Search Results (569)

Crop yields are influenced by various factors, including seed quality and environmental conditions. Detecting seed vigor is a critical task for seed researchers, as it plays a vital role in seed quality assessment. Traditionally, this evaluation was performed manually, which is time-consuming and labor-intensive. To address this limitation, this study integrates the ConvUpDownModule (a customized convolutional module), C2f-DSConv(C2f module with Integrated Dynamic Snake Convolution), and T-SPPF (the SPPF module integrated with the transformer multi-head attention mechanism) into the VT-YOLOv8-Seg network (the improved YOLOv8-Seg Network), an enhancement of the YOLOv8-Seg architecture. The ConvUpDownModule reduces the computational complexity and model parameters. The C2f-DSConv leverages flexible convolutional kernels to enhance the accuracy of maize germ edge segmentation. The T-SPPF integrates global information to improve multi-scale segmentation performance. The proposed model is designed for detecting and segmenting maize seeds and germs, facilitating seed germination detection and germination speed computation. In detection tasks, the VT-YOLOv8-Seg model achieved 97.3% accuracy, 97.9% recall, and 98.5% mAP50, while in segmentation tasks, it demonstrated 97.2% accuracy, 97.7% recall, and 98.2% mAP50. Comparative experiments with Mask R-CNN, YOLOv5-Seg, and YOLOv7-Seg further validated the superior performance of our model in both detection and segmentation. Additionally, the impact of seed aging on maize seed growth and development was investigated through artificial aging studies. Key metrics such as germination rate and germ growth speed, both closely associated with germination vigor, were analyzed, demonstrating the effectiveness of the proposed approach for seed vigor assessment. Full article

This study addresses the issue of energy efficiency evaluation for rural residential buildings and proposes a method for facade recognition based on an improved Mask R-CNN network model. By introducing the Coordinate Attention (CA) mechanism module, the quality of feature extraction and detection accuracy is enhanced. Experimental results demonstrate that this method effectively recognizes and segments windows, doors, and other components on building facades, accurately extracting key information, such as their dimensions and positions. For energy consumption simulation, this study utilized the Ladybug Tool in the Grasshopper plugin, combined with actual collected facade data, to assess and simulate the energy consumption of rural residences. By setting building envelope parameters and air conditioning operating parameters, detailed calculations of energy consumption for different orientations, window-to-wall ratios, and sunshade lengths were performed. The results show that the improved Mask R-CNN network model plays a crucial role in quickly and accurately extracting building parameters, providing reliable data support for energy consumption evaluation. Finally, through case studies, specific energy-saving retrofit suggestions were proposed, offering robust technical support and practical guidance for energy optimization in rural residences. Full article

Precision agriculture seeks to optimize crop yields while minimizing resource use. A key challenge is achieving uniform pesticide spraying to prevent crop damage and environmental contamination. Water-sensitive paper (WSP) is a common tool used for assessing spray quality, as it visually registers droplet impacts through color change. This work introduces a smartphone-based solution for capturing WSP images within vegetation, offering a tool for farmers to assess spray quality in real-world conditions. To achieve this, two approaches were explored: classical computer vision techniques and machine learning (ML) models (YOLOv8, Mask-RCNN, and Cellpose). Addressing the challenges of limited real-world data and the complexity of manual annotation, a programmatically generated synthetic dataset was employed to enable sim-to-real transfer learning. For the task of WSP segmentation within vegetation, YOLOv8 achieved an average Intersection over Union of 97.76%. In the droplet detection task, which involves identifying individual droplets on WSP, Cellpose achieved the highest precision of 96.18%, in the presence of overlapping droplets. While classical computer vision techniques provided a reliable baseline, they struggled with complex cases. Additionally, ML models, particularly Cellpose, demonstrated accurate droplet detection even without fine-tuning. Full article

A comprehensive understanding of the compositions and physicochemical properties of coal-based liquids is conducive to the rapid development of multipurpose, high-performance, and high-value functional chemicals. However, because of their complex compositions, coal-based liquids generate two-dimensional gas chromatography (GC × GC) chromatograms that are very complex and very time consuming to analyze. Therefore, the development of a method for accurately and rapidly analyzing chromatograms is crucial for understanding the chemical compositions and structures of coal-based liquids, such as direct coal liquefaction (DCL) oils and coal tar. In this study, DCL oils were distilled and qualitatively analyzed using GC × GC chromatograms. A deep-learning (DL) model was used to identify spectral features in GC × GC chromatograms and predominantly categorize the corresponding DCL oils as aliphatic alkanes, cycloalkanes, mono-, bi-, tri-, and tetracyclic aromatics. Regional labels associated with areas in the GC × GC chromatograms were fed into the mask-region-based convolutional neural network’s (Mask R-CNN’s) algorithm. The Mask R-CNN accurately and rapidly segmented the GC × GC chromatograms into regions representing different compounds, thereby automatically qualitatively classifying the compounds according to their spots in the chromatograms. Results show that the Mask R-CNN model’s accuracy, precision, recall, F1 value, and Intersection over Union (IoU) value were 93.71%, 96.99%, 96.27%, 0.95, and 0.93, respectively. DL is effective for visually comparing GC × GC chromatograms to analyze the compositions of chemical mixtures, accelerating GC × GC chromatogram interpretation and compound characterization and facilitating comparisons of the chemical compositions of multiple coal-based liquids produced in the coal and petroleum industry. Applying DL to analyze chromatograms improves analysis efficiency and provides a new method for analyzing GC × GC chromatograms, which is important for fast and accurate analysis. Full article

In this paper, we propose a recommendation method for food intake order based on the glycemic index (GI) using deep learning to reduce rapid blood sugar spikes during meals. The foods in a captured image are classified through a food detection network. The GIs for the detected foods are found by matching their names or categories with the information stored in the database. If the detected food name or category is not found in the database, the food information is found from a public API. The food is classified into one of the food categories based on nutrients, and the median GI of the corresponding category is assigned to the food. The food intake order is recommended from the lowest to the highest GI. We implemented a web service that visualizes the food analysis results and the recommended food intake order. In experimental results, the average inference time and accuracy were 57.1 ms and 98.99% for Mask R-CNN, respectively, and 24.4 ms and 91.72% for YOLOv11, respectively. Full article

Airport runways, as the core part of airports, belong to vital national infrastructure, and the target detection and segmentation of airport runways in remote sensing images using deep learning methods have significant research value. Most of the existing airport target detection methods based on deep learning rely on horizontal bounding boxes for localization, which often contain irrelevant background information. Moreover, when detecting multiple intersecting airport runways in a single remote sensing image, issues such as false positives and false negatives are apt to occur. To address these challenges, this study proposes an end-to-end remote sensing image airport runway detection and segmentation method based on an improved Mask RCNN (CR-Mask RCNN). The proposed method uses a rotated region generation network instead of a non-rotated region generation network, allowing it to generate rotated bounding boxes that fit the shape of the airport runway more closely, thus avoiding the interference of a large amount of invalid background information brought about by horizontal bounding boxes. Furthermore, the method incorporates an attention mechanism into the backbone feature extraction network to allocate attention to different airport runway feature map scales, which enhances the extraction of local feature information, captures detailed information more effectively, and reduces issues of false positives and false negatives when detecting airport runway targets. The results indicate that, when comparing horizontal bounding boxes with rotated bounding boxes for detecting and segmenting airport runways, the latter are more precise for complex backgrounds. Furthermore, incorporating an attention mechanism enhances the accuracy of airport runway recognition, making it highly effective and practical. Full article

Measurements of tooth size for estimating inter-arch tooth size discrepancies and inter-tooth distances, essential for orthodontic diagnosis and treatment, are primarily done using traditional methods involving plaster models and calipers. These methods are time-consuming and labor-intensive, requiring multiple steps. With advances in cone-beam computerized tomography (CBCT) and intraoral scanning technology, these processes can now be automated through computer analyses. This study proposes a multi-step computational method for measuring mesiodistal tooth widths and inter-tooth distances, applicable to both CBCT and scan images of plaster models. The first step involves 3D segmentation of the upper and lower teeth using CBCT, combining results from sagittal and panoramic views. For intraoral scans, teeth are segmented from the gums. The second step identifies the teeth based on an adaptively estimated jaw midline using maximum intensity projection. The third step uses a decentralized convolutional neural network to calculate key points representing the parameters. The proposed method was validated against manual measurements by orthodontists using plaster models, achieving an intraclass correlation coefficient of 0.967 and a mean absolute error of less than 1 mm for all tooth types. An analysis of variance test confirmed the statistical consistency between the method’s measurements and those of human experts. Full article

In current engineering applications, target detection based on power vision neural networks has problems with low accuracy and difficult defect recognition. Thus, this paper proposes a high-precision substation equipment defect recognition algorithm based on the Mask R-CNN algorithm framework to achieve high-precision substation equipment defect monitoring. The effectiveness of the Mask R-CNN algorithm is compared and analyzed in substation equipment defect recognition and the applicability of the Mask R-CNN algorithm in edge computing. According to different types of substation equipment defect characteristics, substation equipment defect recognition guidelines were developed. The guideline helps to calibrate the existing training set and build defect recognition models for substation equipment based on different algorithms. In the end, the system based on a power edge vision neural network was built. The feasibility and accuracy of the algorithm was verified by model training and actual target detection results. Full article

Effective management of malignant weeds is critical to soybean growth. This study focuses on addressing the critical challenges of targeted spraying operations for malignant weeds such as Cirsium setosum, which severely threaten soybean yield in soybean fields. Specifically, this research aims to tackle key issues in plant protection operations, including the precise identification of weeds, the lightweight deployment of segmentation models, real-time requirements for spraying operations, and the generalization ability of models in diverse field environments. To address these challenges, this study proposes an improved weed instance segmentation model based on YOLOv8s-Seg, named FCB-YOLOv8s-Seg, for targeted spraying operations in soybean fields. The FCB-YOLOv8s-Seg model incorporates a lightweight backbone network to accelerate computations and reduce model size, with optimized Squeeze-and-Excitation Networks (SENet) and Bidirectional Feature Pyramid Network (BiFPN) modules integrated into the neck network to enhance weed recognition accuracy. Data collected from real soybean field scenes were used for model training and testing. The results of ablation experiments revealed that the FCB-YOLOv8s-Seg model achieved a mean average precision of 95.18% for bounding box prediction and 96.63% for segmentation, marking an increase of 5.08% and 7.43% over the original YOLOv8s-Seg model. While maintaining a balanced model scale, the object detection and segmentation accuracy of this model surpass other existing classic models such as YOLOv5s-Seg, Mask-RCNN, and YOLACT. The detection results in different scenes show that the FCB-YOLOv8s-Seg model performs well in fine-grained feature segmentation in complex scenes. Compared with several existing classical models, the FCB-YOLOv8s-Seg model demonstrates better performance. Additionally, field tests on plots with varying weed densities and operational speeds indicated an average segmentation rate of 91.30%, which is 6.38% higher than the original model. The proposed algorithm shows higher accuracy and performance in practical field instance segmentation tasks and is expected to provide strong technical support for promoting targeted spray operations. Full article

Background: Microcalcifications in the breast are often an early warning sign of breast cancer, and their accurate detection is crucial for the early discovery and management of the disease. In recent years, deep learning technology, particularly models based on object detection, has significantly improved the ability to detect microcalcifications. This study aims to use the advanced YOLO-v8 object detection algorithm to identify breast microcalcifications and explore its advantages in terms of performance and clinical application. Methods: This study collected mammograms from 7615 female participants, with a dataset including 10,323 breast images containing microcalcifications. We used the YOLO-v8 model for microcalcification detection and trained and validated the model using five-fold cross-validation. The model’s performance was evaluated through metrics such as accuracy, recall, F1 score, mAP50, and mAP50-95. Additionally, this study explored the potential applications of this technology in clinical practice. Results: The YOLO-v8 model achieved an mAP50 of 0.921, an mAP50-95 of 0.709, an F1 score of 0.82, a detection accuracy of 0.842, and a recall rate of 0.796 in breast microcalcification detection. Compared to previous similar deep learning object detection techniques like Mask R-CNN, YOLO-v8 has shown improvements in both speed and accuracy. Conclusions: YOLO-v8 outperforms traditional detection methods in detecting breast microcalcifications. Its multi-scale detection capability significantly enhances both speed and accuracy, making it more clinically practical for large-scale screenings. Future research should further explore the model’s potential in benign and malignant classification to promote its application in clinical settings, assisting radiologists in diagnosing breast cancer more efficiently. Full article

Among the emerging applications of artificial intelligence is animal instance segmentation, which has provided a practical means for various researchers to accomplish some aim or execute some order. Though video and image processing are two of the several complex tasks in artificial intelligence, these tasks have become more complex due to the large data and resources needed for training deep learning models. However, these challenges are beginning to be overcome by the transfer learning method of deep learning. In furtherance of the application of the transfer learning method, a system is proposed in this study that applies transfer learning to the detection and recognition of animal activity in a typical farm environment using deep learning models. Among the deep learning models compared, Enhanced Mask R-CNN obtained a significant computing time of 0.2 s and 97% mAP results, which are better than the results obtained by Mask R-CNN, Faster R-CNN, SSD, and YOLOv3, respectively. The findings from the results obtained in this study validate the innovative use of transfer learning to address challenges in cattle segmentation by optimizing the segmentation accuracy and processing time (0.2 s) of the proposed Enhanced Mask R-CNN. Full article

Arecaceae (palms) play a crucial role for native communities and wildlife in the Amazon region. This study presents a first-of-its-kind regional-scale spatial cataloging of palms using remotely sensed data for the country of Guyana. Using very high-resolution satellite images from the GeoEye-1 and WorldView-2 sensor platforms, which collectively cover an area of 985 km², a total of 472,753 individual palm crowns are detected with F1 scores of 0.76 and 0.79, respectively, using a convolutional neural network (CNN) instance segmentation model. An example of CNN model transference between images is presented, emphasizing the limitation and practical application of this approach. A method is presented to optimize precision and recall using the confidence of the detection features; this results in a decrease of 45% and 31% in false positive detections, with a moderate increase in false negative detections. The sensitivity of the CNN model to the size of the training set is evaluated, showing that comparable metrics could be achieved with approximately 50% of the samples used in this study. Finally, the diameter of the palm crown is calculated based on the polygon identified by mask detection, resulting in an average of 7.83 m, a standard deviation of 1.05 m, and a range of {4.62, 13.90} m for the GeoEye-1 image. Similarly, for the WorldView-2 image, the average diameter is 8.08 m, with a standard deviation of 0.70 m and a range of {4.82, 15.80} m. Full article

The scale of horticultural facilities in Japan is expanding, making the efficient management of labor costs essential, particularly in large-scale tomato production. This study developed a consistent and practical system for predicting harvest working time and estimating the quantity and weight of harvested fruit using panoramic images of cultivation rows. The system integrates a deep learning model, the Mask ResNet-50 convolutional neural network, to count harvestable fruits from images and a predictive algorithm to estimate working time based on the fruit count. The results indicated that the average for all workers could be predicted with an error margin of 30.1% when predicted three days before the harvest date and 15.6% when predicted on the harvest date. The trial also revealed that the accuracy of the predictions varied based on workers’ experience and cultivation methods. This study highlights the system’s potential to optimize harvesting plans and labor allocation, providing a novel tool for reducing labor costs while maintaining efficiency in large-scale tomato greenhouse production. Full article

Distance measurement plays a key role in many fields of science and technology, including robotics, civil engineering, and navigation systems. This paper focuses on analyzing the precision of a measurement system using stereo camera distance measurement technology in the context of measuring two objects of different sizes. The first part of the paper presents key information about stereoscopy, followed by a discussion of the process of building a measuring station. The Mask R-CNN algorithm, which is a deep learning model that combines object detection and instance segmentation, was used to identify objects in the images. In the following section, the calibration process of the system and the distance calculation method are presented. The purpose of the study was to determine the precision of the measurement system and to identify the distance ranges where the measurements are most precise. Measurements were made in the range of 20 to 70 cm. The system demonstrated a relative error of 0.95% for larger objects and 1.46% for smaller objects at optimal distances. A detailed analysis showed that for larger objects, the system exhibited higher precision over a wider range of distances, while for smaller objects, the highest accuracy was achieved over a more limited range. These results provide valuable information on the capabilities and limitations of the measurement system used, while pointing out directions for its further optimization. Full article

Currently, intelligent pest monitoring systems transmit entire monitoring images to cloud servers for analysis. This approach not only consumes significant bandwidth and increases monitoring costs, but also struggles with accurately recognizing small-target and overlapping pests. To overcome these challenges, this paper introduces a two-stage multi-feature fusion small-target pest detection algorithm based on edge computing devices, termed TFEMRNet. The algorithm initially conducts semantic segmentation on an edge processor, followed by uploading the segmented images to a cloud server for target identification. Specifically, the semantic segmentation model TFENet incorporates a Multi-Attention Channel Aggregation (MACA) module, which integrates semantic features from EfficientNet-Pest and Swin Transformer, thereby enhancing the model’s ability to extract features of small-target pests. Experimental results demonstrate that TFEMRNet surpasses models such as YOLOv11, Fast R-CNN, and Mask R-CNN on small-target pest datasets, achieving precision of 96.75%, recall of 96.45%, and an F1 score of 95.60%. Notably, the TFENet model within TFEMRNet attains an IoU of 91.63% in semantic segmentation accuracy, outperforming other segmentation models such as U-Net and PSPNet. These findings affirm TFEMRNet’s superior efficacy in small-target pest detection, offering an effective solution for agricultural pest monitoring. Full article