meet the requirements for accuracy and real-time detection in industrial production. Since it is difficult to accurately identify the fertilization and infertility status of multiple duck eggs on an incubation tray, and due to the lack of easy-to-deploy detection models, a novel lightweight detection architecture (LDA) based on the YOLOX-Tiny framework is proposed in this paper to identify sterile duck eggs with the aim of reducing model deployment requirements and improving detection accuracy. Specifically, the method acquires duck egg images through an acquisition device and augments the dataset using rotation, symmetry, and contrast enhancement methods. Then, the traditional convolution is replaced by a depth-wise separable convolution with a smaller number of parameters, while a new CSP structure and backbone network structure are used to reduce the number of parameters of the model. Finally, to improve the accuracy of the network, the method includes an attention mechanism after the backbone network and uses the cosine annealing algorithm in training. An experiment was conducted on 2111 duck eggs, and 6488 duck egg images were obtained after data augmentation. In the test set of 326 duck egg images, the mean average precision (mAP) of the method in this paper was 99.74%, which was better than the 94.92% of the YOLOX-Tiny network before improvement, and better than the reported prediction accuracy of 92.06%. The number of model parameters was only 1.93 M, which was better than the 5.03 M of the YOLOX-Tiny network. Further, by analyzing the concurrent detection of single 3 × 5, 5 × 7 and 7 × 9 grids, the algorithm achieved a single detection number of 7 × 9 = 63 eggs. The method proposed in this paper significantly improves the efficiency and detection accuracy of single-step detection of breeder duck eggs, reduces the network size, and provides a suitable method for identifying sterile duck eggs on hatching egg trays. Therefore, the method has good application prospects. [ABSTRACT FROM AUTHOR]

• Our proposed model has a small number of parameters while maintaining high accuracy. • The PA-AFF module is used instead of PA-FPN, allowing the model to pay attention to features at different scales. • Our proposed model can initially detect unfertilized eggs as early as the fourth day. Early hatching information detection of duck eggs is a crucial step in the duck egg hatching industry. In this study, we proposed a lightweight deep learning model AFF-YOLOX to detect the hatching information of multiple duck eggs on the standard hatching trays, meeting the speed requirements of real production. Based on YOLOX of networks structure, we added the AFF to the PA-FPN. Additionally, the input size of the image was changed according to the hatching tray and remove the redundant part of the network. The results showed that AFF-YOLOX could significantly improve the detection effect compared with the original YOLOX. The mAP was improved from 74.30% to 97.55%, the number of parameters was reduced from 99 M to 0.49 M, and the latency per image was decreased from 556 ms to 178 ms. AFF-YOLOX can detect abnormal eggs on incubation day 4 and can completely identify all abnormal eggs on incubation day 6. The results demonstrated that the optimization and lightweight methods we are effective and provides a technical reference for automatic detection of hatching information of duck eggs in the hatchery industry. [ABSTRACT FROM AUTHOR]

To address the problem that duck egg mortality is not easily detected at mid-incubation, this paper explored a method to detect mid-incubation egg activity information based on temperature drop curve (TDC) features. In this paper, we used a thermal infrared camera to obtain continuous thermal images of death fertilized duck eggs (DFDE) on the 16th day of incubation and alive fertilized duck eggs (AFDE) hatched for 16–19 days in a 20 °C environment. By observing the temperature drop curve of egg surface, we extracted and visualized five features that could reflect the activity information of duck eggs. And we used K-Nearest Neighbor (KNN), Naive Bayesian (NB) and Support Vector Machine (SVM) to establish the activity information detection models for different incubation days. The results showed that KNN could better distinguish the activity of eggs at the 16th and the 17th day of incubation, with F1-score of 85.43% and 85.98%, respectively. The SVM showed better results at the 18th and the 19th day of incubation, with F1-score of 90.57% and 96.3%, respectively. The experimental results demonstrated that the activity detection method based on the temperature drop curve features in this paper could efficiently and nondestructively detect the activity information of mid-incubation duck eggs, which provided a technical foundation for detecting the activity information of duck eggs at mid-incubation. • We built a collection platform for capturing thermal images of duck eggs. • 5 features extracted from duck eggs' temperature drop curves. • KNN can detect the activity information on the 16th and the 17th incubation day. • SVM can detect the activity information on the 18th and the 19th incubation day. [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]

• Proposed a duck flock daily behavior recognition model with good performance under low-light conditions. • The model was lightly improved with an 8.7 % reduction in the number of parameters. • The method in this study accurately monitors specific events and behavioral rhythms. • The proposed method can record the behavioral rhythms of ducks in real time. Accurate monitoring of animal behavioral rhythms is essential. Currently, it is challenging to identify the behavior of animals under low-light conditions. In this study, we proposed a deep learning model DHSW-YOLO (DH-SENet-WIoU-YOLO) to detect the daily behaviors of duck flocks under bright and dark conditions, meeting the speed requirement for real-time detection, using White Muscovy ducks (WMD) as the research object. Based on the YOLOv8 of network structure, we simplify the detection head of YOLOv8 and introduce the SENet attention mechanism and WIoU v3 loss function. The results showed that DHSW-YOLO could significantly improve the detection effect compared with the original YOLOv8. The mAP was improved from 92.2 % to 94.4 %, the Model size was reduced by 2.8 MB, the Inference time was faster by 1.2 ms, and the number of parameters were reduced by 8.7 %. The mAP of DHSW-YOLO under bright condition was 94.8 %, and that under dark condition was 93.6 %. This indicated that DHSW-YOLO could effectively monitor the behavior of WMD under bright and dark conditions. These results demonstrated that the lightweight and the optimization methods proposed in this paper are effective and provide a technical reference for the automated monitoring and warning system of duck flock behavior rhythms. [ABSTRACT FROM AUTHOR]

Simple Summary: In the realm of livestock management, accurately estimating the weight of pigs presents a critical yet challenging task, particularly in the dynamic environment of farms. Traditional methods often struggle due to the continuous movement of pigs and fluctuating conditions such as lighting. To address these challenges, our study focuses on developing a novel method that simplifies weight estimation while adapting to the constantly changing conditions of real-world pig farms. Our solution, the moving pig weight estimate algorithm based on deep vision (MPWEADV), marks a significant step in this direction. It employs advanced imaging technology to capture both the visual appearance and depth information of moving pigs. The central idea is to combine these two types of data for more accurate weight estimates than traditional methods could provide. To validate our proposed method, we replicated two recently published methods and demonstrated through experimental results that our pig weight estimation model could rapidly and accurately determine the weight of pigs in the challenging scenarios we constructed. This model operates in an unconstrained environment, providing real-time evaluation of pigs' weight, thereby offering data support for grading and adjusting breeding plans, indicating a wide range of potential applications. In the field of livestock management, noncontact pig weight estimation has advanced considerably with the integration of computer vision and sensor technologies. However, real-world agricultural settings present substantial challenges for these estimation techniques, including the impacts of variable lighting and the complexities of measuring pigs in constant motion. To address these issues, we have developed an innovative algorithm, the moving pig weight estimate algorithm based on deep vision (MPWEADV). This algorithm effectively utilizes RGB and depth images to accurately estimate the weight of pigs on the move. The MPWEADV employs the advanced ConvNeXtV2 network for robust feature extraction and integrates a cutting-edge feature fusion module. Supported by a confidence map estimator, this module effectively merges information from both RGB and depth modalities, enhancing the algorithm's accuracy in determining pig weight. To demonstrate its efficacy, the MPWEADV achieved a root-mean-square error (RMSE) of 4.082 kg and a mean absolute percentage error (MAPE) of 2.383% in our test set. Comparative analyses with models replicating the latest research show the potential of the MPWEADV in unconstrained pig weight estimation practices. Our approach enables real-time assessment of pig conditions, offering valuable data support for grading and adjusting breeding plans, and holds broad prospects for application. [ABSTRACT FROM AUTHOR]

• Expanded the insufficient citrus greening diseased leaves to improve the generalization of the classification network. The diseased leaves with insufficient are expanded to strengthen the generalization of the classification network. Meanwhile, the generated citrus yellow dragon disease leaf fake data has the phenotypic characteristics of the real data, and the yellow dragon disease researchers are unable to identify the generated data real and fake, testing out TRL-GAN to achieve certain generation effect. • Effective background culling of direct collection of diseased leaf data in the field to achieve shooting effect under indoor conditions. • To make the classification network achieve a certain improvement in the accuracy rate of citrus greening diseased leaves. The monitoring and prevention and control of citrus yellow dragon disease is a significant measure to ensure citrus production. If yellow dragon disease appears in citrus orchards, it will cause root rot, fruit deformation and wilting of fruit trees, which will eventually spread to every fruit tree in the whole orchard and cause the death of fruit trees, so it is very meaningful to detect the symptoms of citrus yellow dragon disease early and take appropriate treatment and prevention measures. Pratically, the orchard owner will remove the corresponding fruit trees as soon as they are found to be infected with Huanglong disease, so that it is extremely problematic to obtain a large number of Huanglong disease leaf data. Meanwhile, due to the uncertainty of the pathological trait distribution of citrus yellow dragon disease leaves and the extreme shortage of data, the convolutional neural network model learned in a small number of samples is not capable of generalization. In order to improve the accuracy and generalization of Citrus Greening Disease recognition algorithm, this paper introduces Texture Reconstruction Loss CycleGAN(TRL-GAN) to generate citrus diseased leaf data in realistic scene to increase the richness of samples, and thus proposes the Recognizing Citrus Greening Based on TRL-GAN(RCG TRL-GAN). This algorithm firstly performs background culling by using the instance segmentation network Mask RCNN for realistic scenes citrus yellow dragon disease mottled, zinc deficiency, magnesium deficiency, leaf veins yellowing and other corresponding symptomatic leaves, then introduces texture reconstruction loss improvement CycleGAN as training and migrates the diseased leaf style to ordinary green leaves for data expansion, and finally uses the expanded dataset to train the convolutional neural network. Experimental results on the constructed dataset of 4516 images (762 mottled, 749 Zn deficient, 737 Mg deficient, 721 Vein yellowing, 783 Diachyma yellowing, 764 green leaves) reveal that TRL-GAN has 13.49% and 1.1% improvement in FID and KID, respectively, relative to the original structure CycleGAN, and has been identified by six citrus yellow dragon disease experts and three vision professionals identify that the fake data generated by TRL-GAN have similarity with the leaf pathological characteristics and real data, and also by using T-SNE technique it is observed that the real data have similar distribution with the generated fake data in two-dimensional plane. Meanwhile, the more outstanding accuracy performance in the classification network is ResNeXt101 with 97.45% accuracy, and the average accuracy of RCG TRL-GAN technique in the recognition of classification network is improved 2.76%. The study proves that the RCG TRL-GAN effectively improves the citrus greening disease phenotype data generation and recognition, and can provide method reference for the expansion and recognition of complex plant disease phenotype images. [ABSTRACT FROM AUTHOR]

• Standardized ear tag data via transformation and cleaning. • Conducted time series analysis on daily pig data. • Analyzed seasonal trends in pig population data. • Classified ear tag data using six methods. The behavioral and physiological patterns of pigs are key indicators for assessing their health status. This study aims to explore the differences in activity level and body temperature variation patterns between normal and abnormal pigs. In view of the characteristics of pig ear tag data, such as high volatility, unclear features and strong randomness, we adopted various processing and analysis methods. The main work of this paper includes: (1) Preprocessing and integrating pig ear tag data to improve data quality; (2) Performing similarity and time series analysis on the daily data of each pig to identify the change patterns of activity level and body temperature; (3) Performing seasonal feature analysis and trend change analysis on the data of the pig population, finding the gap between abnormal pigs and the population pattern, and classifying abnormal and normal pigs. The main results and conclusions of this paper are as follows: (1) Pigs are most active in two time periods: 5:00 to 10:00 in the morning and 14:00 to 18:00 in the afternoon; (2) The activity duration of lame pigs is significantly lower than that of normal pigs, while the activity duration of pigs under other abnormal conditions is not much different; (3) Although the ear tag temperature data is affected by the pig's behavior, abnormal pigs can be found by the characteristic of low temperature trend within a day. (4) Random forest algorithm can effectively classify normal and abnormal pigs, with an accuracy of 0.879. The research results of this paper have important significance and value for realizing the refined management of pigs, improving the breeding efficiency, and ensuring the health and production safety of pigs. [ABSTRACT FROM AUTHOR]

The brown rice planthopper (Nilaparvata lugens Stal) is one of the main pests of rice. The rapid and accurate detection of brown rice planthoppers (BRPH) can help treat rice in time. Due to the small size, large number and complex background of BRPHs, image detection of them is challenging. In this paper, a two-layer detection algorithm based on deep learning technology is proposed to detect them. The algorithm for both layers is the Faster RCNN (regions with CNN features). To effectively utilize the computing resources, different feature extraction networks have been selected for each layer. In addition, the second layer detection network was optimized to improve the final detection performance. The detection results of the two-layer detection algorithm were compared with the detection results of the single-layer detection algorithm. The detection results of the two-layer detection algorithm for detecting different populations and numbers of BRPHs were tested, and the test results were compared with YOLO v3, a deep learning target detection network. The test results show that the detection results of the two-layer detection algorithm were significantly better than those of the single-layer detection algorithm. In the tests for different numbers of BRPHs, the average recall rate of this algorithm was 81.92%, and the average accuracy was 94.64%; meanwhile, the average recall rate of YOLO v3 was 57.12%, and the average accuracy rate was 97.36%. In the experiment with different ages of BRPHs, the average recall rate of the algorithm was 87.67%, and the average accuracy rate was 92.92%. In comparison, for the YOLO v3, the average recall rate was 49.60%, and the average accuracy rate was 96.48%. [ABSTRACT FROM AUTHOR]

• Multispectral images taken by drones can be used to detect fire blight of apple trees from the canopy. • A feature selection method called mRMR was used to select the optimal combination of vegetation indices to detect fire blight. • RVI, ARI, and TVI indices are useful for the detection of fire blight in apple trees. Apple fire blight is a common disease that seriously damages the growth of apple trees. It is urgent to detect the severity difference and spatial distribution of its infection in time and accurately. In this study, we used the DJI Matrice 200 multi-rotor UAV equipped with the MicaSense RedEdge-M multispectral camera to obtain the multispectral images of apple tree canopies. Then, based on the Minimum Redundancy Maximum Relevance (mRMR) algorithm, we selected the Ratio Vegetation Index (RVI), Anthocyanin Reflectance Index (ARI) and Triangular Vegetation Index (TVI) from 20 candidate vegetation indices as the optimal feature combinations. And then we use the isolation forest (iForest) algorithm to detect the abnormal values. The samples with the abnormal values removed were used as input to construct apple fire blight detection models using decision trees, Random Forest (RF) and Support Vector Machine (SVM) classification algorithms, respectively. The results show that the overall accuracy of the RF model reaches 94.0%, which is 6.0% and 10.0% higher than the SVM model and the decision tree model, respectively. The Kappa coefficient of the RF model is 0.904, which is the highest among all models, and the omission error and commission error are also the smallest. For healthy samples, slightly infected samples and seriously infected samples, the omission error and commission error were 0, 7.69%, 13.34%, 7.14% and 9.09%, 0, respectively. The research results prove the feasibility of UAV multi-spectral remote sensing images to detect apple fire blight. [ABSTRACT FROM AUTHOR]

With the rapid development of microelectronic technology, increasing wearable devices are available for us in daily lives. These wearable devices are usually powered by batteries, so the endurance of wearable devices is limited by battery capacity. Biomechanical energy harvesting (EH) is a promising approach to extend the endurance or replace batteries to power microelectronic devices. In this paper, we would first review the different types of EH devices and analyze the key technologies. Secondly, to compare the advantages and disadvantages of different EH devices, the design guidelines of the EH device is proposed. According to the design guidelines, an EH device with a weight of only 110 g is designed, which is lighter than the suspended-load backpack (38 kg) and the knee harvester (1.6 kg). Our EH device is able to convert the vibrations energy generated by the motion of lower limbs into electrical energy. Finally, to verify whether our EH device meets the design guidelines, three sets of experiment are conducted to evaluate the performance of the EH device. Experiment A is used to monitor the metabolic energy and electricity energy. According to experiment data, we calculate the COH and TCOH of EH device. The lowest COH and TCOH are 58 and 59, respectively. The TCOH of our EH device is higher than suspended-load backpack (30.7) and the knee harvester (13.6). Experiment B is used to test the adaptability of the EH device under the different conditions of terrains and walking speeds. The EH device is able to harvest energy in different terrains (up and down stair, at the treadmill with a slope of 0 ° , 5 ° and 10 ° ) and at different speeds(4 km/h~8 km/h). The converted electrical power is up to 7.71 mW during walking at the speed of 8 km/h and is up to 5.28 mW when going up stairs. Experiment C is conducted to investigate the influence of the EH device on human motion by measuring the torque of the ankle, knee, and hip joints. When comparing the curves of torque, the EH device does not influence the biological moment of joints, indicating the EH device does not interfere with the movement. At the same time, another method to calculate the TCOH by calculating the net work done by the muscle in a gait cycle is proposed. When comparing the TCOH calculated by the metabolic energy with the TCOH calculated by the additional work done by the muscle, the results are basically the same. Meanwhile, the variation of the latter calculation result is smaller, indicating the method proposed by us is more precise. [ABSTRACT FROM AUTHOR]