Objective Scale Research Articles

Endoscopic management of pediatric complex hydrocephalus-a procedure survival analysis and clinico-radiological outcome study using ventricular volumetry.

To evaluate the survival of endoscopic procedures performed for complex hydrocephalus, quantify clinical outcomes in standardized scales, and assess correlation with radiological outcomes using ventricular volumetry. A retrospective analysis of patients with complex hydrocephalus, managed with neuroendoscopic procedures at a tertiary neurosurgical center over 20years, was performed. In addition to demographic and clinical details, pre-operative and follow-up clinical status (using the Pediatric Functional Status Score (FSS) and Pediatric Cerebral Performance Category (PCPC) Scales) was assessed. Procedure failure was defined as any subsequent surgical procedure for the management of hydrocephalus and survival as time from the first endoscopic procedure to failure or last available follow-up. Ventricular volume and ventricle:brain volume ratio was calculated using serial imaging. We analyzed 40 pediatric patients who met the study criteria with a mean age of 19months, the most common subtype being post-meningitic multiloculated hydrocephalus (70%). The median survival of an endoscopic procedure was 24months (5.7-33.6months). Over a median follow-up duration of 15months, 28days (2.2-111months), median FSS improved by 5 points, and median PCPC score improved from 4 (severe disability) to 3 (moderate disability). Over a median radiological follow-up of 5.9months, the median percentage decrease in ventricle size was 27.14%, and the ventricle:brain volume ratio was 30.57%. A strong positive correlation (r = 0.58-0.75) was noted between the decrease in ventricular volume and ventricle:brain ratio with improvement in FSS and PCPC scores. Endoscopic procedures, although effective in managing complex hydrocephalus, may not be a one-stop long-term solution, which we have described in terms of procedure survival. Objective scales and ventricular volumetry to quantify clinical and radiological improvement demonstrated a significant correlation, even in complex hydrocephalus. The potential of ventricular volumetry as a prognostic factor in complex hydrocephalus is postulated.

Position and orientation determination using quadric fitting optimization for object’s motion analyzing

Abstract The accurate determination of the position and orientation of moving objects from images is a critical challenge in visual sensing, with significant implications for robotics, augmented reality and computer vision. Traditional pose estimation methods often fail in complex scenarios due to inconsistent and imprecise feature extraction. This research introduces a novel quadric fitting optimization framework that exploits the compact representation of ellipsoids for robust motion analysis. We propose Manhattan and Euclidean norm-based solvers, designed to optimize quadric fitting for varying object scales and distances. A hybrid approach is developed to strategically fuse these solvers to maximize accuracy and efficiency in various practical applications. Theoretical analysis and extensive experimental validation demonstrate the significant improvements offered by our method over conventional techniques, particularly under challenging conditions. This work not only advances the state of the art in object pose determination, but also provides a solid foundation for improved manipulation and understanding of moving objects in dynamic environments.

Grading scales for vitreous haze

Background: Grading scales for vitreous haze are crucial for the diagnosis, monitoring, and management of uveitis. The presence of inflammatory cells within the vitreous cavity is widely recognized as a key indicator of disease activity and severity, offering valuable insights into the underlying inflammatory processes. This mini-review aims to explore the evolution of vitreous haze grading scales systematically, emphasizing conventional grading methods, advances in imaging technologies, and the integration of artificial intelligence (AI) into the grading process. Methods: The PubMed/MEDLINE database was comprehensively searched for studies published between 1959 and 2024, using keywords such as “AI-based grading systems,” “artificial intelligence,” “automated grading,” “grading scales for vitreous cells,” “inflammation,” “uveitis,” and “vitreous haze.” Relevant studies were identified, and additional articles were selected by reviewing the reference lists of the included publications. The selection of articles for inclusion in the mini-review was limited to those written in English. Results: In the current literature, two grading methods are used: the National Institutes of Health (NIH) scale and the Miami scale. Despite their widespread utilization, both scales entail subjective assessments of vitreous haze, which renders them susceptible to observer bias and interobserver variability. The NIH scale uses six levels, while the Miami scale employs nine levels, both of which require subjective assessments of vitreous haze. Recent advances in objective imaging technologies, namely ultrawide-field fundus photography and advanced optical coherence tomography-based analysis, have given rise to increasingly consistent and standardized grading systems, which may enhance the reliability of these assessments. Innovative techniques have been developed to enhance accuracy and sensitivity, thereby facilitating the early detection and precise monitoring of vitreous inflammation. Despite these advances, challenges remain, including the difficulty of distinguishing subtle variations in vitreous haze and the variability of inflammatory presentations. The incorporation of AI-driven tools and state-of-the-art imaging technologies into the vitreous cell grading signifies a substantial advance in the evaluation and management of uveitis. Conclusions: The development of more objective, reproducible, and quantitative grading scales is imperative for optimizing uveitis evaluation and grading vitreous haze in clinical settings and clinical trials. These innovations will also provide robust endpoints for clinical studies, ultimately improving patient care. Moreover, objective grading criteria will enhance diagnostic precision, facilitate better management of ocular inflammatory diseases, and promote further advances in uveitis research and treatment.

Efficiency of immersive virtual reality game technology on pain management in children with limb fractures: A randomized controlled trial.

Children with fractured limbs usually have moderate to high pain, and distraction can help reduce their pain and anxiety. Virtual reality technology is an emerging method of distraction. We investigated whether the use of immersive virtual reality gaming technology to treat perioperative pain in children with school-age limb fractures effectively. Ninty-nine patients who had limb fracture surgery between October 2021 and September 2022 were randomly assigned to receive immersive virtual reality game therapy (Group A), non-immersive virtual reality game therapy (Group B), or conventional treatment group (Group C). Changes in pain, anxiety, fear, and biochemical markers were assessed at various time points in the three groups using subjective and objective rating scales. Both Group A and Group B consistently showed lower pain scores, fear levels, and anxiety levels compared to Group C after surgery, statistical analysis revealed significant differences among the three groups (p<0.001). Additionally,serum levels in group A were significantly lower than those in other groups, showing a notable statistical discrepancy (p<0.001). Both immersive and non-immersive virtual reality gaming significantly reduce perioperative pain, fear, and anxiety in children with limb fractures, and have practical significance for pain management of pediatric orthopedic patients. Immersive virtual reality, however, appears to have a more pronounced effect. The trial was registered prior to patient enrollment at the Chinese Clinical Trial Registry(ChiCTR210004583).

Integrating EnlightenGAN for enhancing car logo detection under challenging lighting conditions

Abstract Detecting small objects in challenging lighting conditions is a critical task with broad applications in computer vision, surveillance, and medical imaging. Small objects are especially vulnerable to detection errors due to their size and the significant impact of varying lighting conditions, such as low-light environments or high glare. Furthermore, the lack of a benchmark dataset that accurately simulates real-world scenarios makes it difficult to evaluate the performance of detection models in such conditions. In the proposed paper, we address these challenges by developing a comprehensive dataset specifically designed for car logo detection under diverse and challenging lighting environments. The dataset incorporates variations in lighting, viewing angles, and object scales to replicate real-world conditions. We also introduce a detection pipeline integrating EnlightenGAN for low-light image enhancement, which preserves fine details and textures, and YOLOv7 and YOLOv8 for improved detection accuracy. By enhancing image quality and refining object detection models, our approach significantly boosts the detection of small car logos, even in challenging lighting scenarios where traditional models tend to fail. Experimental results show that YOLOv8 outperforms YOLOv7 by approximately 7%, with YOLOv8 achieving a mean Average Precision (mAP) of 73.3% on the augmented dataset compared to 68.4% for the original dataset and 67.2% for the processed images. These results validate the effectiveness of GAN-based enhancement techniques in preserving small object details and improving detection performance. Additionally, introducing a new dataset and benchmark provides a valuable resource for future research in small object detection under complex lighting conditions.

Semantic Object Segmentation using Modified HRNet Deep Learning Model

This paper presents a modified High-Resolution Network (HRNet) architecture designed for enhanced semantic object segmentation, addressing the prevalent challenges of accuracy and computational efficiency in complex image analyses. Through strategic modifications to the conventional HRNet, including optimized feature blocks and advanced feature extraction techniques, our model demonstrates significant improvements in segmentation performance. Utilizing the Cityscapes dataset, renowned for its comprehensive urban scene representation, our enhanced HRNet model achieved a notable increase in validation accuracy to 85.8% and mean Intersection over Union (mIoU) to 63.43%, surpassing the original HRNet benchmarks by 3.39% and 3.43%, respectively. These results highlight not only the precision of our model in delineating intricate urban landscapes but also its robustness in handling diverse object scales and complexities. The qualitative analysis, underscored by comparison images, reveals our model's ability to produce more defined segmentation contours and accurate object identifications, setting a new standard for HRNet-based semantic segmentation. This work not only advances the field of high-resolution image segmentation but also offers a foundational model for future research aimed at solving increasingly complex image processing challenges

Bilingual Perspectives of Functional Dyspepsia Management in People From Underserved Areas.

Disorders of gut-brain interaction, such as functional dyspepsia (FD), are prevalent and challenging conditions. In other gastrointestinal (GI) disorders, individuals from underserved areas (UAs) have difficulty accessing care. Little is known about UA FD patient perspectives of their care, especially in those with limited English proficiency. We aimed to characterize patients' experiences with FD management with the goal of informing future studies targeting disorders of gut-brain interaction management in potentially vulnerable communities residing in UAs. Participants meeting FD criteria were identified in 2 community health centers affiliated with a large academic medical center in the Northeastern United States. Semistructured interviews were conducted in English and Spanish. Transcripts were reviewed by a bilingual panel of investigators using the constant comparative method of iterative data acquisition. Psychosocial stressors and GI symptom severity were assessed. A total of 26 participants were interviewed (12 English-speaking and 14 Spanish-speaking). Broadly, GI symptoms were mild and there was mild-to-moderate psychological distress present. Adverse social determinants of health were highly prevalent. Despite mild symptom severity on objective scales, FD severely affected quality of life and interfered with physical, psychological, and social well-being, including avoidance of certain foods and professional/social situations. Study participants (particularly those with limited English proficiency status) reported difficulty in receiving care. Thematic saturation was achieved. Even when symptoms were mild, interviewees from UAs reported significant FD-related impairment, along with psychological distress. Education interventions targeting FD-related care in UAs should be designed to improve shared decision making in FD, sensitive to the burden of social determinants of health.

FAMHE-Net: Multi-Scale Feature Augmentation and Mixture of Heterogeneous Experts for Oriented Object Detection

Object detection in remote sensing images is essential for applications like unmanned aerial vehicle (UAV)-assisted agricultural surveys and aerial traffic analysis, facing unique challenges such as low resolution, complex backgrounds, and the variability of object scales. Current detectors struggle with integrating spatial and semantic information effectively across scales and often omit necessary refinement modules to focus on salient features. Furthermore, a detector head that lacks a meticulous design may face limitations in fully understanding and accurately predicting based on the enriched feature representations. These deficiencies can lead to insufficient feature representation and reduced detection accuracy. To address these challenges, this paper introduces a novel deep-learning framework, FAMHE-Net, for enhancing object detection in remote sensing images. Our framework features a consolidated multi-scale feature enhancement module (CMFEM) with integrated Path Aggregation Feature Pyramid Network (PAFPN), utilizing our efficient atrous channel attention (EACA) within CMFEM for enhanced contextual and semantic information refinement. Additionally, we introduce a sparsely gated mixture of heterogeneous expert heads (MOHEH) to adaptively aggregate detector head outputs. Compared to the baseline model, FAMEH-Net demonstrates significant improvements, achieving a 0.90% increase in mean Average Precision (mAP) of the DOTA dataset and a 1.30% increase in mAP12 of HRSC2016 datasets. These results highlight the effectiveness of FAMEH-Net in object detection within complex remote sensing images.

Gradient Enhancement Techniques and Motion Consistency Constraints for Moving Object Segmentation in 3D LiDAR Point Clouds

The ability to segment moving objects from three-dimensional (3D) LiDAR scans is critical to advancing autonomous driving technology, facilitating core tasks like localization, collision avoidance, and path planning. In this paper, we introduce a novel deep neural network designed to enhance the performance of 3D LiDAR point cloud moving object segmentation (MOS) through the integration of image gradient information and the principle of motion consistency. Our method processes sequential range images, employing depth pixel difference convolution (DPDC) to improve the efficacy of dilated convolutions, thus boosting spatial information extraction from range images. Additionally, we incorporate Bayesian filtering to impose posterior constraints on predictions, enhancing the accuracy of motion segmentation. To handle the issue of uneven object scales in range images, we develop a novel edge-aware loss function and use a progressive training strategy to further boost performance. Our method is validated on the SemanticKITTI-based LiDAR MOS benchmark, where it significantly outperforms current state-of-the-art (SOTA) methods, all while working directly on two-dimensional (2D) range images without requiring mapping.

A study on UAV target detection and 3D positioning methods based on the improved deformable DETR model and multi-view geometry

This paper addresses critical challenges in Unmanned Aerial Vehicle (UAV) target detection and 3D positioning, specifically inaccuracies in localization and lack of robustness in complex environments. The objective of this research is to improve UAV detection and positioning accuracy by proposing an enhanced Deformable DETR (Detection Transformer) model integrated with multi-view geometry theory. To achieve this, the study first preprocesses UAV-collected data, then optimizes the convolutional layers of the original DETR model to better handle object occlusion and scale variations. Furthermore, the research incorporates multi-view geometric modeling and multimodal fusion strategies to enhance detection accuracy during the target recognition process. Experimental results demonstrate that the proposed approach achieves over 70% detection accuracy, significantly outperforming traditional methods. The findings underscore the effectiveness of combining the improved Deformable DETR model with multi-view geometry for high-precision detection and 3D localization in complex environments. This research has significant implications for UAV-based applications, such as autonomous navigation, surveillance, and search-and-rescue missions, where precise target detection and 3D positioning are critical for successful operation.

Efficacy of Trataka Kriya in Improving Quality of Sleep in population aged 30-50 years: An open clinical trial

Background: In present era, Sleeplessness and disturbed sleep is a common disorder associated with morbidity and poor quality of life. In Ayurveda, Sleep is included under three supportive pillars of life (trayopasthambha). More than 50-70 million people in the United States have a sleep disorder i. In India prevalence rates are 6.5% among women and 4.3% among men. Trataka is one of the Shat Karma (yogic purificatory therapy) but is also observed to be having effects similar to meditative practices. It relieves mental stress so can improve sleep quality. Aim: To study the effect of Trataka Kriya in improving Quality of sleep-in population aged 30- 50 years. Objective: To evaluate the change in subjective and objective parameters on Pittsburgh Sleep Quality Index (PSQI) &amp; WHO-QOL Bref Questionnaire. Materials and Methodology: Part 1: Survey Study: A survey was conducted in 100 subjects to understand the distribution of sleep disorder in the population. Part 2: Interventional Study: From the participants of the survey 35 subjects were selected who reported sleep disturbance (decreased sleep). After Day 0 Assessment of the PSQI &amp; WHO-QOL BREF Scales, Training session on Trataka Kriya was given to the subjects and were advised to continue the practice for 15 days. Re-assessment of the objective Scales was done on Day 15. Results: PSQI SCORE: Based on the observations there was a significant improvement (p= &lt;0.001) in PSQI Global score. WHO-QOL BREF: There was a significant improvement (p= &lt;0.001, p = 0.016) respectively in the Physical &amp; Psychological Health Domains in WHO=QOL BREF questionnaire. However, no significant changes observed in overall quality of life (p=1.000), overall quality of general health (p=I.000), Domain Social Relationships (p=I.000), Environmental Health (p=I.000). Conclusion: It can be concluded that Trataka Kriya is effective in improving the quality of sleep in population aged 30-50 years.

The Relationship Between the Interpersonal Relationship and Altruistic Behavior of College Students Majoring in Physical Education: The Mediating Effect of Empathy and the Moderating Effect of Responsibility.

Students majoring in physical education are the main source of physical education teachers in Chinese schools, and they are the main body in achieving the function of physical education in schools. The improvement of their altruistic behavior helps enhance the educational literacy of outstanding physical education teachers. This study conducted a questionnaire survey on 310 students majoring in physical education from 5 universities in 5 selected regions using the General Interpersonal Communication Objective Scale, Interpersonal Reactivity Index-C, the "responsibility" subscale of the Big Five Inventory Questionnaire, and the Altruistic Behavior of College Students questionnaire. We performed correlation analysis, mediation effect analysis, and moderation effect analysis on the data using SPSS 24.0 and MPLUS 7.4. Empathy partially mediates 30% of the total effect between interpersonal relationships and altruistic behavior; social responsibility has a moderating effect on empathy and altruistic behavior, with higher levels of responsibility having a greater moderating effect. Interpersonal relationships, empathy, and a sense of responsibility affect the current, recent, and long-term states of altruistic behavior, respectively. To improve students' altruistic behavior throughout the entire process, schools should develop training systems specifically for interpersonal relationships, empathy, and social responsibility.

Shared visuo-tactile interactive perception for robust object pose estimation

Shared perception between robotic systems significantly enhances their ability to understand and interact with their environment, leading to improved performance and efficiency in various applications. In this work, we present a novel full-fledged framework for robotic systems to interactively share their visuo-tactile perception for the robust pose estimation of novel objects in dense clutter. This is demonstrated with a two-robot team sharing their visuo-tactile scene representation which then declutters the scene using interactive perception and precisely estimates the 6 Degrees-of-Freedom (DoF) pose and 3 DoF scale of a target unknown object. This is achieved with the Stochastic Translation-Invariant Quaternion Filter (S-TIQF), a novel Bayesian filtering method with robust stochastic optimization for estimating the globally optimal pose of a target object. S-TIQF is also deployed to perform in situ visuo-tactile hand-eye calibration, since shared perception requires accurate extrinsic calibration between the two different sensing modalities, tactile and visual. Finally, we develop a novel active shared visuo-tactile representation and object reconstruction method employing a joint information gain criterion to improve the sample efficiency of the robot actions. To validate the effectiveness of our approach, we perform extensive experiments across standard datasets for pose estimation, as well as real-robot experiments with opaque, transparent and specular objects in randomised clutter settings and comprehensive comparison with other state-of-the-art approaches. Our experiments indicate that our approach outperforms state-of-the-art methods in terms of pose estimation accuracy for dense visual and sparse tactile point clouds.

Cross-Field Road Markings Detection Based on Inverse Perspective Mapping.

With the rapid development of the autonomous vehicles industry, there has been a dramatic proliferation of research concerned with related works, where road markings detection is an important issue. When there is no public open data in a field, we must collect road markings data and label them by ourselves manually, which is huge labor work and takes lots of time. Moreover, object detection often encounters the problem of small object detection. The detection accuracy often decreases when the detection distance increases. This is primarily because distant objects on the road take up few pixels in the image and object scales vary depending on different distances and perspectives. For the sake of solving the issues mentioned above, this paper utilizes a virtual dataset and open dataset to train the object detection model and cross-field testing in the field of Taiwan roads. In order to make the model more robust and stable, the data augmentation method is employed to generate more data. Therefore, the data are increased through the data augmentation method and homography transformation of images in the limited dataset. Additionally, Inverse Perspective Mapping is performed on the input images to transform them into the bird's eye view, which solves the "small objects at far distance" problem and the "perspective distortion of objects" problem so that the model can clearly recognize the objects on the road. The model testing on the front-view images and bird's eye view images also shows a remarkable improvement of accuracy by 18.62%.

YH-RTYO: an end-to-end object detection method for crop growth anomaly detection in UAV scenarios.

Small object detection via unmanned Aerial vehicle (UAV) is crucial for smart agriculture, enhancing yield and efficiency. This study addresses the issue of missed detections in crowded environments by developing an efficient algorithm tailored for precise, real-time small object detection. The proposed Yield Health Robust Transformer-YOLO (YH-RTYO) model incorporates several key innovations to advance conventional convolutional models. The model features an efficient convolutional expansion module that captures additional feature information through extended branches while maintaining parameter efficiency by consolidating features into a single convolution during validation. It also includes a local feature pyramid module designed to suppress background interference during feature interaction. Furthermore, the loss function is optimized to accommodate various object scales in different scenes by adjusting the regression box size and incorporating angle factors. These enhancements collectively contribute to improved detection performance and address the limitations of traditional methods. Compared to YOLOv8-L, the YH-RTYO model achieves superior performance in all key accuracy metrics, with a 13% reduction in the scale of model. Experimental results demonstrate that the YH-RTYO model outperforms others in key detection metrics. The model reduces the number of parameters by 13%, facilitating deployment while maintaining accuracy. On the OilPalmUAV dataset, it achieves a 3.97% improvement in average precision (AP). Additionally, the model shows strong generalization on the RFRB dataset, with AP50 and AP values exceeding those of the YOLOv8 baseline by 3.8% and 2.7%, respectively.

Zone Evaluation: Revealing Spatial Bias in Object Detection.

A fundamental limitation of object detectors is that they suffer from "spatial bias", and in particular perform less satisfactorily when detecting objects near image borders. For a long time, there has been a lack of effective ways to measure and identify spatial bias, and little is known about where it comes from and what degree it is. To this end, we present a new zone evaluation protocol, extending from the traditional evaluation to a more generalized one, which measures the detection performance over zones, yielding a series of Zone Precisions (ZPs). For the first time, we provide numerical results, showing that the object detectors perform quite unevenly across the zones. Surprisingly, the detector's performance in the 96% border zone of the image does not reach the AP value (Average Precision, commonly regarded as the average detection performance in the entire image zone). To better understand spatial bias, a series of heuristic experiments are conducted. Our investigation excludes two intuitive conjectures about spatial bias that the object scale and the absolute positions of objects barely influence the spatial bias. We find that the key lies in the human-imperceptible divergence in data patterns between objects in different zones, thus eventually forming a visible performance gap between the zones. With these findings, we finally discuss a future direction for object detection, namely, spatial disequilibrium problem, aiming at pursuing a balanced detection ability over the entire image zone. By broadly evaluating 10 popular object detectors and 5 detection datasets, we shed light on the spatial bias of object detectors. We hope this work could raise a focus on detection robustness.

Prior Knowledge-Guided U-Net for Automatic Clinical Target Volume Segmentation in Postmastectomy Radiation Therapy of Breast Cancer.

This study aimed to design and evaluate a prior-knowledge-guided U-Net (PK-UNet) for automatic clinical target volume (CTV) segmentation in postmastectomy radiation therapy for breast cancer. A total of 102 computed tomography (CT) scans from breast cancer patients who underwent postmastectomy were retrospectively collected. Of these, 80 scans were used for training with 5-fold cross-validation, and 22 scans for independent testing. The CTV included the chest wall, supraclavicular region, and axillary group III. The proposed PK-UNet method employs a 2-stage auto-segmentation process. Initially, the localization network categorizes CT slices based on the anatomic information of the CTV and generates prior knowledge labels. These outputs, along with the CT images, were fed into the final segmentation network. Quantitative evaluation was conducted using the mean Dice similarity coefficient (DSC), 95% Hausdorff distance, average surface distance, and surface DSC. A four-level objective scale evaluation was performed by 2 experienced radiation oncologists in a randomized double-blind manner. Quantitative evaluations revealed that PK-UNet significantly outperformed state-of-the-art segmentation methods (P < .01), with a mean DSC of 0.90 ± 0.02 and a 95% Hausdorff distance of 2.82 ± 1.29 mm. The mean average surface distance of PK-UNet was 0.91 ± 0.22 mm and the surface DSC was 0.84 ± 0.07, significantly surpassing the performance of AdwU-Net (P < .01) and showing comparable results to other models. Clinical evaluation confirmed the efficacy of PK-UNet, with 81.8% of the predicted contours being acceptable for clinical application. The advantages of the auto-segmentation capability of PK-UNet were most evident in the superior and inferior slices and slices with discontinuities at the junctions of different subregions. The average manual correction time was reduced to 1.02 min, compared with 18.20 min for manual contouring leading to a 94.4% reduction in working time. This study introduced the pioneering integration of prior medical knowledge into a deep learning framework for postmastectomy radiation therapy. This strategy addresses the challenges of CTV segmentation in postmastectomy radiation therapy and improves clinical workflow efficiency.

A Universal Method for Quantitatively Measuring Land Surface Anomaly Intensity Using Multiscale Remote Sensing Features

Land surface anomalies refer to various activities on the Earth’s surface that consist of short-term and sudden changes due to external disturbances. These anomalies are closely related to the safety of human life and property. Remote sensing offers irreplaceable advantages such as broad coverage, high temporal dynamics, and comprehensive observations, so it is the most effective tool for monitoring land surface anomalies and measuring their intensities. However, existing studies have limitations such as unclear sensitivity features, uncertain applicability, and a lack of quantitative expression at different scales. Therefore, this study develops a quantitative assessment framework for land surface anomaly intensity across four scales: the pixel scale, structure scale, object scale, and scene scale. This framework enables an adaptive and flexible weight determination of the intensity of land surface anomalies from a satellite perspective. Using the Chongqing fire as an example of a land surface anomaly, this study evaluates its land surface anomaly intensity. Moreover, we demonstrate the method’s applicability to other land surface anomaly events, such as floods and earthquakes. The experiments reveal that the land surface anomaly intensity evaluation framework, which is constructed based on pixel-scale, structure-scale, object-scale, and scene-scale features, can quantitatively express the land surface anomaly intensity with an accuracy of 75.25% and more effectively represent severely affected areas. The weights of the features at the four scales sequentially decrease: structure scale (0.2974), pixel scale (0.3225), object scale (0.1867), and scene scale (0.1932). The extensive application of this method to other land surface anomaly events provides accurate quantitative expressions of the land surface anomaly intensity. This remote sensing-based multiscale feature assessment method is adaptable and applicable to various land surface anomalies and offers critical decision support for land surface anomaly intensity warning systems.

Coal and Gangue Detection Networks with Compact and High-Performance Design.

The efficient separation of coal and gangue remains a critical challenge in modern coal mining, directly impacting energy efficiency, environmental protection, and sustainable development. Current machine vision-based sorting methods face significant challenges in dense scenes, where label rewriting problems severely affect model performance, particularly when coal and gangue are closely distributed in conveyor belt images. This paper introduces CGDet (Coal and Gangue Detection), a novel compact convolutional neural network that addresses these challenges through two key innovations. First, we proposed an Object Distribution Density Measurement (ODDM) method to quantitatively analyze the distribution density of coal and gangue, enabling optimal selection of input and feature map resolutions to mitigate label rewriting issues. Second, we developed a Relative Resolution Object Scale Measurement (RROSM) method to assess object scales, guiding the design of a streamlined feature fusion structure that eliminates redundant components while maintaining detection accuracy. Experimental results demonstrate the effectiveness of our approach; CGDet achieved superior performance with AP50 and AR50 scores of 96.7% and 99.2% respectively, while reducing model parameters by 46.76%, computational cost by 47.94%, and inference time by 31.50% compared to traditional models. These improvements make CGDet particularly suitable for real-time coal and gangue sorting in underground mining environments, where computational resources are limited but high accuracy is essential. Our work provides a new perspective on designing compact yet high-performance object detection networks for dense scene applications.

ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection

Object detection using UAV images is a current research focus in the field of computer vision, with frequent advancements in recent years. However, many methods are ineffective for challenging UAV images that feature uneven object scales, sparse spatial distribution, and dense occlusions. We propose a new algorithm for detecting small objects in UAV images, called ATBHC-YOLO. Firstly, the MS-CET module has been introduced to enhance the model’s focus on global sparse features in the spatial distribution of small objects. Secondly, the BHC-FB module is proposed to address the large-scale variance of small objects and enhance the perception of local features. Finally, a more appropriate loss function, WIoU, is used to penalise the quality variance of small object samples and further enhance the model’s detection accuracy. Comparison experiments on the DIOR and VEDAI datasets validate the effectiveness and robustness of the improved method. By conducting experiments on the publicly available UAV benchmark dataset Visdrone, ATBHC-YOLO outperforms the state-of-the-art method(YOLOv7) by 3.5%.