Search Results (6,132)

The precise positioning of anchoring-hole centers on the steel belts used for anchor support in coal mines is essential for improving the automation and efficiency of roadway support. To address the issues of poor positioning accuracy and the low support efficiency caused by the manual determination of anchoring-hole-center positions, this paper proposes a monocular-vision-based method for locating anchoring-hole centers. Firstly, a laser pointer and an industrial camera are used to build an anchoring-hole positioning device, and its visual positioning model is constructed to achieve the automatic and precise localization of the anchoring-hole center. Secondly, to overcome the difficulty of obtaining high-precision spot centers using edge and grayscale information-based spot extraction methods, a spot center extraction method based on two-dimensional arctangent function fitting is proposed, achieving high precision and the stable acquisition of spot pixel coordinates. The experimental results show that the average measurement errors of the anchoring-hole centers in the camera’s coordinate system along the X-axis, Y-axis, and Z-axis are 3.36 mm, 3.30 mm, and 5.75 mm, respectively, with maximum errors of 4.23 mm, 4.39 mm, and 6.63 mm. The average measurement errors of the steel belt’s pitch, yaw, and roll angles in the camera’s coordinate system are 0.16°, 0.16°, and 0.08°, respectively, with maximum errors of 0.21°, 0.27°, and 0.13°. The proposed method can achieve the precise localization of anchoring holes, improve the efficiency of roadway support, and provide new insights for the automation and intelligentization of roadway anchor support. Full article

Targeting the dynamic image-motion problem of aerial cameras in the process of swing imaging, the image-motion compensation technology of aerial cameras based on the multi-dimensional motion of the secondary mirror was adopted. The secondary mirror was used as the image-motion compensation element, and the comprehensive image-motion compensation of the aerial camera was realized through the multi-dimensional motion of the secondary mirror. However, in the process of compensating for the image motion, the secondary mirror would be eccentric and inclined, which would cause the secondary mirror to be off-axis and affect the image quality. Therefore, a misalignment optical system model was established to study the relationship between the deviation vector and the misalignment of the secondary mirror, and the influence of the secondary mirror’s motion on the distribution of the aberration was analyzed. In order to verify the image-motion compensation ability of the multi-dimensional motion of the secondary mirror, an experimental platform was built to conduct a laboratory imaging experiment and flight experiment on the aerial camera. The experimental results showed that the dynamic resolution of the aerial camera using the image-motion compensation technology could reach 74 lp/mm, and the image-motion compensation accuracy was better than 0.5 pixels, which met the design expectation. In conclusion, the image-motion compensation technology is expected to be applied to various high-precision optical imaging as well as optical detection systems. Full article

High Spectral Spatial Frequency Domain Imaging (HSFDI) combines high spectral imaging and spatial frequency domain imaging techniques, offering advantages such as wide spectral range, non-contact, and differentiated imaging depth, making it well-suited for measuring the optical properties of agricultural products. The diffuse reflectance spectra of the samples at spatial frequencies of 0⁻¹  (R_d0) and 0.2⁻¹  (R_d0) were obtained using the three-phase demodulation algorithm. The pixel-by-pixel inversion was performed to obtain the absorption coefficient (μa) spectra and the reduced scattering coefficient (μ′s) spectra of the pears. For predicting the SSC and firmness of the pears, these optical properties and their specific combinations were used as inputs for partial least squares regression (PLSR) modeling by combining them with the wavelength selection algorithm of competitive adaptive reweighting sampling (CARS). The results showed that  had a stronger correlation with SSC, whereas  exhibited a stronger correlation with firmness. Taking the plane diffuse reflectance  as the comparison object, the prediction results of SSC based on both  and the combination of diffuse reflectance at two spatial frequencies ( ) were superior (the best  of 0.90 and  of 0.41%). Similarly, in the prediction of firmness, the results of μ′s, μa × μ's and R_d1 were better than that of R_d0 (the best R_p2 of 0.80 and RMSE_p of 3.25%). The findings of this research indicate that the optical properties represented by HSFDI technology and their combinations can accurately predict the internal quality of pears, providing a novel technical approach for the non-destructive internal quality evaluation of agricultural products. Full article

Gastric cancer has become a serious worldwide health concern, emphasizing the crucial importance of early diagnosis measures to improve patient outcomes. While traditional histological image analysis is regarded as the clinical gold standard, it is labour intensive and manual. In recognition of this problem, there has been a rise in interest in the use of computer-aided diagnostic tools to help pathologists with their diagnostic efforts. In particular, deep learning (DL) has emerged as a promising solution in this sector. However, current DL models are still restricted in their ability to extract extensive visual characteristics for correct categorization. To address this limitation, this study proposes the use of ensemble models, which incorporate the capabilities of several deep-learning architectures and use aggregate knowledge of many models to improve classification performance, allowing for more accurate and efficient gastric cancer detection. To determine how well these proposed models performed, this study compared them with other works, all of which were based on the Gastric Histopathology Sub-Size Images Database, a publicly available dataset for gastric cancer. This research demonstrates that the ensemble models achieved a high detection accuracy across all sub-databases, with an average accuracy exceeding 99%. Specifically, ResNet50, VGGNet, and ResNet34 performed better than EfficientNet and VitNet. For the 80 × 80-pixel sub-database, ResNet34 exhibited an accuracy of approximately 93%, VGGNet achieved 94%, and the ensemble model excelled with 99%. In the 120 × 120-pixel sub-database, the ensemble model showed 99% accuracy, VGGNet 97%, and ResNet50 approximately 97%. For the 160 × 160-pixel sub-database, the ensemble model again achieved 99% accuracy, VGGNet 98%, ResNet50 98%, and EfficientNet 92%, highlighting the ensemble model’s superior performance across all resolutions. Overall, the ensemble model consistently provided an accuracy of 99% across the three sub-pixel categories. These findings show that ensemble models may successfully detect critical characteristics from smaller patches and achieve high performance. The findings will help pathologists diagnose gastric cancer using histopathological images, leading to earlier identification and higher patient survival rates. Full article

Amidst the escalating threat of global warming, which manifests in more frequent forest fires, the prompt and accurate detection of forest fires has ascended to paramount importance. The current surveillance algorithms employed for forest fire monitoring—including, but not limited to, fixed threshold algorithms, multi-channel threshold algorithms, and contextual algorithms—rely primarily upon the degree of deviation between the pixel temperature and the background temperature to discern pyric events. Notwithstanding, these algorithms typically fail to account for the spatial heterogeneity of the background temperature, precipitating the consequential oversight of low-temperature fire point pixels, thus impeding the expedited detection of fires in their initial stages. For the amelioration of this deficiency, the present study introduces a spatial feature-based (STF) method for forest fire detection, leveraging Himawari-8/9 imagery as the main data source, complemented by the Shuttle Radar Topography Mission (SRTM) DEM data inputs. Our proposed modality reconstructs the surface temperature information via selecting the optimally designated machine learning model, subsequently identifying the fire point through utilizing the difference between the reconstructed surface temperatures and empirical observations, in tandem with the spatial contextual algorithm. The results confirm that the random forest model demonstrates superior efficacy in the reconstruction of the surface temperature. Benchmarking the STF method against both the fire point datasets disseminated by the China Forest and Grassland Fire Prevention and Suppression Network (CFGFPN) and the Wild Land Fire (WLF) fire point product validation datasets from Himawari-8/9 yielded a zero rate of omission errors and a comprehensive evaluative index, predominantly surpassing 0.74. These findings show that the STF method proposed herein significantly augments the identification of lower-temperature fire point pixels, thereby amplifying the sensitivity of forest surveillance. Full article

This research study represents a polydexterous deep reinforcement learning-based pick-and-place framework for industrial clutter scenarios. In the proposed framework, the agent tends to learn the pick-and-place of regularly and irregularly shaped objects in clutter by using the sequential combination of prehensile and non-prehensile robotic manipulations involving different robotic grippers in a completely self-supervised manner. The problem was tackled as a reinforcement learning problem; after the Markov decision process (MDP) was designed, the off-policy model-free Q-learning algorithm was deployed using deep Q-networks as a Q-function approximator. Four distinct robotic manipulations, i.e., grasp from the prehensile manipulation category and inward slide, outward slide, and suction grip from the non-prehensile manipulation category were considered as actions. The Q-function comprised four fully convolutional networks (FCN) corresponding to each action based on memory-efficient DenseNet-121 variants outputting pixel-wise maps of action-values jointly trained via the pixel-wise parametrization technique. Rewards were awarded according to the status of the action performed, and backpropagation was conducted accordingly for the FCN generating the maximum Q-value. The results showed that the agent learned the sequential combination of the polydexterous prehensile and non-prehensile manipulations, where the non-prehensile manipulations increased the possibility of prehensile manipulations. We achieved promising results in comparison to the baselines, differently designed variants, and density-based testing clutter. Full article

Data and reports indicate an increasing frequency and intensity of natural disasters worldwide. Buildings play a crucial role in disaster responses and damage assessments, aiding in planning rescue efforts and evaluating losses. Despite advances in applying deep learning to building extraction, challenges remain in handling complex natural disaster scenes and reducing reliance on labeled datasets. Recent advances in satellite video are opening a new avenue for efficient and accurate building extraction research. By thoroughly mining the characteristics of disaster video data, this work provides a new semantic segmentation model for accurate and efficient building extraction based on a limited number of training data, which consists of two parts: the prediction module and the automatic correction module. The prediction module, based on a base encoder–decoder structure, initially extracts buildings using a limited amount of training data that are obtained instantly. Then, the automatic correction module takes the output of the prediction module as input, constructs a criterion for identifying pixels with erroneous semantic information, and uses optical flow values to extract the accurate corresponding semantic information on the corrected frame. The experimental results demonstrate that the proposed method outperforms other methods in accuracy and computational complexity in complicated natural disaster scenes. Full article

Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have made considerable advances in hyperspectral image (HSI) classification. However, most CNN-based methods learn features at a single-scale in HSI data, which may be insufficient for multi-scale feature extraction in complex data scenes. To learn the relations among samples in non-grid data, GCNs are employed and combined with CNNs to process HSIs. Nevertheless, most methods based on CNN-GCN may overlook the integration of pixel-wise spectral signatures. In this paper, we propose a pyramid cascaded convolutional neural network with graph convolution (PCCGC) for hyperspectral image classification. It mainly comprises CNN-based and GCN-based subnetworks. Specifically, in the CNN-based subnetwork, a pyramid residual cascaded module and a pyramid convolution cascaded module are employed to extract multiscale spectral and spatial features separately, which can enhance the robustness of the proposed model. Furthermore, an adaptive feature-weighted fusion strategy is utilized to adaptively fuse multiscale spectral and spatial features. In the GCN-based subnetwork, a band selection network (BSNet) is used to learn the spectral signatures in the HSI using nonlinear inter-band dependencies. Then, the spectral-enhanced GCN module is utilized to extract and enhance the important features in the spectral matrix. Subsequently, a mutual-cooperative attention mechanism is constructed to align the spectral signatures between BSNet-based matrix with the spectral-enhanced GCN-based matrix for spectral signature integration. Abundant experiments performed on four widely used real HSI datasets show that our model achieves higher classification accuracy than the fourteen other comparative methods, which shows the superior classification performance of PCCGC over the state-of-the-art methods. Full article

High-mountain water bodies represent critical components of their ecosystems, serving as vital freshwater reservoirs, environmental regulators, and sentinels of climate change. To understand the environmental dynamics of these regions, comprehensive analyses of lakes across spatial and temporal scales are necessary. While remote sensing offers a powerful tool for lake monitoring, applications in high-mountain terrain present unique challenges. The Ancash and Cuzco regions of the Peruvian Andes exemplify these challenges. These regions harbor numerous high-mountain lakes, which are crucial for fresh water supply and environmental regulation. This paper presents an exploratory examination of remote sensing techniques for lake monitoring in the Ancash and Cuzco regions of the Peruvian Andes. The study compares three deep learning models for lake segmentation: the well-established DeepWaterMapV2 and WatNet models and the adapted WaterSegDiff model, which is based on a combination of diffusion and transformation mechanisms specifically conditioned for lake segmentation. In addition, the Normalized Difference Water Index (NDWI) with Otsu thresholding is used for comparison purposes. To capture lakes across these regions, a new dataset was created with Landsat-8 multispectral imagery (bands 2–7) from 2013 to 2023. Quantitative and qualitative analyses were performed using metrics such as Mean Intersection over Union (MIoU), Pixel Accuracy (PA), and F1 Score. The results achieved indicate equivalent performance of DeepWaterMapV2 and WatNet encoder–decoder architectures, achieving adequate lake segmentation despite the challenging geographical and atmospheric conditions inherent in high-mountain environments. In the qualitative analysis, the behavior of the WaterSegDiff model was considered promising for the proposed application. Considering that WatNet is less computationally complex, with 3.4 million parameters, this architecture becomes the most pertinent to implement. Additionally, a detailed temporal analysis of Lake Singrenacocha in the Vilcanota Mountains was conducted, pointing out the more significant behavior of the WatNet model. Full article

The extraction of navigation lines is a crucial aspect in the field autopilot system for intelligent agricultural equipment. Given that soybean seedlings are small, and straw can be found in certain Northeast China soybean fields, accurately obtaining feature points and extracting navigation lines during the soybean seedling stage poses numerous challenges. To solve the above problems, this paper proposes a method of extracting navigation lines based on the average coordinate feature points of pixel points in the bean seedling belt according to the calculation of the average coordinate. In this study, the soybean seedling was chosen as the research subject, and the Hue, Saturation, Value (HSV) colour model was employed in conjunction with the maximum interclass variance (OTSU) method for RGB image segmentation. To extract soybean seedling bands, a novel approach of framing binarised image contours by drawing external rectangles and calculating average coordinates of white pixel points as feature points was proposed. The feature points were normalised, and then the improved adaptive DBSCAN clustering method was used to cluster the feature points. The least squares method was used to fit the centre line of the crops and the navigation line, and the results showed that the average distance deviation and the average angle deviation of the proposed algorithm were 7.38 and 0.32. The fitted navigation line achieved an accuracy of 96.77%, meeting the requirements for extracting navigation lines in intelligent agricultural machinery equipment for soybean inter-row cultivation. This provides a theoretical foundation for realising automatic driving of intelligent agricultural machinery in the field. Full article

This research presents a GIS-based framework used to detect urban heat islands and determine which urban settlement elements are most critical when heatwave risks exist. The proposed method uses the Iterative Self-Organizing Data Analysis (ISODATA) clustering algorithm applied to the satellite land surface temperature distribution recorded during heatwaves for the detection of urban heat islands. A pixel classification confidence level maximization approach, obtained by running a maximum likelihood classification algorithm, is performed to determine the optimal number of clusters. The areas labeled as hotspots constitute the detected urban heat islands (UHIs). This method was tested on an urban settlement set up by the municipality of Naples (Italy). Comparison tests were performed with other urban heat island detection methods such as standard deviation thresholding and Getis-Ord Gi* hotspot detection; indices measuring the density of buildings, the percentage of permeable open spaces, and vegetation cover are taken into consideration to evaluate the accuracy of the urban heat islands detected. These tests highlight that the proposed method provides the most accurate results. It could be an effective tool to support the decision maker in evaluating which urban areas are the most critical during heatwave scenarios. Full article

Traditional frame-based cameras, despite their effectiveness and usage in computer vision, exhibit limitations such as high latency, low dynamic range, high power consumption, and motion blur. For two decades, researchers have explored neuromorphic cameras, which operate differently from traditional frame-based types, mimicking biological vision systems for enhanced data acquisition and spatio-temporal resolution. Each pixel asynchronously captures intensity changes in the scene above certain user-defined thresholds, and streams of events are captured. However, the distinct characteristics of these sensors mean that traditional computer vision methods are not directly applicable, necessitating the investigation of new approaches before being applied in real applications. This work aims to fill existing gaps in the literature by providing a survey and a discussion centered on the different application domains, differentiating between computer vision problems and whether solutions are better suited for or have been applied to a specific field. Moreover, an extensive discussion highlights the major achievements and challenges, in addition to the unique characteristics, of each application field. Full article

The superpixel usually serves as a region-level feature in various image processing tasks, and is known for segmentation accuracy, spatial compactness and running efficiency. However, since these properties are intrinsically incompatible, there is still a compromise within the overall performance of existing superpixel algorithms. In this work, the property constraint in superpixels is relaxed by in-depth understanding of the image content, and a novel two-stage superpixel generation framework is proposed to produce content-aware superpixels. In the global processing stage, a diffusion-based online average clustering framework is introduced to efficiently aggregate image pixels into multiple superpixel candidates according to color and spatial information. During this process, a centroid relocation strategy is established to dynamically guide the region updating. According to the area feature in manifold space, several superpixel centroids are then split or merged to optimize the regional representation of image content. Subsequently, local updating is adopted on pixels in those superpixel regions to further improve the performance. As a result, the dynamic centroid relocating strategy offers online averaging clustering the property of content awareness through coarse-to-fine label updating. Extensive experiments verify that the produced superpixels achieve desirable and comprehensive performance on boundary adherence, visual satisfactory and time consumption. The quantitative results are on par with existing state-of-the-art algorithms in terms with several common property metrics. Full article

Recent advancements in satellite technology have significantly increased the availability of high-resolution imagery for Earth observation, enabling nearly all regions to be captured frequently throughout the year. These images have become a vast source of big data and hold immense potential for various applications, including environmental monitoring, urban planning, and disaster management. However, obtaining ground control points (GCPs) and performing geometric correction is a time-consuming and costly process, often limiting the efficient use of these images. To address this challenge, this study introduces a Rational Function Model (RFM)-based rigorous bundle adjustment method to enhance the relative geometric positioning accuracy of multiple KOMPSAT-3A images without the need for GCPs. The proposed method was tested using KOMPSAT-3A images. The results showed a significant improvement in geometric accuracy, with mean positional errors reduced from 30.02 pixels to 2.21 pixels. This enhancement ensured that the corrected images derived from the proposed method were reliable and accurate, making it highly valuable for various geospatial applications. Full article

Small UAV target detection and tracking based on cross-modality image fusion have gained widespread attention. Due to the limited feature information available from small UAVs in images, where they occupy a minimal number of pixels, the precision required for detection and tracking algorithms is particularly high in complex backgrounds. Image fusion techniques can enrich the detailed information for small UAVs, showing significant advantages under extreme lighting conditions. Image registration is a fundamental step preceding image fusion. It is essential to achieve accurate image alignment before proceeding with image fusion to prevent severe ghosting and artifacts. This paper specifically focused on the alignment of small UAV targets within infrared and visible light imagery. To address this issue, this paper proposed a cross-modality image registration network based on deep learning, which includes a structure preservation and style transformation network (SPSTN) and a multi-level cross-attention residual registration network (MCARN). Firstly, the SPSTN is employed for modality transformation, transferring the cross-modality task into a single-modality task to reduce the information discrepancy between modalities. Then, the MCARN is utilized for single-modality image registration, capable of deeply extracting and fusing features from pseudo infrared and visible images to achieve efficient registration. To validate the effectiveness of the proposed method, comprehensive experimental evaluations were conducted on the Anti-UAV dataset. The extensive evaluation results validate the superiority and universality of the cross-modality image registration framework proposed in this paper, which plays a crucial role in subsequent image fusion tasks for more effective target detection. Full article