Search Results (810)

Sperm morphology assessment plays a vital role in semen analysis and the diagnosis of male infertility. By quantitatively analyzing the morphological characteristics of the sperm head, midpiece, and tail, it provides essential insights for assisted reproductive technologies (ARTs), such as in vitro fertilization (IVF). However, traditional manual evaluation methods not only rely on staining procedures that can damage the cells but also suffer from strong subjectivity and inconsistent results, underscoring the urgent need for an automated, accurate, and non-invasive method for multi-sperm morphology assessment. To address the limitations of existing techniques, this study proposes a novel method that combines a multi-scale part parsing network with a measurement accuracy enhancement strategy for non-stained sperm morphology analysis. First, a multi-scale part parsing network integrating semantic segmentation and instance segmentation is introduced to achieve instance-level parsing of sperm, enabling precise measurement of morphological parameters for each individual sperm instance. Second, to eliminate measurement errors caused by the reduced resolution of non-stained sperm images, a measurement accuracy enhancement method based on statistical analysis and signal processing is designed. This method employs an interquartile range (IQR) method to exclude outliers, Gaussian filtering to smooth data, and robust correction techniques to extract the maximum morphological features of sperm. Experimental results demonstrate that the proposed multi-scale part parsing network achieves 59.3% $A{P}_{\mathrm{vol}}^p$, surpassing the state-of-the-art AIParsing by 9.20%. Compared to evaluations based solely on segmentation results, the integration of the measurement accuracy enhancement strategy significantly reduces measurement errors, with the largest reduction in errors for head, midpiece, and tail measurements reaching up to 35.0%. Full article

Video instance segmentation (VIS) is plagued by the high cost of pixel-level annotation and defects of weakly supervised segmentation, leading to the urgent need for a trade-off between annotation cost and performance. We propose a novel In-Depth Collaboratively Supervised video instance segmentation (IDCS) with efficient training. A collaborative supervised training pipeline is designed to flow samples of different labeling levels and carry out multimodal training, in which instance clues are obtained from mask-annotated instances to guide the box-annotated training through an in-depth collaborative paradigm: (1) a trident learning method is proposed, which leverages the video temporal consistency to match instances with multimodal annotation across frames for effective instance relation learning without additional network parameters; (2) spatial clues in the first frames are captured to implement multidimensional pixel affinity evaluation of box-annotated instances and augment the noise-disturbed spatial affinity map. Experiments on YoutTube-VIS validate the performance of IDCS with mask-annotated instances in the first frames and the bounding-box-annotated samples in the remaining frames. IDCS achieves up to 92.0% fully supervised performance and average 1.4 times faster, 2.2% mAP higher than the weakly supervised baseline. The results show that IDCS can efficiently utilize multimodal data, while providing advanced guidance for effective trade-off in VIS training. Full article

In unstructured tea garden environments, accurate recognition and pose estimation of tea bud leaves are critical for autonomous harvesting robots. Due to variations in imaging distance, tea bud leaves exhibit diverse scale and pose characteristics in camera views, which significantly complicates the recognition and pose estimation process. This study proposes a method using an RGB-D camera for precise recognition and pose estimation of tea bud leaves. The approach first constructs an for tea bud leaves, followed by a dynamic weight estimation strategy to achieve adaptive pose estimation. Quantitative experiments demonstrate that the instance segmentation model achieves an mAP@50 of 92.0% for box detection and 91.9% for mask detection, improving by 3.2% and 3.4%, respectively, compared to the YOLOv8s-seg instance segmentation model. The pose estimation results indicate a maximum angular error of 7.76°, a mean angular error of 3.41°, a median angular error of 3.69°, and a median absolute deviation of 1.42°. The corresponding distance errors are 8.60 mm, 2.83 mm, 2.57 mm, and 0.81 mm, further confirming the accuracy and robustness of the proposed method. These results indicate that the proposed method can be applied in unstructured tea garden environments for non-destructive and precise harvesting with autonomous tea bud-leave harvesting robots. Full article

Exploring the relationships between plant phenotypes and genetic information requires advanced phenotypic analysis techniques for precise characterization. However, the diversity and variability of plant morphology challenge existing methods, which often fail to generalize across species and require extensive annotated data, especially for 3D datasets. This paper proposes a zero-shot 3D leaf instance segmentation method using RGB sensors. It extends the 2D segmentation model SAM (Segment Anything Model) to 3D through a multi-view strategy. RGB image sequences captured from multiple viewpoints are used to reconstruct 3D plant point clouds via multi-view stereo. HQ-SAM (High-Quality Segment Anything Model) segments leaves in 2D, and the segmentation is mapped to the 3D point cloud. An incremental fusion method based on confidence scores aggregates results from different views into a final output. Evaluated on a custom peanut seedling dataset, the method achieved point-level precision, recall, and F1 scores over 0.9 and object-level mIoU and precision above 0.75 under two IoU thresholds. The results show that the method achieves state-of-the-art segmentation quality while offering zero-shot capability and generalizability, demonstrating significant potential in plant phenotyping. Full article

Due to the labor-intensive manual annotations for nuclei segmentation, point-supervised segmentation based on nuclei coordinate supervision has gained recognition in recent years. Despite great progress, two challenges hinder the performance of weakly supervised nuclei segmentation methods: (1) The stable and effective segmentation of adjacent cell nuclei remains an unresolved challenge. (2) Existing approaches rely solely on initial pseudo-labels generated from point annotations for training, and inaccurate labels may lead the model to assimilate a considerable amount of noise information, thereby diminishing performance. To address these issues, we propose a method based on center-point prediction and pseudo-label updating for precise nuclei segmentation. First, we devise a Gaussian kernel mechanism that employs multi-scale Gaussian masks for multi-branch center-point prediction. The generated center points are utilized by the segmentation module to facilitate the effective separation of adjacent nuclei. Next, we introduce a point-guided attention mechanism that concentrates the segmentation module’s attention around authentic point labels, reducing the noise impact caused by pseudo-labels. Finally, a label updating mechanism based on the exponential moving average (EMA) and k-means clustering is introduced to enhance the quality of pseudo-labels. The experimental results on three public datasets demonstrate that our approach has achieved state-of-the-art performance across multiple metrics. This method can significantly reduce annotation costs and reliance on clinical experts, facilitating large-scale dataset training and promoting the adoption of automated analysis in clinical applications. Full article

Moving bottlenecks, characterized by their high frequency and unpredictability, pose significant challenges to timely response and management, often resulting in road congestion and increased risk of traffic accidents. To address these issues, this paper proposes an adaptive event-triggered variable speed limit (AET-VSL) method based on a state compensation model, which emphasizes the concept of symmetry in the optimization of multi-segment speed limits. This symmetry approach facilitates a balanced and efficient control strategy that adjusts speed limits in a way that harmonizes traffic flow across multiple road segments, reducing congestion and improving overall traffic stability. The state compensation model builds on the classical METANET traffic flow model, incorporating coordination between road segments to reduce congestion while minimizing disruptions to traffic flow stability. By dynamically adjusting speed limits using real-time traffic data, the AET-VSL method addresses fluctuations in traffic conditions and ensures adaptive control to manage bottlenecks efficiently. A simulation framework was employed to evaluate the proposed strategy across varying traffic scenarios. Results demonstrate that AET-VSL outperforms traditional methods, providing consistent improvements in traffic performance. For instance, under low-traffic-flow conditions, AET-VSL reduced waiting time (WT) by 41.36%, potential collisions (PCs) by 51.92%, and fuel consumptionfuel consumption (FC) by 34.07%. This study highlights the novelty and effectiveness of AET-VSL, offering a scalable and reliable solution for dynamic traffic management and showcasing its potential to enhance traffic safety and efficiency. Full article

Video instance segmentation, a key technology for intelligent sensing in visual perception, plays a key role in automated surveillance, robotics, and smart cities. These scenarios rely on real-time and efficient target-tracking capabilities for accurate perception and intelligent analysis of dynamic environments. However, traditional video instance segmentation methods face complex models, high computational overheads, and slow segmentation speeds in time-series feature extraction, especially in resource-constrained environments. To address these challenges, a Dual-Channel and Frequency-Aware Approach for Lightweight Video Instance Segmentation (DCFA-LVIS) is proposed in this paper. In feature extraction, a DCEResNet backbone network structure based on a dual-channel feature enhancement mechanism is designed to improve the model’s accuracy by enhancing the feature extraction and representation capabilities. In instance tracking, a dual-frequency perceptual enhancement network structure is constructed, which uses an independent instance query mechanism to capture temporal information and combines with a frequency-aware attention mechanism to capture instance features on different attention layers of high and low frequencies, respectively, to effectively reduce the complexity of the model, decrease the number of parameters, and improve the segmentation efficiency. Experiments show that the model proposed in this paper achieves state-of-the-art segmentation performance with few parameters on the YouTube-VIS dataset, demonstrating its efficiency and practicality. This method significantly enhances the application efficiency and adaptability of visual perception intelligent sensing technology in video data acquisition and processing, providing strong support for its widespread deployment. Full article

Phenotypic analysis of mature soybeans is a critical aspect of soybean breeding. However, manually obtaining phenotypic parameters not only is time-consuming and labor intensive but also lacks objectivity. Therefore, there is an urgent need for a rapid, accurate, and efficient method to collect the phenotypic parameters of soybeans. This study develops a novel pipeline for acquiring the phenotypic traits of mature soybeans based on three-dimensional (3D) point clouds. First, soybean point clouds are obtained using a multi-view stereo 3D reconstruction method, followed by preprocessing to construct a dataset. Second, a deep learning-based network, PVSegNet (Point Voxel Segmentation Network), is proposed specifically for segmenting soybean pods and stems. This network enhances feature extraction capabilities through the integration of point cloud and voxel convolution, as well as an orientation-encoding (OE) module. Finally, phenotypic parameters such as stem diameter, pod length, and pod width are extracted and validated against manual measurements. Experimental results demonstrate that the average Intersection over Union (IoU) for semantic segmentation is 92.10%, with a precision of 96.38%, recall of 95.41%, and F1-score of 95.87%. For instance segmentation, the network achieves an average precision (AP@50) of 83.47% and an average recall (AR@50) of 87.07%. These results indicate the feasibility of the network for the instance segmentation of pods and stems. In the extraction of plant parameters, the predicted values of pod width, pod length, and stem diameter obtained through the phenotypic extraction method exhibit coefficients of determination ($R^2$) of 0.9489, 0.9182, and 0.9209, respectively, with manual measurements. This demonstrates that our method can significantly improve efficiency and accuracy, contributing to the application of automated 3D point cloud analysis technology in soybean breeding. Full article

Objective: This study evaluated the applicability of the classical method, height loss ratio (HLR), for identifying major acute compression fractures in clinical practice and compared its performance with deep learning (DL)-based VCF detection methods. Additionally, it examined whether combining the HLR with DL approaches could enhance performance, exploring the potential integration of classical and DL methodologies. Methods: End-to-End VCF Detection (EEVD), Two-Stage VCF Detection with Segmentation and Detection (TSVD_SD), and Two-Stage VCF Detection with Detection and Classification (TSVD_DC). The models were evaluated on a dataset of 589 patients, focusing on sensitivity, specificity, accuracy, and precision. Results: TSVD_SD outperformed all other methods, achieving the highest sensitivity (84.46%) and accuracy (95.05%), making it particularly effective for identifying true positives. The complementary use of DL methods with HLR further improved detection performance. For instance, combining HLR-negative cases with TSVD_SD increased sensitivity to 87.84%, reducing missed fractures, while combining HLR-positive cases with EEVD achieved the highest specificity (99.77%), minimizing false positives. Conclusion: These findings demonstrated that DL-based approaches, particularly TSVD_SD, provided robust alternatives or complements to traditional methods, significantly enhancing diagnostic accuracy for acute VCFs in clinical practice. Full article

In recent years, large-scale point cloud semantic segmentation has been widely applied in various fields, such as remote sensing and autonomous driving. Most existing point cloud networks use local aggregation to abstract unordered point clouds layer by layer. Among these, position embedding serves as a crucial step. However, current methods of position embedding have limitations in modeling spatial relationships, especially in deeper encoders where richer spatial positional relationships are needed. To address these issues, this paper summarizes the advantages and disadvantages of mainstream position embedding methods and proposes a novel Hybrid Offset Position Encoding (HOPE) module. This module comprises two branches that compute relative positional encoding (RPE) and offset positional encoding (OPE). RPE combines explicit encoding to enhance position features through attention, learning position bias implicitly, while OPE calculates absolute position offset encoding by considering differences with grouping embeddings. These two encodings are adaptively mixed in the final output. The experiment conducted on multiple datasets demonstrates that our module helps the deep encoders of the network capture more robust features, thereby improving model performance on various baseline models. For instance, PointNet++ and PointMetaBase enhanced with HOPE achieved mIoU gains of 2.1% and 1.3% on the large-scale indoor dataset S3DIS area-5, 2.5% and 1.1% on S3DIS 6-fold, and 1.5% and 0.6% on ScanNet, respectively. RandLA-Net with HOPE achieved a 1.4% improvement on the large-scale outdoor dataset Toronto3D, all with minimal additional computational cost. PointNet++ and PointMetaBase had approximately only a 0.1 M parameter increase. This module can serve as an alternative for position embedding, and is suitable for point-based networks requiring local aggregation. Full article

Manual labeling of lesions in medical image analysis presents a significant challenge due to its labor-intensive and inefficient nature, which ultimately strains essential medical resources and impedes the advancement of computer-aided diagnosis. This paper introduces a novel medical image-segmentation framework named Efficient Generative-Adversarial U-Net (EGAUNet), designed to facilitate rapid and accurate multi-organ labeling. To enhance the model’s capability to comprehend spatial information, we propose the Global Spatial-Channel Attention Mechanism (GSCA). This mechanism enables the model to concentrate more effectively on regions of interest. Additionally, we have integrated Efficient Mapping Convolutional Blocks (EMCB) into the feature-learning process, allowing for the extraction of multi-scale spatial information and the adjustment of feature map channels through optimized weight values. Moreover, the proposed framework progressively enhances its performance by utilizing a generative-adversarial learning strategy, which contributes to improvements in segmentation accuracy. Consequently, EGAUNet demonstrates exemplary segmentation performance on public multi-organ datasets while maintaining high efficiency. For instance, in evaluations on the CHAOS T2SPIR dataset, EGAUNet achieves approximately $2\%$ higher performance on the Jaccard metric, $1\%$ higher on the Dice metric, and nearly $3\%$ higher on the precision metric in comparison to advanced networks such as Swin-Unet and TransUnet. Full article

Malaria remains a global health concern, with 249 million cases and 608,000 deaths being reported by the WHO in 2022. Traditional diagnostic methods often struggle with inconsistent stain quality, lighting variations, and limited resources in endemic regions, making manual detection time-intensive and error-prone. This study introduces an automated system for analyzing Romanowsky-stained thick blood smears, focusing on image quality evaluation, leukocyte detection, and malaria parasite classification. Using a dataset of 1000 clinically diagnosed images, we applied feature extraction techniques, including histogram bins and texture analysis with the gray level co-occurrence matrix (GLCM), alongside support vector machines (SVMs), for image quality assessment. Leukocyte detection employed optimal thresholding segmentation utility (OTSU) thresholding, binary masking, and erosion, followed by the connected components algorithm. Parasite detection used high-intensity region selection and adaptive bounding boxes, followed by a custom convolutional neural network (CNN) for candidate identification. A second CNN classified parasites into trophozoites, schizonts, and gametocytes. The system achieved an F1-score of 95% for image quality evaluation, 88.92% for leukocyte detection, and 82.10% for parasite detection. The F1-score—a metric balancing precision (correctly identified positives) and recall (correctly detected instances out of actual positives)—is especially valuable for assessing models on imbalanced datasets. In parasite stage classification, CNN achieved F1-scores of 85% for trophozoites, 88% for schizonts, and 83% for gametocytes. This study introduces a robust and scalable automated system that addresses critical challenges in malaria diagnosis by integrating advanced image quality assessment and deep learning techniques for parasite detection and classification. This system’s adaptability to low-resource settings underscores its potential to improve malaria diagnostics globally. Full article

Tea is a significant cash crop grown widely around the world. Currently, tea plucking predominantly relies on manual work. However, due to the aging population and increasing labor costs, machine plucking has become an important trend in the tea industry. The determination of the plucking position and plucking posture is a critical prerequisite for machine plucking tea leaves. In order to improve the accuracy and efficiency of machine plucking tea leaves, a method is presented in this paper to determine the plucking point and plucking posture based on the instance segmentation deep learning network. In this study, tea images in the dataset were first labeled using the Labelme software (version 4.5.13), and then the LDS-YOLOv8-seg model was proposed to identify the tea bud region and plucking area. The plucking points and the central points of the tea bud’s bounding box were calculated and matched as pairs using the nearest point method (NPM) and the point in range method (PIRM) proposed in this study. Finally, the plucking posture was obtained according to the results of the feature points matching. The matching results on the test dataset show that the PIRM has superior performance, with a matching accuracy of 99.229% and an average matching time of 2.363 milliseconds. In addition, failure cases of feature points matching in the plucking posture determination process were also analyzed in this study. The test results show that the plucking position and posture determination method proposed in this paper is feasible for machine plucking tea. Full article

To cope with the complexity, the digital transformation of cyber-physical and socio-technology systems demands the utilization of heterogeneous tailorable development environments with dynamic configuring ability and transparent integration of independently developed dedicated frameworks. The essential design principles and component-based architecting of the initial prototype of the digital transformation hyper-framework represent this research target. These principles are derived from the broad scope analysis of digital transformation projects, methods, and tools and are glued to the proposed virtual twin hyper-document. The critical analysis of the digital transformation domain influenced the formulation of five research hypotheses that frame digital transformation of digital transformation, as the second goal of this research article. Armed with a meta-modeling layer, the incremental development of hybrid architecture instances focuses on meta-models and their transformations into functional, interpretable environments. The applicability aspects of the formulated hypothesis are verified throughout the architecture, meta-configuration, and handling of information resources as the essential segments of the initial version of the proposed evolution prototype. The detailed illustration of the horizontal and vertical interoperability of the proposed framework is illustrated by the Life Cycle Modeling component framework that creatively integrates the System, Software, and Operation Engineering aspects of the proposed hyper-framework. The proposed prototype capabilities are discussed in the context of the contemporary digital transformation ecosystem. Specification and development of the additional component frameworks, in compliance with specified generative mechanisms, directing further refinements of the proposed hyper-framework. Full article

Drainage pipeline construction projects are vulnerable to a range of defects, such as branch concealed joints, variable diameter, two pipe mouth significances, foreign object insertion, pipeline rupture, and pipeline end disconnection, generated during long-term service in a complex environment. This paper proposes two enhancements to multiple attention learning to detect and segment multiple defects. Firstly, we collected numerous samples of drainage pipeline sonar defect videos. Then, our multiple attention segmentation network was used for target segmentation. The test precision and accuracy of MAP@50 reach 96.0% and 90.9%, respectively, in the segmentation prediction. Compared to the coordinate attention and convolutional block attention module attention models, it had a significant precision advantage, and the weight file size is merely 7.0 MB, which is far smaller than the Yolov9 model segmentation weight size. The multiple attention method proposed in this paper was adopted for detection, instance segmentation, and pose detection in different public datasets, especially in the object detection of the coco128-seg dataset under the same condition. Map@50:95 has increased by 13.0% assisted by our multiple attention mechanism. The results indicated the memory efficiency and high precision of the integration of the multiple attention model on several public datasets. Full article