Search Results (250)

Computer vision is of wide interest to perform the phenotyping of horticultural crops such as apple trees at high throughput. In orchards specially constructed for variety testing or breeding programs, computer vision tools should be able to extract phenotypical information form each tree separately. We focus on segmenting individual apple trees as the main task in this context. Segmenting individual apple trees in dense orchard rows is challenging because of the complexity of outdoor illumination and intertwined branches. Traditional methods rely on supervised learning, which requires a large amount of annotated data. In this study, we explore an alternative approach using prompt engineering with the Segment Anything Model and its variants in a zero-shot setting. Specifically, we first detect the trunk and then position a prompt (five points in a diamond shape) located above the detected trunk to feed to the Segment Anything Model. We evaluate our method on the apple REFPOP, a new large-scale European apple tree dataset and on another publicly available dataset. On these datasets, our trunk detector, which utilizes a trained YOLOv11 model, achieves a good detection rate of $97\%$ based on the prompt located above the detected trunk, achieving a Dice score of 70% without training on the REFPOP dataset and 84% without training on the publicly available dataset.We demonstrate that our method equals or even outperforms purely supervised segmentation approaches or non-prompted foundation models. These results underscore the potential of foundational models guided by well-designed prompts as scalable and annotation-efficient solutions for plant segmentation in complex agricultural environments. Full article

Blindness and low vision are increasing serious public health issues that affect a significant percentage of the population worldwide. Vision plays a crucial role in spatial navigation and daily activities. Its reduction or loss creates numerous challenges for an individual. Assistive technology can enhance mobility and navigation in outdoor environments. In the field of orientation and mobility training, technologies with haptic interaction can assist individuals with visual impairments in learning how to navigate safely and effectively using the sense of touch. This paper presents a virtual reality platform designed to support the development of navigation techniques within a safe yet realistic environment, expanding upon existing research in the field. Following extensive optimization, we present a visual representation that accurately simulates various 3D tile textures using graphics replicating real tactile surfaces. We conducted a user interaction study in a virtual environment consisting of 3D navigation tiles enhanced with tactile textures, placed appropriately for a real-world scenario, to assess user performance and experience. This study also assess the usability and user experience of the platform. We hope that the findings will contribute to the development of new universal navigation techniques for people with visual impairments. Full article

Background: Motion capture (MoCap) technologies have transformed athlete monitoring, yet athletic departments face complex decisions when selecting systems for multiple sports. Methods: We conducted a narrative review of peer-reviewed studies (2015–2025) examining optical marker-based, inertial measurement unit (IMU) systems, including Global Navigation Satellite System (GNSS)-integrated systems, and markerless computer vision systems. Studies were evaluated for validated accuracy metrics across indoor court, aquatic, and outdoor field environments. Results: Optical systems maintain sub-millimeter accuracy in controlled environments but face field limitations. IMU systems demonstrate an angular accuracy of 2–8° depending on movement complexity. Markerless systems show variable accuracy (sagittal: 3–15°, transverse: 3–57°). Environmental factors substantially impact system performance, with aquatic settings introducing an additional orientation error of 2° versus terrestrial applications. Outdoor environments challenge GNSS-based tracking (±0.3–3 m positional accuracy). Critical gaps include limited gender-specific validation and insufficient long-term reliability data. Conclusions: This review proposes a tiered implementation framework combining foundation-level team monitoring with specialized assessment tools. This evidence-based approach guides the selection of technology aligned with organizational priorities, sport-specific requirements, and resource constraints. Full article

Single image dehazing is a fundamental task in computer vision, aiming to recover a clear scene from a hazy input image. To address the limitations of traditional dehazing algorithms—particularly in global feature association and local detail preservation—this study proposes a novel Transformer-based dehazing model enhanced by an interactive channel attention mechanism. The proposed architecture adopts a U-shaped encoder–decoder framework, incorporating key components such as a feature extraction module and a feature fusion module based on interactive attention. Specifically, the interactive channel attention mechanism facilitates cross-layer feature interaction, enabling the dynamic fusion of global contextual information and local texture details. The network architecture leverages a multi-scale feature pyramid to extract image information across different dimensions, while an improved cross-channel attention weighting mechanism enhances feature representation in regions with varying haze densities. Extensive experiments conducted on both synthetic and real-world datasets—including the RESIDE benchmark—demonstrate the superior performance of the proposed method. Quantitatively, it achieves PSNR gains of 0.53 dB for indoor scenes and 1.64 dB for outdoor scenes, alongside SSIM improvements of 1.4% and 1.7%, respectively, compared with the second-best performing method. Qualitative assessments further confirm that the proposed model excels in restoring fine structural details in dense haze regions while maintaining high color fidelity. These results validate the effectiveness of the proposed approach in enhancing both perceptual quality and quantitative accuracy in image dehazing tasks. Full article

Aiming to address the problems of fewer related studies on autonomous navigation algorithms based on multi-sensor fusion in complex scenarios in pastures, lower degrees of fusion, and insufficient cruising accuracy of the operation path in complex outdoor environments, a multimodal autonomous navigation system is proposed based on a loosely coupled architecture of Cartographer–RTAB-Map (real-time appearance-based mapping). Through laser-vision inertial guidance multi-sensor data fusion, the system achieves high-precision mapping and robust path planning in complex scenes. First, comparing the mainstream laser SLAM algorithms (Hector/Gmapping/Cartographer) through simulation experiments, Cartographer is found to have a significant memory efficiency advantage in large-scale scenarios and is thus chosen as the front-end odometer. Secondly, a two-way position optimization mechanism is innovatively designed: (1) When building the map, Cartographer processes the laser with IMU and odometer data to generate mileage estimations, which provide positioning compensation for RTAB-Map. (2) RTAB-Map fuses the depth camera point cloud and laser data, corrects the global position through visual closed-loop detection, and then uses 2D localization to construct a bimodal environment representation containing a 2D raster map and a 3D point cloud, achieving a complete description of the simulated ranch environment and material morphology and constructing a framework for the navigation algorithm of the pushing robot based on the two types of fused data. During navigation, the combination of RTAB-Map’s global localization and AMCL’s local localization is used to generate a smoother and robust positional attitude by fusing IMU and odometer data through the EKF algorithm. Global path planning is performed using Dijkstra’s algorithm and combined with the TEB (Timed Elastic Band) algorithm for local path planning. Finally, experimental validation is performed in a laboratory-simulated pasture environment. The results indicate that when the RTAB-Map algorithm fuses with the multi-source odometry, its performance is significantly improved in the laboratory-simulated ranch scenario, the maximum absolute value of the error of the map measurement size is narrowed from 24.908 cm to 4.456 cm, the maximum absolute value of the relative error is reduced from 6.227% to 2.025%, and the absolute value of the error at each location is significantly reduced. At the same time, the introduction of multi-source mileage fusion can effectively avoid the phenomenon of large-scale offset or drift in the process of map construction. On this basis, the robot constructs a fusion map containing a simulated pasture environment and material patterns. In the navigation accuracy test experiments, our proposed method reduces the root mean square error (RMSE) coefficient by 1.7% and Std by 2.7% compared with that of RTAB-MAP. The RMSE is reduced by 26.7% and Std by 22.8% compared to that of the AMCL algorithm. On this basis, the robot successfully traverses the six preset points, and the measured X and Y directions and the overall position errors of the six points meet the requirements of the pasture-pushing task. The robot successfully returns to the starting point after completing the task of multi-point navigation, achieving autonomous navigation of the robot. Full article

Haze significantly degrades image quality by reducing contrast and blurring object boundaries, which impairs the performance of computer vision systems. Among various approaches, single-image dehazing remains particularly challenging due to the absence of depth information. While Vision Transformer (ViT)-based models have achieved remarkable results by leveraging multi-head attention and large effective receptive fields, their high computational complexity limits their applicability in real-time and embedded systems. To address this limitation, we propose MLKD-Net, a lightweight CNN-based model that incorporates a novel Multi-Head Large Kernel Block (MLKD), which is based on the Multi-Head Large Kernel Attention (MLKA) mechanism. This structure preserves the benefits of large receptive fields and a multi-head design while also ensuring compactness and computational efficiency. MLKD-Net achieves a PSNR of 37.42 dB on the SOTS-Outdoor dataset while using 90.9% fewer parameters than leading Transformer-based models. Furthermore, it demonstrates real-time performance with 55.24 ms per image (18.2 FPS) on the NVIDIA Jetson Orin Nano in TensorRT-INT8 mode. These results highlight its effectiveness and practicality for resource-constrained, real-time image dehazing applications. Full article

Traditional structural damage detection relies on multi-sensor arrays (e.g., total stations, accelerometers, and GNSS). However, these sensors have some inherent limitations such as high cost, limited accuracy, and environmental sensitivity. Advances in computer vision technology have driven the research on vision-based structural vibration analysis and damage identification. In this study, an optimized Lucas–Kanade optical flow algorithm is proposed, and it integrates feature point trajectory analysis with an adaptive thresholding mechanism, and improves the accuracy of the measurements through an innovative error vector filtering strategy. Comprehensive experimental validation demonstrates the performance of the algorithm in a variety of test scenarios. The method tracked MTS vibrations with 97% accuracy in a laboratory environment, and the robustness of the environment was confirmed by successful noise reduction using a dedicated noise-suppression algorithm under camera-induced interference conditions. UAV field tests show that it effectively compensates for UAV-induced motion artifacts and maintains over 90% measurement accuracy in both indoor and outdoor environments. Comparative analyses show that the proposed UAV-based method has significantly improved accuracy compared to the traditional optical flow method, providing a highly robust visual monitoring solution for structural durability assessment in complex environments. Full article

Improvement of recreational areas between the residential areas to achieve human behavior and the concept of humanization is urgently needed to achieve the 2030 vision of Saudi Arabia. This study aims to develop a parametric urban optimization framework to optimize the outdoor thermal comfort in outdoor recreational areas between residential buildings in Riyadh City, Saudi Arabia, based on the 2030 vision of Saudi Arabia to achieve a high standard of quality of life with thermal comfort. Measurement was conducted inside the sports walking path with walk-through observation and interviews. Then, case study geometry was generated computationally, using Rhinoceros software and its plug-in Grasshopper to implement the set of development scenarios. Then, the optimization process for the case study was integrated with 192 proposed development solutions to assess the solutions’ influence in reducing the Universal Thermal Comfort Index (UTCI) and average solar irradiance, besides increasing energy generated by PV panels. EnergyPlus engine and Ladybug plug-in are used to integrate PV panels with shading scenarios, to utilize the high solar irradiation, and to calculate the generated electrical energy. The results concluded that trees with diameters between 10 and 15 m could achieve thermal comfort and reduction UTCI by 11.26 K and average solar irradiance by 642.77 W/m² with average energy generation of PV panel and optimum inclination angle of 20°. The integration of PV with shading scenarios generates electricity for every square meter of PV panel, equal to 578.84 kWh/m² for lighting poles and service areas within the recreational areas. The results of this study help to improve the current park as a prototype, for which results can be implemented in more than 8100 instances of gardens, parks, and municipal squares in Saudi Arabia. Full article

Activity recognition and localization in outdoor environments involve identifying and tracking human movements using sensor data, computer vision, or deep learning techniques. This process is crucial for applications such as smart surveillance, autonomous systems, healthcare monitoring, and human–computer interaction. However, several challenges arise in outdoor settings, including varying lighting conditions, occlusions caused by obstacles, environmental noise, and the complexity of differentiating between similar activities. This study presents a hybrid deep learning approach that integrates human activity recognition and localization in outdoor environments using Wi-Fi signal data. The study focuses on applying the hybrid long short-term memory–bi-gated recurrent unit (LSTM-BIGRU) architecture, designed to enhance the accuracy of activity recognition and location estimation. Moreover, experiments were conducted using a real-world dataset collected with the PicoScene Wi-Fi sensing device, which captures both magnitude and phase information. The results demonstrated a significant improvement in accuracy for both activity recognition and localization tasks. To mitigate data scarcity, this study utilized the conditional tabular generative adversarial network (CTGAN) to generate synthetic channel state information (CSI) data. Additionally, carrier frequency offset (CFO) and cyclic shift delay (CSD) preprocessing techniques were implemented to mitigate phase fluctuations. The experiments were conducted in a line-of-sight (LoS) outdoor environment, where CSI data were collected using the PicoScene Wi-Fi sensor platform across four different activities at outdoor locations. Finally, a comparative analysis of the experimental results highlights the superior performance of the proposed hybrid LSTM-BIGRU model, achieving 99.81% and 98.93% accuracy for activity recognition and location prediction, respectively. Full article

The convergence of the Internet of Physical–Virtual Things (IoPVT) and the Metaverse presents a transformative opportunity for safety and health monitoring in outdoor environments. This concept paper explores how integrating human activity recognition (HAR) with the IoPVT within the Metaverse can revolutionize public health and safety, particularly in urban settings with challenging climates and architectures. By seamlessly blending physical sensor networks with immersive virtual environments, the paper highlights a future where real-time data collection, digital twin modeling, advanced analytics, and predictive planning proactively enhance safety and well-being. Specifically, three dimensions of humans, technology, and the environment interact toward measuring safety, health, and climate. Three outdoor cultural scenarios showcase the opportunity to utilize HAR–IoPVT sensors for urban external staircases, rural health, climate, and coastal infrastructure. Advanced HAR–IoPVT algorithms and predictive analytics would identify potential hazards, enabling timely interventions and reducing accidents. The paper also explores the societal benefits, such as proactive health monitoring, enhanced emergency response, and contributions to smart city initiatives. Additionally, we address the challenges and research directions necessary to realize this future, emphasizing AI technical scalability, ethical considerations, and the importance of interdisciplinary collaboration for designs and policies. By articulating an AI-driven HAR vision along with required advancements in edge-based sensor data fusion, city responsiveness with fog computing, and social planning through cloud analytics, we aim to inspire the academic community, industry stakeholders, and policymakers to collaborate in shaping a future where technology profoundly improves outdoor health monitoring, enhances public safety, and enriches the quality of urban life. Full article

Defocus deblurring is a challenging task in the fields of computer vision and image processing. The irregularity of defocus blur kernels, coupled with the limitations of computational resources, poses significant difficulties for defocused image restoration. Additionally, the varying degrees of blur across different regions of the image impose higher demands on feature capture. Insufficient fine-grained feature extraction can result in artifacts and the loss of details, while inadequate coarse-grained feature extraction can cause image distortion and unnatural transitions. To address these challenges, we propose a defocus image deblurring method based on a hybrid CNN–Mamba architecture. This approach employs a data-driven, network-based self-learning strategy for blur processing, eliminating the need for traditional blur kernel estimation. Furthermore, by designing parallel feature extraction modules, the method leverages the local feature extraction capabilities of CNNs to capture image details, effectively restoring texture and edge information. The Mamba module models long-range dependencies, ensuring global consistency in the image. On the real defocus blur dual-pixel image dataset DPDD, the proposed CMDDNet achieves a PSNR of 28.37 in the Indoor dataset, surpassing Uformer-B (28.23) while significantly reducing the parameter count to only 9.74 M, which is 80.9% less than Uformer-B (50.88 M). Although the PSNR on the Outdoor and Combined datasets is slightly lower, CMDDNet maintains competitive performance with a significantly reduced model size, demonstrating its efficiency and effectiveness in defocus deblurring. These results indicate that CMDDNet offers a promising trade-off between performance and computational efficiency, making it well suited for lightweight applications. Full article

Pest infestations have always been a major factor affecting tea production. Real-time detection of tea pests using machine vision is a mainstream method in modern agricultural pest control. Currently, there is a notable absence of machine vision devices capable of real-time monitoring for small-sized tea pests in the market, and the scarcity of open-source datasets available for tea pest detection remains a critical limitation. This manuscript proposes a YOLOv8-FasterTea pest detection algorithm based on cross-domain transfer learning, which was successfully deployed in a novel tea pest monitoring device. The proposed method leverages transfer learning from the natural language character domain to the tea pest detection domain, termed cross-domain transfer learning, which is based on the complex and small characteristics shared by natural language characters and tea pests. With sufficient samples in the language character domain, transfer learning can effectively enhance the tiny and complex feature extraction capabilities of deep networks in the pest domain and mitigate the few-shot learning problem in tea pest detection. The information and texture features of small tea pests are more likely to be lost with the layers of a neural network becoming deep. Therefore, the proposed method, YOLOv8-FasterTea, removes the P5 layer and adds a P2 small target detection layer based on the YOLOv8 model. Additionally, the original C2f module is replaced with lighter convolutional modules to reduce the loss of information about small target pests. Finally, this manuscript successfully applies the algorithm to outdoor pest monitoring equipment. Experimental results demonstrate that, on a small sample yellow board pest dataset, the mAP@.5 value of the model increased by approximately 6%, on average, after transfer learning. The YOLOv8-FasterTea model improved the mAP@.5 value by 3.7%, while the model size was reduced by 46.6%. Full article

Enhancing the visibility of outdoor images under sandstorm conditions remains a significant challenge in computer vision due to the complex atmospheric interference caused by dust particles. While existing image enhancement algorithms perform well in mild sandstorm scenarios, they often struggle to produce satisfactory results in more severe conditions, where residual color casts and chromatic artifacts become pronounced. These limitations highlight the need for a more robust and adaptable restoration method. In this study, we propose an advanced algorithm designed to restore sand-dust images under varying sandstorm intensities, effectively addressing the aforementioned challenges. The approach begins with a color correction step, achieved through channel compensation and color transfer techniques, which leverage the unique statistical properties of sand-dust images. To further refine the restoration, we improve the boundary constraints of the saturation line prior (SLP) by adjusting the local illumination in the atmospheric light map, enhancing the model’s robustness to environmental variations. Finally, the atmospheric scattering model is employed for comprehensive image restoration, ensuring that color correction and dust removal are optimized. Extensive experiments on real-world sandstorm images demonstrate that the proposed method performs on par with state-of-the-art (SOTA) techniques in weaker sandstorm scenarios, showing marked improvements in more severe conditions. These results highlight the potential of our approach for practical applications in outdoor image enhancement under challenging environmental conditions. Full article

Vision-based UAV-AGV (Unmanned Aerial Vehicle–Autonomous Ground Vehicle) systems are prominent for executing tasks in GPS (Global Positioning System)-inaccessible areas. One of the roles of the UAV is guiding the navigation of the AGV. Reactive/mapless navigation assistance to an AGV from a UAV is well known and suitable for computationally less powerful systems. This method requires communication between both agents during navigation as per state of the art. However, communication delays and failures will cause failures in tasks, especially during outdoor missions. In the present work, we propose a mapless technique for the navigation of AGVs assisted by UAVs without communication of obstacles to AGVs. The considered scenario is that the AGV is undergoing sensor and communication module failure and is completely dependent on the UAV for its safe navigation. The goal of the UAV is to take AGV to the destination while guiding it to avoid obstacles. We exploit the autonomous tracking task between the UAV and AGV for obstacle avoidance. In particular, AGV tracking the motion of the UAV is exploited for the navigation of the AGV. YOLO (You Only Look Once) v8 has been implemented to detect the drone by AGV camera. The sliding mode control method is implemented for the tracking motion of the AGV and obstacle avoidance control. The job of the UAV is to localize obstacles in the image plane and guide the AGV without communicating with it. Experimental results are presented to validate the proposed method. This proves to be a significant technique for the safe navigation of the AGV when it is non-communicating and experiencing sudden sensor failure. Full article

Background/Objectives: Asymmetric myopic peripheral defocus lenses (MPDLs) have proven to be effective in slowing the progression of myopia in Spanish children over a period of 12 months. The purpose of this study was to assess the MPDL spectacles’ efficacy in slowing myopia progression over a 24-month period in children. Methods: This study extends the follow-up period of the double-masked, prospective, and randomized clinical trial previously published to 24 months. Children from 6 to 12 years were assigned to two groups: a control group wearing spherotorical single vision lenses (SVLs) or a treatment group wearing MPDL lenses. Inclusion criteria included children with myopia less than −0.50 D, astigmatism below 1.50 D, and best-corrected visual acuity of at least 20/20. Participants underwent cycloplegic autorefractive examination and axial length (AL) measurements at the baseline and six and twelve months in the study already published, and twenty-four months later in the present study. Lifestyle factors, including outdoor activities and digital device use, were also assessed. Baseline characteristics, including age, refractive error, and AL, were comparable between groups. Dropout rates were 15.9%, with 14 participants lost to follow-up, distributed equally between the two groups. Results: After 24 months of follow-up, 69 children remained in this study, comprising 34 participants in the SVL cohort and 35 in the MPDL cohort. Over 24 months, the MPDL group showed significantly less AL elongation than the SVL group (0.27 ± 0.23 mm and 0.37 ± 0.24 mm; p = 0.0341). The mean relative AL increase was 1.10 ± 0.95% in the MPDL group, compared to 1.56 ± 1.02% in the SVL group (p = 0.0322). Younger children exhibited faster AL growth, while digital device use and outdoor activities did not affect AL changes. Conclusions: MPDL spectacle lenses substantially slowed myopia progression over a 24-month period, with 28.7% less progression in absolute AL growth and 29.8% in relative AL growth compared to SVL. These results indicate that MPDL lenses are an effective method for slowing myopia progression. Full article