Search Results (33)

This study proposes a vision-based framework to support AVs in maintaining stable lane-keeping by assessing the condition of lane markings. Unlike existing infrastructure standards focused on human visibility, this study addresses the need for criteria suited to sensor-based AV environments. Using real driving data from urban expressways in Seoul, a YOLOv5-based lane detection algorithm was developed and enhanced through multi-label annotation and data augmentation. The model achieved a mean average precision (mAP) of 97.4% and demonstrated strong generalization on external datasets such as KITTI and TuSimple. For lane condition assessment, a pixel occupancy–based method was applied, combined with Canny edge detection and morphological operations. A threshold of 80-pixel occupancy was used to classify lanes as intact or worn. The proposed framework reliably detected lane degradation under various road and lighting conditions. These results suggest that quantitative, image-based indicators can complement traditional standards and guide AV-oriented infrastructure policy. Limitations include a lack of adverse weather data and dataset-specific threshold sensitivity. Full article

Accurate illuminance measurements are critical in assessing lighting quality during post-occupancy evaluations, and traditional methods are labor-intensive and time-consuming. This pilot study demonstrates an alternative that combines high dynamic range (HDR) imaging with a low-cost proxy-Lambertian surface to transform image luminance into spatial illuminance. Seven readily available materials were screened for luminance uniformity; the specimen with minimal deviation from Lambertian behavior (≈2%) was adopted as the pseudo-Lambertian surface. Calibrated HDR images of a fluorescent-lit university classroom were acquired with a digital single-lens reflex (DSLR) camera and processed in Photosphere, after which pixel luminance was converted to illuminance via Lambertian approximation. Predicted illuminance values were benchmarked against spectral illuminance meter readings at 42 locations on horizontal work planes, vertical presentation surfaces, and the circulation floor. The average errors were 5.20% for desks and 6.40% for the whiteboard—well below the 10% acceptance threshold for design validation—while the projector-screen and floor measurements exhibited slightly higher discrepancies of 9.90% and 14.40%, respectively. The proposed workflow significantly reduces the cost, complexity, and duration of lighting assessments, presenting a promising tool for streamlined, accurate post-occupancy evaluations. Future work may focus on refining this approach for diverse lighting conditions and complex material interactions. Full article

In response to the challenges of the low accuracy and high misdetection and omission rate of disease detection on feeder roads, an improved Rural-YOLO (SAConv-C2f+C2PSA_CAA+MCSAttention+WIOU) disease detection algorithm is proposed in this paper, which is an enhanced target detection framework based on the YOLOv11 architecture, for the identification of common diseases in the complex feeder road environment. The proposed methodology introduces four key innovations: (1) Switchable Atrous Convolution (SAConv) is introduced into the backbone network to enhance multiscale disease feature extraction under occlusion conditions; (2) Multi-Channel and Spatial Attention (MCSAttention) is constructed in the feature fusion process, and the weight distribution of multiscale diseases is adjusted through adaptive weight redistribution. By adjusting the weight distribution, the model’s sensitivity to subtle disease features is improved. To enhance its ability to discriminate between different disease types, Cross Stage Partial with Parallel Spatial Attention and Channel Adaptive Aggregation (C2PSA_CAA) is constructed at the end of the backbone network. (3) To mitigate category imbalance issues, Weighted Intersection over Union loss (WIoU_loss) is introduced, which helps optimize the bounding box regression process in disease detection and improve the detection of relevant diseases. Based on experimental validation, Rural-YOLO demonstrated superior performance with minimal computational overhead. Only 0.7 M additional parameters is required, and an 8.4% improvement in recall and a 7.8% increase in mAP₅₀ were achieved compared to the initial models. The optimized architecture also reduced the model size by 21%. The test results showed that the proposed model achieved 3.28 M parameters with a computational complexity of 5.0 GFLOPs, meeting the requirements for lightweight deployment scenarios. Cross-validation on multi-scenario public datasets was carried out, and the model’s robustness across diverse road conditions. In the quantitative experiments, the center skeleton method and the maximum internal tangent circle method were used to calculate crack width, and the pixel occupancy ratio method was used to assess the area damage degree of potholes and other diseases. The measurements were converted to actual physical dimensions using a calibrated scale of 0.081:1. Full article

Accurate and efficient white-spot defects detection for the surface of galvanized strip steel is one of the most important guarantees for the quality of steel production. It is a fundamental but “hard” small target detection problem due to its small pixel occupation in low-contrast images. By fully exploiting the low-rank and sparse prior information of a surface defect image, a Schatten-p norm-based low-rank tensor decomposition (SLRTD) method is proposed to decompose the defect image into low-rank background, sparse defect, and random noise. Firstly, the original defect images are transformed into a new patch-based tensor mode through data reconstruction for mining valuable information of the defect image. Then, considering the over-shrinkage problem in the low-rank component estimation caused by a vanilla nuclear norm and a weighted nuclear norm, a nonlinear reweighting strategy based on a Schatten $p$-norm is incorporated to improve the decomposition performance. Finally, a solution framework is proposed via a well-designed alternating direction method of multipliers to obtain the white-spot defect target image by a simple segmenting algorithm. The white-spot defect dataset from a real-world galvanized strip steel production line is constructed, and the experimental results demonstrate that the proposed SLRTD method outperforms existing state-of-the-art methods qualitatively and quantitatively. Full article

UAV infrared sensor technology plays an irreplaceable role in various fields. High-altitude infrared images present significant challenges for feature extraction due to their uniform texture and color, fragile and variable edge information, numerous background interference factors, and low pixel occupancy of small targets such as humans, bicycles, and diverse vehicles. In this paper, we propose a Multi-scale Dual-Branch Dynamic Feature Aggregation Network (MDDFA-Net) specifically designed to address these challenges in UAV infrared image processing. Firstly, a multi-scale dual-branch structure is employed to extract multi-level and edge feature information, which is crucial for detecting small targets in complex backgrounds. Subsequently, features at three different scales are fed into an Adaptive Feature Fusion Module for feature attention-weighted fusion, effectively filtering out background interference. Finally, the Multi-Scale Feature Enhancement and Fusion Module integrates high-level and low-level features across three scales to eliminate redundant information and enhance target detection accuracy. We conducted comprehensive experiments using the HIT-UAV dataset, which is characterized by its diversity and complexity, particularly in capturing small targets in high-altitude infrared images. Our method outperforms various state-of-the-art (SOTA) models across multiple evaluation metrics and also demonstrates strong inference speed capabilities across different devices, thereby proving the advantages of this approach in UAV infrared sensor image processing, especially for multi-scale small target detection. Full article

Solar energy utilization in buildings can significantly contribute to energy savings and enhance on-site energy production. However, excessive solar gains may lead to overheating, thereby increasing cooling demands. Accurate calculation of sunlit and shaded areas is essential for optimizing solar technologies and improving the precision of building energy simulations. This paper provides a review of the solar shading calculation methods used in building performance simulation (BPS) tools, focusing on the progression from basic trigonometric models to advanced techniques such as projection and clipping (PgC) and pixel counting (PxC). These advancements have improved the accuracy and efficiency of solar shading simulations, enhancing energy performance and occupant comfort. As building designs evolve and adaptive shading systems become more common, challenges remain in ensuring that these methods can handle complex geometries and dynamic solar exposure. The PxC method, leveraging modern GPUs and parallel computing, offers a solution by providing real-time high-resolution simulations, even for irregular, non-convex surfaces. This ability to handle continuous updates positions PxC as a key tool for next-generation building energy simulations, ensuring that shading systems can adjust to changing solar conditions. Future research could focus on integrating appropriate modeling approaches with AI technologies to enhance accuracy, reliability, and computational efficiency. Full article

As augmented reality (AR) technologies become increasingly integrated into everyday life, privacy-maintenance concerns about their capacity to capture and process sensitive visual data also increase. Visual data sanitization and obfuscation may effectively increase the privacy protection level. This study examines user perceptions of privacy protection strategies within AR environments. We developed and disseminated a questionnaire to assess users’ preferences, experiences, and concerns related to visual obfuscation techniques, namely masking, pixelation, and blurring. We collected and analyzed the responses using both qualitative and quantitative methodologies. The results indicate that user perceptions varied based on the AR context and individual preferences. Participants identified blurring as a versatile option that provides the best aesthetic appeal. Users recognized masking as the most secure method but less visually appealing. This study also revealed that demographic factors, such as age, education, and occupation, influenced privacy concerns and the acceptance of obfuscation methods. These findings enhance the understanding of user preferences and the effectiveness of obfuscation techniques in AR. These insights can guide the development of privacy-preserving AR applications tailored to accommodate diverse user needs. Full article

The land use land cover (LULC) map is extensively employed for different purposes. Machine learning (ML) algorithms applied in remote sensing (RS) data have been proven effective in image classification, object detection, and semantic segmentation. Previous studies have shown that random forest (RF) and support vector machine (SVM) consistently achieve high accuracy for land classification. Considering the important role of Portugal’s Serra da Estrela Natural Park (PNSE) in biodiversity and nature conversation at an international scale, the availability of timely data on the PNSE for emergency evaluation and periodic assessment is crucial. In this study, the application of RF and SVM classifiers, and object-based (OBIA) and pixel-based (PBIA) approaches, with Sentinel-2A imagery was evaluated using Google Earth Engine (GEE) platform for the land cover classification of a burnt area in the PNSE. This aimed to detect the land cover change and closely observe the burnt area and vegetation recovery after the 2022 wildfire. The combination of RF and OBIA achieved the highest accuracy in all evaluation metrics. At the same time, a comparison with the Normalized Difference Vegetation Index (NDVI) map and Conjunctural Land Occupation Map (COSc) of 2023 year indicated that the SVM and PBIA map resembled the maps better. Full article

The Rapid expansion of the Lanzhou–Xining (Lanxi) urban cluster in China during recent decades poses a threat to the fragile arid environment. Quantitatively assessing the impact of urban expansion on vegetation in the Lanxi urban cluster has profound implications for future sustainable urban planning. This study investigated the urban expansion dynamics of the Lanxi urban cluster and its impacts on regional vegetation between 2001 and 2021 based on time series land cover data and auxiliary remote sensing data, such as digital elevation model (DEM) data, nighttime light data, and administrative boundary data. Thereinto, urban expansion dynamics were evaluated using the annual China Land Cover Dataset (CLCD, 2001–2021). Urban expansion impacts on regional vegetation were assessed via the Vegetation Disturbance Index (VDI), an index capable of quantitatively assessing the positive and negative impacts of urban expansion at the pixel level, which can be obtained by overlaying the Enhanced Vegetation Index (EVI) and rainfall data. The major findings indicate that: (1) Over the past two decades, the Lanxi region has experienced rapid urban expansion, with the built-up area expanding from 183.50 km² to 294.30 km², which is an average annual expansion rate of 2.39%. Notably, Lanzhou, Baiyin, and Xining dominated the expansion. (2) Urban expansion negatively affected approximately 53.50 km² of vegetation, while about 39.56 km² saw positive impacts. The negative effects were mainly due to the loss of cropland and grassland. Therefore, cities in drylands should balance urban development and vegetation conservation by strictly controlling cropland and grassland occupancy and promoting intelligent urban growth. Full article

Assessing the quality of urban street space can provide suggestions for urban planning and construction management. Big data collection and machine learning provide more efficient evaluation methods than traditional survey methods. This study intended to quantify the urban street spatial quality based on street view image segmentation. A case study was conducted in the Second Ring Road of Changsha City, China. Firstly, the road network information was obtained through OpenStreetMap, and the longitude and latitude of the observation points were obtained using ArcGIS 10.2 software. Then, corresponding street view images of the observation points were obtained from Baidu Maps, and a semantic segmentation software was used to obtain the pixel occupancy ratio of 150 land cover categories in each image. This study selected six evaluation indicators to assess the street space quality, including the sky visibility index, green visual index, interface enclosure index, public–facility convenience index, traffic recognition, and motorization degree. Through statistical analysis of objects related to each evaluation indicator, scores of each evaluation indicator for observation points were obtained. The scores of each indicator are mapped onto the map in ArcGIS for data visualization and analysis. The final value of street space quality was obtained by weighing each indicator score according to the selected weight, achieving qualitative research on street space quality. The results showed that the street space quality in the downtown area of Changsha is relatively high. Still, the level of green visual index, interface enclosure, public–facility convenience index, and motorization degree is relatively low. In the commercial area east of the river, improvements are needed in pedestrian perception. In other areas, enhancements are required in community public facilities and traffic signage. Full article

In this work, we introduce the design of a 16-channel in-pixel neural analog front end that employs a current-based summing approach to establish a common-mode feedback loop. The primary aim of this novel structure is to enhance both the system common-mode rejection ratio (SCMRR) and the common-mode interference (CMI) range. Compared to more conventional designs, the proposed front end utilizes DC-coupled inverter-based main amplifiers, which significantly reduce the occupied on-chip area. Additionally, the current-based implementation of the CMFB loop obviates the need for voltage buffers, replacing them with simple common-gate transistors, which, in turn, decreases both area occupancy and power consumption. The proposed architecture is further examined from an analytical standpoint, providing a comprehensive evaluation through design equations of its performance in terms of gain, common-mode rejection, and noise power. A 50 $\mathsf{\mu }$m × 65 $\mathsf{\mu }$m compact layout of the pixel amplifiers that make up the recording channels of the front end was designed using a 180 nm CMOS process. Simulations conducted in Cadence Virtuoso reveal an SCMRR of 80.5 dB and a PSRR of 72.58 dB, with a differential gain of 44 dB and a bandwidth that fully encompasses the frequency range of the bio-signals that can be theoretically captured by the neural probe. The noise integrated in the range between 1 Hz and 7.5 kHz results in an input-referred noise (IRN) of 4.04 $\mathsf{\mu }{V}_{rms}$. Power consumption is also tested, with a measured value of 3.77 $\mathsf{\mu }$W per channel, corresponding to an overall consumption of about 60 $\mathsf{\mu }$W. To test its robustness with respect to PVT and mismatch variations, the front end is evaluated through extensive parametric simulations and Monte Carlo simulations, revealing favorable results. Full article

The automatic monitoring and detection of maritime targets hold paramount significance in safeguarding national sovereignty, ensuring maritime rights, and advancing national development. Among the principal means of maritime surveillance, infrared (IR) small ship detection technology stands out. However, due to their minimal pixel occupancy and lack of discernible color and texture information, IR small ships have persistently posed a formidable challenge in the realm of target detection. Additionally, the intricate maritime backgrounds often exacerbate the issue by inducing high false alarm rates. In an effort to surmount these challenges, this paper proposes a flexible convolutional network (FCNet), integrating dilated convolutions and deformable convolutions to achieve flexible variations in convolutional receptive fields. Firstly, a feature enhancement module (FEM) is devised to enhance input features by fusing standard convolutions with dilated convolutions, thereby obtaining precise feature representations. Subsequently, a context fusion module (CFM) is designed to integrate contextual information during the downsampling process, mitigating information loss. Furthermore, a semantic fusion module (SFM) is crafted to fuse shallow features with deep semantic information during the upsampling process. Additionally, squeeze-and-excitation (SE) blocks are incorporated during upsampling to bolster channel information. Experimental evaluations conducted on two datasets demonstrate that FCNet outperforms other algorithms in the detection of IR small ships on maritime surfaces. Moreover, to propel research in deep learning-based IR small ship detection on maritime surfaces, we introduce the IR small ship dataset (Maritime-SIRST). Full article

Semantic labeling of high-resolution remote sensing images (HRRSIs) holds a significant position in the remote sensing domain. Although numerous deep-learning-based segmentation models have enhanced segmentation precision, their complexity leads to a significant increase in parameters and computational requirements. While ensuring segmentation accuracy, it is also crucial to improve segmentation speed. To address this issue, we propose an efficient asymmetric deep learning network for HRRSIs, referred to as EAD-Net. First, EAD-Net employs ResNet50 as the backbone without pooling, instead of the RepVGG block, to extract rich semantic features while reducing model complexity. Second, a dynamic routing module is proposed in EAD-Net to adjust routing based on the pixel occupancy of small-scale objects. Concurrently, a channel attention mechanism is used to preserve their features even with minimal occupancy. Third, a novel asymmetric decoder is introduced, which uses convolutional operations while discarding skip connections. This not only effectively reduces redundant features but also allows using low-level image features to enhance EAD-Net’s performance. Extensive experimental results on the ISPRS 2D semantic labeling challenge benchmark demonstrate that EAD-Net achieves state-of-the-art (SOTA) accuracy performance while reducing model complexity and inference time, while the mean Intersection over Union (mIoU) score reaching 87.38% and 93.10% in the Vaihingen and Potsdam datasets, respectively. Full article

In the realm of maritime target detection, infrared imaging technology has become the predominant modality. Detecting infrared small ships on the sea surface is crucial for national defense and maritime security. However, the challenge of detecting infrared small targets persists, especially in the complex scenes of the sea surface. As a response to this challenge, we propose MAPC-Net, an enhanced algorithm based on an existing network. Unlike conventional approaches, our method focuses on addressing the intricacies of sea surface scenes and the sparse pixel occupancy of small ships. MAPC-Net incorporates a scale attention mechanism into the original network’s multi-scale feature pyramid, enabling the learning of more effective scale feature maps. Additionally, a channel attention mechanism is introduced during the upsampling process to capture relationships between different channels, resulting in superior feature representations. Notably, our proposed Maritime-SIRST dataset, meticulously annotated for infrared small ship detection, is introduced to stimulate advancements in this research domain. Experimental evaluations on the Maritime-SIRST dataset demonstrate the superiority of our algorithm over existing methods. Compared to the original network, our approach achieves a 6.14% increase in mIOU and a 4.41% increase in F1, while maintaining nearly unchanged runtime. Full article

Layered nickelate oxides containing Ni¹⁺/Ni²⁺ are isoelectronic to Cu²⁺/Cu³⁺ compounds and of present interest with respect to recent findings of superconductivity in a series of different compositions. It is thereby questionable why superconductivity is still rare to find in nickelates, compared to the much larger amount of superconducting cuprates. Anisotropic d_z² vs. d_x²−y² orbital occupation as well as interface-induced superconductivity are two of the main advanced arguments. We are here interested in investigating the feasibility of synthesizing layered nickelate-type oxides, where the Ni¹⁺/Ni²⁺ ratio can be tuned by oxygen and/or cation doping. Our strategy is to synthesize Sr-doped n = 1 Ruddlesden–Popper type Nd_2−xSr_xNiO_4+δ single crystals, which are then reduced by H₂ gas, forming Nd_2−xSr_xNiO_4−δ via a topotactic oxygen release at moderate temperatures. We report here on structural studies carried out on single crystals by laboratory and synchrotron diffraction using pixel detectors. We evidence the general possibility to obtain reduced single crystals despite their increased orthorhombicity. This must be regarded as a milestone to obtain single crystalline nickelate oxides, which further on contain charge-ordering of Ni¹⁺/Ni²⁺, opening the access towards anisotropic properties. Full article