Search Results (227)

In the field of Autonomous Surface Vehicle (ASV), research on advanced perception technologies is crucial for enhancing their intelligence and autonomy. In particular, laser point cloud registration technology serves as a foundation for improving the navigation accuracy and environmental awareness of ASV in complex environments. To address the issues of low computational efficiency, insufficient robustness, and incompatibility with low-power devices in laser point cloud registration technology for ASV, a novel point cloud matching method has been proposed. The proposed method includes laser point cloud data processing, feature extraction based on an improved Fast Point Feature Histogram (FPFH), followed by a two-step registration process using SAC-IA (Sample Consensus Initial Alignment) and Small_GICP (Small Generalized Iterative Closest Point). Registration experiments conducted on the KITTI benchmark dataset and the Pohang Canal dataset demonstrate that the relative translation error (RTE) of the proposed method is 16.41 cm, which is comparable to the performance of current state-of-the-art point cloud registration algorithms. Furthermore, deployment experiments on multiple low-power computing devices showcase the performance of the proposed method under low computational capabilities, providing reference metrics for engineering applications in the field of autonomous navigation and perception research for ASV. Full article

Although the dosimetric advantages of rectal spacers in prostate cancer radiotherapy have been demonstrated in selected clinical trials, real-world data from routine clinical practice remain limited—particularly within the Portuguese healthcare system. This study offers a detailed dosimetric comparison of Volumetric Modulated Arc Therapy (VMAT), with and without rectal spacer use, in a real-world patient cohort, aiming to assess the clinical relevance of spacer insertion under standard treatment protocols. A retrospective dosimetric evaluation was performed on 80 prostate cancer patients treated at a radiotherapy centre in southern Portugal. Patients were equally divided into two matched groups (n = 40): one receiving VMAT alone, the other receiving VMAT with hydrogel rectal spacer placement. Dose-volume histograms (DVHs) were analysed for the planning target volume (PTV) and key organs at risk (OARs). Standard dosimetric metrics, such as V50–V75 for the rectum and bladder, V50 for femoral heads, and mean dose for the penile bulb, were assessed. PTV coverage was evaluated using conformity and homogeneity indices. Spacer use significantly decreased rectal dose exposure across all evaluated parameters without compromising PTV coverage or increasing dose to other OARs. These findings support routine rectal spacer applications to enhance treatment safety and patient outcomes. Full article

This study presents a novel method for high-precision detection and quantitative evaluation of the spatial relationship between cells and amyloid-$\beta$ (A$\beta$) in time-lapse brightfield microscopy images. Achieving accurate detection of non-fluorescent cells and A$\beta$ deposits requires high-quality video images free from noise, distortion, and frame-to-frame luminance flicker. To this end, we employ a robust preprocessing pipeline that combines multi-frame integration with vignetting correction to enhance image quality and reduce luminance variability across frames. Key preprocessing steps include background correction via two-dimensional polynomial fitting, temporal smoothing of luminance fluctuations, histogram matching for luminance normalization, and dust artifact removal based on intensity thresholds. This enhanced imaging approach enables accurate identification of A$\beta$ aggregates, which typically appear as jelly-like structures and are difficult to detect under standard brightfield conditions. Furthermore, we introduce a quantitative index to assess the spatial relationship between cells and A$\beta$ concentrations, facilitating detailed analysis under varying A$\beta$ levels. Full article

Soil water content (SWC) critically governs the physical and mechanical behavior of soils. However, conventional methods such as oven drying are laborious, time-consuming, and difficult to replicate in the field. To overcome these limitations, we developed an image-based interpolation framework that leverages histogram statistics from 12 soil surface photographs spanning 3.83% to 19.75% SWC under controlled lighting. For each image, pixel-level values of red, green, blue (RGB) channels and hue, saturation, value (HSV) channels were extracted to compute per-channel histograms, whose empirical means and standard deviations were used to parameterize Gaussian probability density functions. Linear interpolation of these parameters yielded synthetic histograms and corresponding images at 1% SWC increments across the 4–19% range. Validation against the original dataset, using dice score (DS), Bhattacharyya distance (BD), and Earth Mover’s Distance (EMD) metrics, demonstrated that the interpolated images closely matched observed color distributions. Average BD was below 0.014, DS above 0.885, and EMD below 0.015 for RGB channels. For HSV channels, average BD was below 0.074, DS above 0.746, and EMD below 0.022. These results indicate that the proposed method reliably generates intermediate SWC data without additional direct measurements, especially with RGB. By reducing reliance on exhaustive sampling and offering a cost-effective dataset augmentation, this approach facilitates large-scale, noninvasive soil moisture estimation and supports machine learning applications where field data are scarce. Full article

Image encryption plays a critical role in ensuring the confidentiality and integrity of visual information, particularly in applications involving secure transmission and storage. While traditional cryptographic algorithms like AES are widely used, they may not fully exploit the properties of image data, such as high redundancy and spatial correlation. In recent years, chaotic systems have emerged as promising candidates for lightweight and secure encryption schemes, but comprehensive comparisons between different chaotic maps and standardized methods are still lacking. This study investigates the use of three classical chaotic systems—Henon, tent, and logistic maps—for image encryption, and evaluates their performance both visually and statistically. The research is motivated by the need to assess whether these well-known chaotic systems, when used with proper statistical sampling, can match or surpass conventional methods in terms of encryption robustness and complexity. We propose a key generation method based on chaotic iterations, statistically filtered for independence, and apply it to a one-time-pad-like encryption scheme. The encryption quality is validated over a dataset of 100 JPEG images of size $512\times 512$, using multiple evaluation metrics, including MSE, PSNR, NPCR, EQ, and UACI. Results are benchmarked against the AES algorithm to ensure interpretability and reproducibility. Our findings reveal that while the AES algorithm remains the fastest and most uniform in histogram flattening, certain chaotic systems, such as the tent and logistic maps, offer comparable or superior results in visual encryption quality and pixel-level unpredictability. The analysis highlights that visual encryption performance does not always align with statistical metrics, underlining the importance of multi-faceted evaluation. These results contribute to the growing body of research in chaos-based image encryption and provide practical guidelines for selecting encryption schemes tailored to specific application requirements, such as efficiency, visual secrecy, or implementation simplicity. Full article

The accurate and large-scale mapping of seagrass meadows is essential, as these meadows form primary habitats for marine organisms and large sinks for blue carbon. Image data available for mapping these habitats are often scarce or are acquired through multiple surveys and instruments, resulting in images of varying spatial and spectral characteristics. This study presents an unsupervised domain adaptation (UDA) strategy that combines histogram-matching with the transformer-based SegFormer model to address these challenges. Unoccupied aerial vehicle (UAV)-derived imagery (3-cm resolution) was used for training, while orthophotos from airplane surveys (12.5-cm resolution) served as the target domain. The method was evaluated across three Danish estuaries (Horsens Fjord, Skive Fjord, and Lovns Broad) using one-to-one, leave-one-out, and all-to-one histogram matching strategies. The highest performance was observed at Skive Fjord, achieving an F1-score/IoU = 0.52/0.48 for the leave-one-out test, corresponding to 68% of the benchmark model that was trained on both domains. These results demonstrate the potential of this lightweight UDA approach to generalization across spatial, temporal, and resolution domains, enabling the cost-effective and scalable mapping of submerged vegetation in data-scarce environments. This study also sheds light on contrast as a significant property of target domains that impacts image segmentation. Full article

Civil structures carry significant service loads over long times but are prone to deterioration due to various natural impacts. Traditionally, these structures are inspected in situ by qualified engineers, a method that is high-cost, risky, time-consuming, and prone to error. Recently, researchers have explored innovative practices by using virtual reality (VR) technologies as inspection platforms. Despite such efforts, a critical question remains: can VR models accurately reflect real-world structural conditions? This study presents a comprehensive framework for assessing the visual fidelity of VR models for structural inspection. To make it viable, we first introduce a novel workflow that integrates UAV-based photogrammetry, computer graphics, and web-based VR editing to establish interactive VR user interfaces. We then propose a visual fidelity assessment methodology that quantitatively evaluates the accuracy of the VR models through image alignment, histogram matching, and pixel-level deviation mapping between rendered images from the VR models and UAV-captured images under matched viewpoints. The proposed frameworks are validated using two case studies: a historic stone arch bridge and a campus steel building. Overall, this study contributes to the growing body of knowledge on VR-based structural inspections, providing a foundation for our peers for their further research in this field. Full article

To endow a star sensor with strong robustness, low algorithm complexity, and a small database, this paper proposes an all-sky star identification algorithm based on spherical polar pattern matching. The proposed algorithm consists of three main steps. First, the guide star is rotated to be a polar star, and the polar and azimuth angles of neighboring stars are used as polar pattern elements of the guide star. Then, the relative azimuth histogram is applied to the spherical polar pattern matching, and a star pair after spherical polar pattern matching is identified through angular distance cross-verification. Finally, a reference star image is generated from the identified star pair to complete the matching process of all guide stars in the field of view. The proposed algorithm is verified by simulation experiments. The simulation results show that for a star sensor with a medium field of view (15° × 15°, 1024 × 1024 pixel) and a limiting magnitude of 6.0 Mv, the required database size is 161 KB. When false and missing star spots account for 50% of the guide stars and the star spot extraction error is 1.0 pixel, the average star identification time is 0.35 ms (@i7-4790), and the identification probability is 99.9%. However, when false and missing star spots account for 100% of the guide stars and the star spot extraction error is 5.0 pixel, the average star identification time is less than 2.0 ms, and the identification probability is 97.1%. Full article

Background/Objectives: Accurate and efficient diagnosis of heart disease through electrocardiogram (ECG) analysis remains a critical challenge in clinical practice due to noise interference, morphological variability, and the complexity of overlapping cardiac signals. Methods: This study presents a comprehensive deep learning (DL) framework that integrates advanced ECG signal segmentation with transfer learning-based classification, aimed at improving diagnostic performance. The proposed ECG segmentation algorithm introduces a distinct and original approach compared to prior research by integrating adaptive preprocessing, histogram-based lead separation, and robust point-tracking techniques into a unified framework. While most earlier studies have addressed ECG image processing using basic filtering, fixed-region cropping, or template matching, our method uniquely focuses on automated and precise reconstruction of individual ECG leads from noisy and overlapping multi-lead images—a challenge often overlooked in previous work. This innovative segmentation strategy significantly enhances signal clarity and enables the extraction of richer and more localized features, boosting the performance of DL classifiers. The dataset utilized in this work of 12 lead-based standard ECG images consists of four primary classes. Results: Experiments conducted using various DL models—such as VGG16, VGG19, ResNet50, InceptionNetV2, and GoogleNet—reveal that segmentation notably enhances model performance in terms of recall, precision, and F1 score. The hybrid VGG19 + SVM model achieved 98.01% and 100% accuracy in multi-class classification, along with average accuracies of 99% and 97.95% in binary classification tasks using the original and reconstructed datasets, respectively. Conclusions: The results highlight the superiority of deep, feature-rich models in handling reconstructed ECG signals and confirm the value of segmentation as a critical preprocessing step. These findings underscore the importance of effective ECG segmentation in DL applications for automated heart disease diagnosis, offering a more reliable and accurate solution. Full article

The roughness of the Earth’s surface dictates the nature of air flow across it. Detailed meteorological data that are necessary to access the aerodynamic roughness ($z_0$) are not widely collected and, as such, the geometry of a surface can be used to estimate $z_0$. Here, we present a novel formulation, and the corresponding computer code, to compute $z_0$ based on the Lettau (1969) geometric approach. The new code produces a mean $z_0$, as well as a histogram of all $z_0$ values for each individual roughness element (e.g., 10 s of thousand for the 1000 × 1000 grids) discretized using watersheds, as well as directional $z_0$ diagrams, which can be matches with the wind rose for the location. The formulation includes two parameters that may optionally be applied to smooth the surface before calculating $z_0$. By calculating $z_0$ as a function of these two parameters, we demonstrate the sensitivity of the $z_0$ value to these parameter choices. Since a large portion of the Earth’s surface is snow covered during some parts of the year, and the roughness of the snow surface varies over the snow season and over space, we apply the code to three snow surface datasets. Each surface is during a different phases of the snowpack. Each surface is evaluated at two resolutions). These surfaces are: fresh snow accumulation (1 m² at 1 and 10 mm), peak accumulation (1 km² at 1 and 10 m) and ablation sun cups (25 m² at 5 and 50 mm). Full article

This paper addresses the challenge of robust pose estimation for spacecraft under rapid inter-frame motion, proposing a two-stage point cloud registration framework. The first stage computes coarse pose estimation by leveraging Fast Point Feature Histogram (FPFH) descriptors with random sample and consensus (RANSAC) for correspondence matching, effectively handling significant positional displacements. The second stage refines the solution through geometry-aware fine registration using raw point cloud data, enhancing precision through a multi-scale iterative ICP-like framework. To validate the approach, we simulate time-of-flight (ToF) sensor measurements by rendering NASA’s public 3D spacecraft models and obtain 3D point clouds by back-projecting the depth measurements to 3D space. Comprehensive experiments demonstrate superior performance over several state-of-the-art methods in both accuracy and robustness under rapid inter-frame motion scenarios. The dual-stage architecture proves effective in maintaining tracking continuity while mitigating error accumulation from fast relative motion, showing promise for autonomous spacecraft proximity operations. Full article

Industrial defect detection in edge computing environments faces critical challenges in balancing accuracy, efficiency, and adaptability under data scarcity. To address these limitations, we propose the Hybrid Anomaly Detection System (HyADS), a novel lightweight framework for edge-based industrial defect detection. HyADS integrates three synergistic modules: (1) a feature extractor that integrates Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) to capture robust texture features, (2) a lightweight U-net autoencoder that reconstructs normal patterns while preserving spatial details to highlight small-scale defects, and (3) an adaptive patch matching module inspired by memory bank retrieval principles to accurately localize local outliers. These components are synergistically fused and then fed into a segmentation head that unifies global reconstruction errors and local anomaly maps into pixel-accurate defect masks. Extensive experiments on the MVTec AD, NEU, and Severstal datasets demonstrate state-of-the-art performance. Notably, HyADS achieves state-of-the-art F1 scores (94.1% on MVTec) in anomaly detection and IoU scores (85.5% on NEU/82.8% on Seversta) in segmentation. Designed for edge deployment, this framework achieves real-time inference (40–45 FPS on an RTX 4080 GPU) with minimal computational overheads, providing a practical solution for industrial quality control in resource-constrained environments. Full article

Aiming at the problem of easily missed and misdetected parking spaces and obstacles in the automatic parking perception task under low-illumination conditions, this paper proposes a low-illumination parking space and obstacle detection algorithm based on image adaptive enhancement. The algorithm comprises an image adaptive enhancement module, which predicts adaptive parameters using CNN and integrates the low-light image enhancement via illumination map estimation and contrast-limited adaptive histogram equalization algorithms for image processing. The parking space and obstacle detection module adopts parking space corner detection based on image gradient matching, as well as obstacle detection utilizing yolov5s, whose feature pyramid network structure is optimized. The two modules are cascaded to optimize the prediction parameters of the image adaptive enhancement module, comprehensively considering the similarity loss of parking space corner matching and the obstacle detection loss. Experiments show that the algorithm makes the image pixel value distribution more balanced in low-light scenarios, the accuracy of parking space recognition reaches 95.46%, and the mean average precision of obstacle detection reaches 90.4%, which is better than the baseline algorithms, and is of great significance for the development of automatic parking sensing technology. Full article

To address the lack of robustness against illumination and blurring variations in aerial images of transmission towers, an improved image matching algorithm for aerial images is proposed. The proposed algorithm consists of two main components: an enhanced AKAZE algorithm and an improved three-stage feature matching strategy, which are used for feature point detection and feature matching, respectively. First, the improved AKAZE enhances image contrast using Contrast-Limited Adaptive Histogram Equalization (CLAHE), which highlights target features and improves robustness against environmental interference. Subsequently, the original AKAZE algorithm is employed to detect feature points and construct binary descriptors. Building upon this, an improved three-stage feature matching strategy is proposed to estimate the geometric transformation between image pairs. Specifically, the strategy begins with initial feature matching using the nearest neighbor ratio (NNR) method, followed by outlier rejection via the Grid-based Motion Statistics (GMS) algorithm. Finally, an improved Random Sample Consensus (RANSAC) algorithm computes the transformation matrix, further enhancing matching efficiency. Experimental results demonstrate that the proposed method exceeds the original AKAZE algorithm’s matching accuracy by 4∼15% on different image sets while achieving faster matching speeds. Under real-world conditions with UAV-captured aerial images of transmission towers, the proposed algorithm achieves over 95% matching accuracy, which is higher than other algorithms. Our proposed algorithm enables fast and accurate matching of transmission tower aerial images. Full article

Prior research has shown that for specific periods, vegetation indices from PlanetScope and Sentinel-2 (used as a reference) must be aligned to benefit from the experience of Sentinel-2 and utilize techniques such as data fusion. Even during the worst-case scenario, it is possible through histogram matching to calibrate PlanetScope indices to achieve the same values as Sentinel-2 (useful also for proxy). Based on these findings, the authors examined the effectiveness of linear regression in aligning individual bands prior to computing indices to determine if the bands are shifted differently. The research was conducted on five important bands: Red, Green, Blue, NIR, and RedEdge. These bands allow for the computation of well-known vegetation indices like NDVI and NDRE, and soil indices like Iron Oxide Ratio and Coloration Index. Previous research showed that linear regression is not sufficient by itself to align indices in the worst-case scenario. However, this paper demonstrates its efficiency in achieving accurate band alignment. This finding highlights the importance of considering specific scaling requirements for bands obtained from different satellite sensors, such as PlanetScope and Sentinel-2. Contemporary images acquired by the two sensors during May and July demonstrated different behaviors in their bands; however, linear regression can align the datasets even during the problematic month of May. Full article