Map Information Research Articles

Quantifying indoor navigation map information considering the dynamic map elements for scale adaptation

Quantifying indoor navigation map information considering the dynamic map elements for scale adaptation

MFFOD: Multidomain Feature Fusion Object Detector for Infrared Images

Abstract Infrared imagery surpasses the limitations of visible light images and finds widespread applications in fields such as military reconnaissance and security surveillance. Recent studies on infrared target detection aim to preserve local features and global representations to the greatest extent. However, compared to visible light images, infrared images exhibit inherent challenges such as insufficient texture information and coarse boundaries, which introduce new difficulties to this research. To address these issues, this paper introduces additional information cues from the perspective of enriching feature map information. Specifically, we propose a multidomain feature fusion object detector (MFFOD), whose backbone feature extraction network consists of a convolutional branch and a fast Fourier transform (FFT) branch. This hybrid domain representation enables the extraction of both domain-specific information and global high-frequency and low-frequency information with minimal computational overhead. Furthermore, in the intermediate layers of the network, we have carefully designed a feature injection module that enables comprehensive interaction between channel features and spatial features within a single feature map. Experimental results demonstrate that MFFOD achieves average detection accuracies of 88.97%, 90.32%, and 99.25% on three significant infrared scene datasets, outperforming existing target detection methods. We hope that this general detection algorithm will provide a robust reference for future infrared target detection research.

Enhanced oracle bone corrosion detection using attention-guided YOLO with ghost convolution

Oracle bone inscriptions (OBIs), as the important records of early Chinese characters, possess profound cultural and historical significance. However, These fragments are susceptible to further damage due to corrosion. Consequently, the identification and localization of corroded regions on these fragments to prevent further deterioration has emerged as a critical task. Current object detection algorithms exhibit limitations in identifying corroded regions on oracle bone fragments, which is manifested by suboptimal detection accuracy, F1 scores, and average precision (AP) values. This deficiency hinders their capability to effectively manage the complexity and diversity of corrosion patterns present on oracle bone fragments. To tackle this challenge, this study incorporates advanced attention mechanisms, including Squeeze-and-Excitation Networks (SE), Coordinate attention, and Convolutional Block Attention Module (CBAM), into the YOLOv5 detection architecture. Additionally, we introduce Ghost convolution into the backbone network to effectively retain critical feature map information while optimizing computational efficiency. Our experimental results indicate that the integration of CBAM attention and Ghost convolution within the YOLOv5 backbone markedly improves the detection accuracy of corroded regions on oracle bone fragments. Specifically, compared to the baseline YOLOv5 model, the proposed models incorporating SE, CBAM, and Ghost convolution obtain the improvements of 2.2%, 6.3%, and 8.5% in AP, respectively. This improvement in detection performance not only facilitates the identification of corroded areas but also contributes to the preservation of oracle bone heritage and the continuity of cultural knowledge.

Where will the next flank eruption at Etna occur? An updated spatial probabilistic assessment

Abstract. The assessment of the spatial probability of future vent opening is one of the key factors in quantifying volcanic hazard, especially for active volcanoes where eruptions can occur at different locations and altitudes over distributed areas. Mount Etna (Italy), one of the most active volcanoes in the world, exhibits such variability, and its flank eruptions can harm people, properties and services over the volcano's slopes. In this paper, we quantify the spatial probability of future vent opening for Etna's flank eruptions, adopting a kernel analysis and testing different functions (exponential, Cauchy, uniform and Gaussian). Starting from the assumption that the location of past fissures is indicative of where future events will occur, we consider the flank eruptions of the last 4000 years, thus accounting for a much longer and complete record than in previous studies. The large dataset of eruptive fissures enables splitting the data into training and testing subsets. This allows selecting the best kernel model, testing the completeness of the fissure dataset and investigating a possible migration through time in fissure location. The results show that neither under-recording nor possible migration over time significantly affects the informative value of previous flank fissures in forecasting the location of future ones. The resulting map highlights that the most likely opening area follows a northeast-to-south trend, corresponding to the location of the most active rifts. It also shows that the southern flank of the volcano, which is the most urbanized one, sits downhill of the largest cumulated probability area for flank eruption. We also run sensitivity analyses to test the effect of (i) restricting the data to the most recent 400 years and (ii) including the information on the stress induced on the mapped fissures by sources of deformation proposed in the literature for recent eruptions of Etna. The sensitivity analyses confirm the main features of the proposed map and add information on the epistemic uncertainty attached to it.

Attributes Classification for Elaborating the Information of Digital and Imaging Mapping

The rapid development of information has made it possible for everyone to obtain the latest information, complete and accurate, in real time, anytime, anywhere, all over the world. Any information is fine catching up by updated with the latest news and even detailed information on local conditions. With the same analogy, detailed information regarding land utilization, land containing, landscape provision, earth surface contour, etc., are required to inform and elaborate any appropriate decision needed. The Geographic information systems (GIS) is a recent technology commonly used by research in earth science to facilitate many layered detail information by one way to get up-to-date, detailed information. In this research, the GIS utilizes several types of imaging data such remote sensing images and digitize images. As the name suggests, this system captures detailed geographic information about a location or region. By inputting classified images of remote sensing results into a GIS database at regular intervals (adjusted as necessary, such as every year, every two years, every three years, etc.), the number of information sources that can be obtained increases. There are several reasons for that. First, remote sensing images are images that cover the entire surface of the Earth. Next, remote sensing images are images that contain information about the state of the earth's surface. Third, a variety of information can be obtained by performing appropriate image processing. Furthermore, this research could be elaborated by implementing an artificial intelligent algorithm to create a robust outcome.

UGVs’ Navigation Supported by Multi-UAVs in a ROS Environment

It is challenging for unmanned ground vehicles (UGVs) to navigate in an unknown environment without equipping them with sensors, such as LiDAR, cameras, etc. As a result, it is necessary to employ an unmanned aerial vehicle (UAV) to provide the UGVs with map information, obstacle information and relative position estimations. The UGVs receive the messages from the UAV and then automatically plan a global route. When approaching obstacles, UGVs release collision position messages to the UAV. This UAV calculates the optimal path point based on the collision position and the time to collision of the UGVs. However, the UAV’s relative position estimation equipment has a limited range, such that it cannot provide all UGVs with the information in time. This means that UGVs receive information late or even lose communication with the UAV. To address the above issues, this paper advocates for the use of multiple UAVs and the creation of different communication strategies. A variety of tests are conducted in a simulated environment built in ROS to pair each UAV with different numbers of UGVs and explore their initial positions to find the most suitable configuration.

A novel model for mapping soil organic matter: Integrating temporal and spatial characteristics

Mapping the spatial distribution of soil organic matter (SOM) content is crucial for land management decisions, yet its accurate mapping faces challenges due to complex soil-environment relationships and temporal feature capture limitations in machine learning models. This study focuses on the typical black soil region in Northeast China, specifically using Youyi Farm as the main research area and Heshan Farm as the transfer research area. A novel approach is proposed that combines the CNN-LSTM model with a Cosine Annealing Warm Restarts learning rate (CNN-LSTM-CAWR) to enhance the accuracy of SOM mapping. In this model, the Convolutional Neural Network (CNN) extracts spatial context features from static variables (e.g., climate and terrain variables), while the Long Short-Term Memory (LSTM) network captures temporal features from dynamic variables (e.g., Sentinel-2 time series from April to October). The incorporation of the CAWR learning rate helps alleviate overfitting issues. Comparing the CNN-LSTM model, CNN model, and traditional RF model, the results show that the CNN-LSTM-CAWR model achieves the highest accuracy within research Area 1 (R2 = 0.64, RMSE = 0.54 %) and maintains strong performance in the transfer research area (R2 = 0.60, RMSE = 0.57 %). CNN-LSTM-CAWR demonstrates faster convergence, thereby improving mapping precision and effectively utilizing temporal information from features to enhance overall model performance. This study underscores the significant potential of the hybrid CNN-LSTM with CAWR model, highlighting the valuable information for SOM mapping contained within Sentinel-2 time series data.

Direct Determination of Metallic Contamination on and in Wafers Using Laser Ablation Inductively Coupled Plasma Mass Spectrometry

A new analytical technique has been developed for determination of metallic impurities on and in wafers using LA-GED-MSAG-ICP-MS. Up to 300 mm wafer can be analyzed directly without using a small enclosed chamber. Particles generated by a femto-second laser ablation were aspirated together with particle free clean air by an ejector and introduced to the ICP-MS (Inductively Coupled Plasma Mass Spectrometry) via GED (Gas Exchange Device). Particles in air could not be introduced to the plasma of ICP-MS directly because the Ar plasma could not be sustained when air was introduced. The GED exchanged air with Ar efficiently (> 99.98%), the particles came out from GED in Ar gas stream that could be introduced to the plasma of ICP-MS. For quantitation of LA-ICP-MS, MSAG (Metal Standard Aerosol Generation) was used. MSAG could introduce nearly a 100% of aqueous multi-element standard solution to the plasma of ICP-MS, which allowed precise quantitation using the method of standard addition while ablating wafer samples. The technique was used for the following applications:- Metallic contamination mapping of a wafer. Multiple spots (1 cm2/spot) of 300 mm wafer were laser ablated and analyzed by ICP-MS as shown in Fig.1. E6 - E7 atoms/cm2 of detection limit was obtained. The conventional VPD-ICP-MS technique uses a 1 mL scan solution to collect metallic impurities on an entire wafer surface of 300 mm wafer, and the collected solution is analyzed by ICP-MS giving E6 - E7 atoms/cm2 detection limit. It was impossible to get the contamination mapping information at such a low concentration. TRXRF has also been commonly used for the same purpose, but the detection limit is E10 - 12 atoms/cm2.- Particle measurement on a wafer. A spike recovery test of 20 and 50 nm Au nano-particle standard on Si wafer was performed, and individual nano-particle signals were detected by ICP-MS. The number of Au particle recovery was more than 85%. 200 nm SiO2 particles on Si wafer were also detected after the optimization of laser parameters.- Metallic contamination mapping on a wafer bevel. Several metallic contaminants were detected at certain spots of bevel, and E4 atoms of spot contamination could be detected.- Depth profile analysis of an ion implanted wafer. The laser ablation was performed on the same area repeatedly and the profile of As ion implanted wafer could be carried out in atmospheric pressure. This technique was also used for analysis of multi-layer film wafers.This paper explains how the new technique overcame the issues of the conventional LA-ICP-MS technique; why an entire wafer could not be analyzed and why an accurate quantitative analysis was impossible. Figure 1

3-D Mapping Approach for High-Efficiency and High-Precision Latent Flaw Detection

In semiconductor manufacturing, fine-polishing process plays important role in achieving high-performance products. In recent years, driven by the escalating demand for process precision, the formation of latent flaws formation, which are defects that cannot be detected by general inspection, during fine-polishing process has emerged as a critical concern. Latent flaws cannot be observed with optical or electron microscopes and require destructive inspection such as etching for reliable detection. Previously, we have reported successful detection of latent flaws by applying stress [1] or heat [2,3] to the substrate.In this presentation, we present the development of a three-dimensional(3D) mapping approach for detecting latent flaws in glass substrates. Initially, defects were induced in a glass substrate through laser processing (532 nm). Subsequently, by observing the light scattering of the defects while adjusting the focus of the microscope, we analyzed not only the two-dimensional (2D) distribution of latent flaws but also their 3D distribution (Figure), with the addition of depth information. Understanding the depth of latent flaws is crucial, as it provides essential information for calculating the margin for shaving required for repolishing, which is necessary for removing the latent flaws and other defects. Furthermore, the 3D mapping information is anticipated to be valuable not only for optimizing polishing parameters but also for investigating any issues that may arise during the process.The data obtained from the described methods can be incorporated into a machine learning model to predict the depth of latent flaws from the image data. Our approach enables not only highly sensitive but also highly efficient inspection and is expected to make a significant contribution to the semiconductor manufacturing industry.[1] Yoshitaro Sakata et al. “Stress-induced light scattering method for the detection of latent flaws on fine polished glass substrates” REVIEW OF SCIENTIFIC INSTRUMENTS 85, 083303 (2014)[2] Yoshitaro Sakata et al. “Microscopic study of stress effects around micro-crack tips using a non-contact stress-induced light scattering method” AIP ADVANCES 6, 095315 (2016)[3] Yoshitaro Sakata et al. ” Development of a novel non-contact inspection technique to detect microcracks under the surface of a glass substrate by thermal stress-induced light scattering method” Optics & Laser Technology 90 80–83 (2017) Figure 1

Modeling inter-modal incongruous sentiment expressions for multi-modal sarcasm detection

Multi-modal sarcasm detection (MSD) presents a formidable and intricate endeavor. Despite strides made by extant models, two principal hurdles persist: Firstly, prevailing methodologies merely address superficial disparities between textual inputs and associated images, neglecting nuanced inter-modal combinations. Secondly, satirical instances frequently involve intricate emotional expressions, highlighting the imperative of leveraging emotional cues across modalities to discern satirical nuances. Accordingly, this research proposes the utilization of a deep graph convolutional network that integrates cross-modal mapping information to effectively identify significant incongruent sentiment expressions across various modalities for the purpose of multi-modal sarcasm detection. Specifically, we first design a cross-modal mapping network, which obtains the interaction information between these two modalities by mapping text feature vectors and image feature vectors two by two to compensate for the lack of multi-modal data in the fusion process. Additionally, we employ external knowledge of ANPS as a bridge to construct cross-correlation graphs through highly correlated satirical cues and their connection weights between image and text modalities. Afterward, the GCN architecture with retrieval-based attentional mechanisms will effectively capture satirical cues. The experiments conducted on two publicly available datasets demonstrate a significant enhancement in the performance of our method when compared to numerous contemporary models.

Dynamic Path Planning Scheme for OHT in AMHS Based on Map Information Double Deep Q-Network

Dynamic Path Planning Scheme for OHT in AMHS Based on Map Information Double Deep Q-Network

A small‐target traffic sign detection algorithm based on partial conv and atrous spatial pyramid

AbstractTraffic sign detection is essential to an intelligent driving assistance system. The deep learning‐based algorithm proposed in this paper aims to address the issue of low detection accuracy caused by the small size and high density of traffic signs in real‐world traffic scenarios. First, to improve the feature extraction module of the backbone network and to increase the model's ability to capture contextual information, partial convolution (PConv) is introduced. Second, to prevent information loss during the downsampling process, a cross‐stage atrous spatial pyramid (ASPPFCSPC) is constructed using atrous convolution. This method combines feature map information from various scales and expands the receptive field. Lastly, the small‐target detection precision is improved by incorporating an additional small‐target detection head, which uses high‐resolution feature maps for shallow features. The detection head is decoupled to extract the location and class information of the predicted target separately, thereby enhancing the generalization ability of the proposed model. Experiments have demonstrated the superiority of the proposed algorithm, as testing on the TT100K dataset resulted in a mAP@0.5 of 91.2% and a mAP@0.5:0.95 of 71.8% using the proposed algorithm.

Hindcasting the typhoon haiyan storm surge in coastal eastern leyte

This study introduces the 'Zero-Point Boundary' method to map the 2013 Typhoon Haiyan storm surge in coastal eastern Leyte. Utilising the 'Rivera Dispersive Wave Model' or RDM, we interpolated simulated storm surge and wave height data, subtracting them from a 5-m resolution digital terrain model raster provided by the National Mapping and Resource Information Authority (NAMRIA) to determine inundation limits and depths relative to the average Filipino male height (i.e., 165 cm). Validation against the 2013 joint survey conducted by the Japan Society of Civil Engineers (JSCE) and the Philippine Institute of Civil Engineers (PICE) showed an 81 % accuracy rate when identifying water limit locations in Tacloban City, suggesting potential for future forecasting. However, the absence of compound flooding consideration in the simulations may have influenced this rate. Overall, this study underscores the importance of accurate modelling and communication in hazard mapping for enhancing preparedness and mitigation efforts, emphasising a balanced approach to risk perception.

Model for analysis of actors in divergence or convergence of strategic health objectives.

Correlate methods to analyze and identify the effectiveness of the objectives in actors with maps of strategic power. It is a conceptual study, analytical and with deductive reasoning, of explanatory scope in correlation of convergent and divergent strategic objectives to health processes. Understanding the importance of analyzing and understanding the prospective in the decision-making of the actors that impact their strategic, tactical and operational deployment of hospital medical care with the proposals of models with alignment in the health system and comprehensive practicality and analytical architecture modeling of how the hierarchical levels of actors can be concentrated according to the objectives with indicators and committed goals. The prospective analysis of actors makes it easier to evaluate health leaders according to the effectiveness of their established objectives through the collection of information in matrices, MACTOR (Method, Actors, Objectives, Force Results) and mapping of health objectives. It is relevant in favor of ensuring strategic alignment in health institutions until reaching hospitals and giving continuity to the objectives and improving conflict management for the benefit of medical care.

Multi-stage magma emplacement in the western end of the Jinchuan Ni[sbnd]Cu sulfide deposit, NW China, and mineral exploration strategy based on exploration data

The western intrusion of the world-class Jinchuan NiCu sulfide deposit consists of fine-grained and coarse-grained binary lithofacies units. However, recent exploration has revealed two layers of net-textured sulfides in the fine-grained unit at the western end of the Jinchuan intrusion, adding complexity to the genesis of sulfide mineralization. We measured chalcophile elements and collected exploration data on Cu and Ni content to investigate their genesis and prospecting potential. The lower fine-grained subunits, comprising a layer of disseminated sulfides (DS-1) in the bottom and overlain by massive sulfide (MS) and olivine-sulfide cumulates (NTS-1), were overlain by the upper fine-grained subunits disseminated sulfides (DS-2) with a core of net-textured sulfides (NTS-2). The coarse-grained lherzolite with disseminated sulfides (DS-3) sharply cut through the upper subunit. All disseminated samples have Cu/Pd ratios (11,414–128,626) that exceed the mantle range. Additionally, the Pd/Ru ratios of DS-1 (1.26–13.2) are the lowest, followed by DS-2 (3.69–13.5), and highest in DS-3 (2.80–33.6). The exploration data indicate that the Ni and Cu contents and Cu/(Cu + Ni) ratios are significantly higher in DS-3 than in DS-2, while DS-1 shows more dispersed. The NTS-1 exhibits significant Ir and Ru depletion, with Cu/(Cu + Ni) decreasing with depth, eventually encountering Ir and Ru-riched MS. In addition, NTS-2 shows partially Ir depletion but Ru non-depletion, and Cu/(Cu + Ni) increases with depth. These signatures suggest that the lower and upper subunits, along with the coarse-grained unit, formed from platinum-group elements (PGE) in increasingly depleted magma, likely resulting from prior sulfide segregation before emplacement. Furthermore, the differences in Ir and Ru depletion and the variation in the Cu/(Cu + Ni) trend with depth between NTS-1 and NTS-2 were explained by the migration direction of fractional sulfide liquid during sulfide fractionation. We propose that the western end of the Jinchuan intrusion was formed by multi-stage magma emplacement. The strong correlation between exploration data (Ni, Cu, and Cu/(Cu + Ni)) and various sulfide mineralization layers suggests that delineating the spatial range of each sulfide mineralization could provide valuable information for deep mineral prospectivity mapping.

Global Path Optimal Planning Method for Autonomous Vehicles Based on Image Feature Extraction

In order to solve the problem of autonomous vehicles driving safely on the road while searching for optimal paths to avoid traffic congestion and obstruction, this paper establishes an optimal path planning model based on image feature extraction. The model consists of four parts: the selection of key turning points, interpolation between turning points, definition of the evaluation function, and global optimal path search. First, based on the map information provided by the network, an image feature detection algorithm was proposed, and the key turning points of the map route were selected and stored in an open table. Then, based on mechanical analysis theory, the cubic interpolation between two key turning points of the optimal path was defined. This allows the car to drive along a continuous curve with a certain arc radius, enabling it to drive smoothly, effectively avoid obstacles, and ensure safety. Then, an evaluation function is defined as needed, and different evaluation functions are specified for different road sections to avoid excessive local deviations in planning and to reduce the impact of known obstacles on the path. Finally, the cost of the search path is calculated based on the evaluation function. According to the principle of minimum cost, a globally optimal heuristic search algorithm is proposed to find the globally optimal path. Experimental results show that the proposed global optimal path planning algorithm has excellent performance, with an average accuracy of 96.71% and a search speed of 2.78 ms. The model not only provides accurate path planning and fast path selection capabilities but also has strong robustness against interference.

Including soil spatial neighbor information for digital soil mapping

Digital soil mapping (DSM) is transforming how we understand and manage soil resources, offering high-resolution spatial–temporal soil information essential for addressing environmental challenges. The integration of environmental covariates has advanced soil mapping accuracy, while the potential of neighboring soil sample data has been largely overlooked. This study introduces soil spatial neighbor information (SSNI) as a novel approach to enhance the predictive power of spatial models. Utilizing two open-access datasets from LUCAS Soil and Meuse, our findings showed that incorporating SSNI improved the accuracy of random forest models in mapping soil organic carbon density (reduced %RMSE of 3.1%), cadmium (reduced %RMSE of 3.6%), copper (reduced %RMSE of 5.9%), lead (reduced %RMSE of 11.5%), and zinc (reduced %RMSE of 7.4%). Compared to the inclusion of buffer distance or oblique geographic coordinates for modelling, SSNI also performed better for both LUCAS Soil and Meuse datasets. This study underscores the value of SSNI in improving digital soil maps by capturing the neighboring information. Embracing SSNI could lead to more informed decision-making in soil management and its potential applicability across other disciplines also remains open for exploration in future research endeavors.

Small Target Detection Algorithm Based on Improved YOLOv5

Small targets exist in large numbers in various fields. They are broadly used in aerospace, video monitoring, and industrial detection. However, because of its tiny dimensions and modest resolution, the precision of small-target detection is low, and the erroneous detection rate is high. Therefore, based on YOLOv5, an improved small-target detection model is proposed. First, in order to improve the number of tiny targets detected while enhancing small-target detection performance, an additional detection head is added. Second, involution is used between the backbone and neck to increase the channel information of feature mapping. Third, the model introduces the BiFormer, wherein both the global and local feature information are captured simultaneously by means of its double-layer routing attention mechanism. Finally, a context augmentation module (CAM) is inserted into the neck in order to maximize the structure of feature fusion. In addition, in order to consider among the required real frame as well as the prediction frame simultaneously, YOLOv5’s original loss function is exchanged. The experimental results using the public dataset VisDrone2019 show that the proposed model has P increased by 13.43%, R increased by 11.28%, and mAP@.5 and mAP@[.5:.95] increased by 13.88% and 9.01%, respectively.

Deep indoor illumination estimation based on spherical gaussian representation with scene prior knowledge

High dynamic range (HDR) illumination estimation from a single low dynamic range image is a critical task in the fields of computer vision, graphics and augmented reality. However, directly learning the full HDR environment map or parametric lighting information from a single image is extremely difficult and inaccurate. As a result, we propose a two-stage network approach for illumination estimation that integrates spherical gaussian (SG) representation with scene prior knowledge. In the first stage, a convolutional neural network is utilized to generate material and geometric information about the scene, which serves as prior knowledge for lighting prediction. In the second stage, we model indoor environment illumination using 128 SG functions with fixed center direction and bandwidth, allowing only the amplitude to vary. Subsequently, a Transformer-based lighting parameter regressor is employed to capture the complex relationship between the input images with scene prior information and its SG illumination. Additionally, we introduce a hybrid loss function, which combines a masked loss for high-frequency illumination with a rendering loss for improving the visual quality. By training and evaluating the lighting model on the created SG illumination dataset, the proposed method achieves competitive results in both quantitative metrics and visual quality, outperforming state-of-the-art methods.

A Pilot Study of Deep Learning-Based Monocular Depth Estimation from Fundus Photographs

The purpose of this study was to evaluate the feasibility of a generalizable deep-learning (DL) based system with no a priori knowledge of fundus photographs to generate monocular depth map information about optic disc structures from this imaging modality. Images of 30 stereo pairs of fundus photographs centered on the optic disc of 30 subjects were analyzed with this DL system to generate monocular depth maps using zero-shot cross-dataset transfer. These maps were registered onto reference standard depth maps derived from Optical Coherence Tomography. Accuracy of the DL system was assessed by the root of mean squared error (RMSE) between the estimate and reference standard. 47% of the total images from the dataset were successfully processed, with mean RMSE of 0.081. Our findings demonstrate that single image, monocular depth estimation with a generalizable DL system using zero-shot cross-dataset transfer applied to retinal color fundus photographs is feasible and has potential.