Hasil untuk "Maps"

Ting Zhao, Xiangqian Wu

Saliency detection is one of the basic challenges in computer vision. Recently, CNNs are the most widely used and powerful techniques for saliency detection, in which feature maps from different layers are always integrated without distinction. However, instinctively, the different feature maps of CNNs and the different features in the same maps should play different roles in saliency detection. To address this problem, a novel CNN named pyramid feature attention network (PFAN) is proposed to enhance the high-level context features and the low-level spatial structural features. In the proposed PFAN, a context-aware pyramid feature extraction (CPFE) module is designed for multi-scale high-level feature maps to capture the rich context features. A channel-wise attention (CA) model and a spatial attention (SA) model are respectively applied to the CPFE feature maps and the low-level feature maps, and then fused to detect salient regions. Finally, an edge preservation loss is proposed to get the accurate boundaries of salient regions. The proposed PFAN is extensively evaluated on five benchmark datasets and the experimental results demonstrate that the proposed network outperforms the state-of-the-art approaches under different evaluation metrics.

Haiyuan Yu, P. Braun, Muhammed A. Yıldırım et al.

P. Wessel, Walter H. F. Smith

S. Schmid, B. Fügenschuh, E. Kissling et al.

D. Walker, M. Raynolds, F. Daniëls et al.

Saikat Panja

We introduce the notions of Fatou and Julia sets in the context of word maps on complex Lie groups and polynomial maps on finite-dimensional associative $\mathbb C$-algebras. For the group-theoretic question, we investigate the dynamics of the power map $x \mapsto x^{M}$ on the Lie group $\mathrm{GL}_n(\mathbb C)$, where $M \geq 2$ is an integer. For the algebra-related question, we study polynomial self-maps of $\mathrm{M}_n(\mathbb C)$ induced by monic polynomials in one variable. In both cases, we pin down the explicit description of the Fatou and Julia sets. We also show that there does not exist any wandering Fatou component of the pair $(p,\mathrm M_n(\mathbb C))$ where $p\in\mathbb C[z]$ is a monic polynomial of degree $\geq 2$.

Yunshuang Yuan, Frank Thiemann, Monika Sester

Historical maps are valuable resources that capture detailed geographical information from the past. However, these maps are typically available in printed formats, which are not conducive to modern computer-based analyses. Digitizing these maps into a machine-readable format enables efficient computational analysis. In this paper, we propose an automated approach to digitization using deep-learning-based semantic segmentation, which assigns a semantic label to each pixel in scanned historical maps. A key challenge in this process is the lack of ground-truth annotations required for training deep neural networks, as manual labeling is time-consuming and labor-intensive. To address this issue, we introduce a weakly-supervised age-tracing strategy for model fine-tuning. This approach exploits the similarity in appearance and land-use patterns between historical maps from neighboring time periods to guide the training process. Specifically, model predictions for one map are utilized as pseudo-labels for training on maps from adjacent time periods. Experiments conducted on our newly curated \textit{Hameln} dataset demonstrate that the proposed age-tracing strategy significantly enhances segmentation performance compared to baseline models. In the best-case scenario, the mean Intersection over Union (mIoU) achieved 77.3\%, reflecting an improvement of approximately 20\% over baseline methods. Additionally, the fine-tuned model achieved an average overall accuracy of 97\%, highlighting the effectiveness of our approach for digitizing historical maps.

Zhenzhen Song, Mingqiang Guo, Liang Wu et al.

While most existing advanced large-scale point cloud semantic segmentation methods can accurately identify most large-scale objects, there is still room for improvement in the recognition accuracy of small-scale, low-proportion objects. Compared to point clouds, digital orthophoto maps (DOMs) has a more structured data format, allowing for better recognition of small-scale surface features. However, in existing projection-based methods, directly mapping images onto point clouds leads to occlusion issues. If image and point cloud features are simply concatenated, it results in feature blurring. Based on this observation, this article proposes a DAPSS network for point cloud semantic segmentation, assisted by prior knowledge constructed from DOM. The pretrained DOM features can provide a broader receptive field as guidance for learning the local context features of point clouds. Vertical occlusion has an issue, making ray-based mapping methods unsuitable. We propose a method that search for the nearest mapped point cloud in spherical space to fill in the occluded point cloud based on the already mapped point cloud. The traditional approach of directly concatenating point cloud features with image features often leads to feature blurring. Therefore, we propose a plug-and-play multimodal feature adaptive fusion module, which can adaptively select and aggregate features from different modalities to reduce redundant information further. In addition, we designed a cascaded multimodal feature deep fusion module to promote deep fusion between different modal features. Experiments on two large datasets demonstrate that DAPSS outperforms current mainstream methods, achieving mean Intersection-over-Union scores of 65.9% and 82.9% on the SansetUrban and SUM-Helsinki datasets, respectively. DAPSS not only effectively addresses the recognition of small-scale surface features, but also resolves the occlusion problems associated with projection-based methods.

Yujian Yang, Ying Zhao, Rongjiang Yao et al.

Soil salinization poses a serious global threat to agricultural production and has emerged as a critical issue of land degradation. To comprehensively investigate the risks and uncertainty quantification associated with soil salinization, Yucheng County, a typical fluvo-aquic soil area located in Shandong Province, China, was selected as the case study region. In October 2021, soil samples were collected from 101 sampling sites utilizing the Global Navigation Satellite System (GNSS) for precise positioning. Soil electrical conductivity (EC) was measured at these sites using a PR-3001-TRREC-N01 sensor. The performance of Bayesian inference using Integrated Nested Laplace Approximation with the Stochastic Partial Differential Equation (INLA-SPDE) approach for predicting soil salinization at unsampled locations was compared with that obtained using Kriging. The results indicated that the maps generated by the Kriging interpolation and INLA-SPDE approach showed similar distribution patterns for soil salinization but differed in detail. High EC values corresponded to specific regions, while low EC values were consistent across both methods. The posterior mean, together with the lower and upper limits of the 95 % credible intervals, effectively quantified the uncertainty associated with soil salinization risk. Both Fangsi township and Xindian township are identified as high-risk areas for soil salinization with exceedance probability map for policymaking. Correspondingly, the implementation of an optimized farmland irrigation and drainage system is recommended, particularly in low-lying areas, to mitigate soil salinization. Additionally, No-U-Turn Sampler (NUTS), highest-posterior density interval (HDI), Kernel density estimation (KDE), rank plots and trace plots enhanced the transparency and interpretability of soil salinization prediction. KDE of 100 groups of predicted values showed a good fit based on data-driven soil EC, higher levels of uncertainty associated with soil EC correspond to areas where the gaussian distributions overlap using Theano, as PyMC3 core component based on deep learning principles.

Szilárd Szabó, Abdelmajeed A. Elrasheed, Lilla Kovács et al.

Reference data are the most crucial points in model building. In geoscience, a scarcity of sufficient reference data is common. Pseudo-labelling (PL), i.e. incorporating high-probability data in the model-building process, offers a potential solution. We aimed to reveal the efficiency of PL in lithological mapping in a vegetation-free arid region of Sudan. Multiple Adaptive Regression Splines (MARS) and Random Forest (RF) were used to classify a Landsat 9 image. Reference data were collected during fieldwork and through visual interpretation. Image processing yielded classified maps with associated probability layers, from which 1000 additional traditional samples (PL data) were extracted at a 95 percent probability. A detailed accuracy assessment was conducted, and accuracy measures were evaluated using statistical analysis and visual inspection. MARS was found to be an ambiguous classifier because the probability was too optimistic related to the overall accuracy (OA) (81% of samples had above 99% probability, OA = 98.2%) compared to RF (21% above 99%, OA = 98.1%); that is, despite the high probability, the accuracy improvement was only 0.1 percent. At the class level, the correlation between probability and the F1-score was low (0.21%). The original and PL-based models resulted in different maps with improved accuracy, although the new model version showed lower probability values for both the classifiers. Visual inspection proved essential for better insights into the spatial patterns: expert knowledge is crucial for controlling the occurrence of rock types and identifying false classifications. The main finding is that probability should be handled carefully, as it does not guarantee high model performance in classification, although the PL approach can lead to more reliable maps.

Ning Zhang, Yongcheng Wang, Gang Li et al.

In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by variational autoencoders (VAEs) that model data distributions through latent representations, this paper proposes a VAE framework for unsupervised remote sensing image (RSI) SR. VAEs excel at learning rich latent representations, modeling probabilistic distributions of input data and unsupervised learning, making them inherently well-suited to real-world blind SR scenarios. The proposed framework consists of an encoder that maps low-resolution (LR) images into a latent space and a decoder that reconstructs super-resolved images from the latent representations. To enhance latent modeling, an alternating optimization strategy is implemented for training the encoder and decoder. Furthermore, a comprehensive loss function and a latent coding regularization strategy are designed to constrain latent representations while maintaining image domain consistency. Experimental results demonstrate that on synthetic data, our method achieves favorable performance in both visual quality and quantitative metrics. It also demonstrates competitively performance compared to supervised methods, particularly in 4× and 8× SR tasks. Additionally, evaluations on Jilin-1 satellite RSIs further validate the effectiveness of our approach.

Shaozong Wang

In this paper, we study the gluing construction of the extended harmonic maps between Riemannian manifolds. Harmonic maps are critical points of the energy functional. We construct the gluing map of the extended harmonic maps from Riemann surfaces to some Riemannian manifold $N$ under certain conditions.

Qijin Song, Weibang Bai

Can robots imagine or generate maps like humans do, especially when only limited information can be perceived like blind people? To address this challenging task, we propose a novel group diffusion model (GDM) based architecture for robots to generate point cloud maps with very limited input information.Inspired from the blind humans' natural capability of imagining or generating mental maps, the proposed method can generate maps without visual perception data or depth data. With additional limited super-sparse spatial positioning data, like the extra contact-based positioning information the blind individuals can obtain, the map generation quality can be improved even more.Experiments on public datasets are conducted, and the results indicate that our method can generate reasonable maps solely based on path data, and produce even more refined maps upon incorporating exiguous LiDAR data.Compared to conventional mapping approaches, our novel method significantly mitigates sensor dependency, enabling the robots to imagine and generate elementary maps without heavy onboard sensory devices.

Vitor Hugo dos Santos Filho, Luis Maurício Martins de Resende, Joseane Pontes

This study aims to develop a theoretical model for digital risks arising from implementing Industry 4.0 (represented by the acronym TMR-I4.0). A systematic literature review was initially conducted using the Methodi Ordinatio methodology to map the principal dimensions and digital risks associated with Industry 4.0 in order to achieve this objective. After completing the nine steps of Methodi, a bibliographic portfolio with 118 articles was obtained. These articles were then subjected to content analysis using QSR Nvivo^® version 10 software to categorize digital risks. The analysis resulted in the identification of 9 dimensions and 43 digital risks. The categorization of these risks allowed the construction of maps showing the digital risks and their impacts resulting from the implementation of Industry 4.0. This study advances the literature by proposing a comprehensive categorization of digital risks associated with Industry 4.0, which resulted from an exhaustive literature review. At the conclusion of the study, based on the proposed Theoretical Risk Model for Digital Risks arising from the implementation of Industry 4.0, a research agenda for future studies will be proposed, enabling other researchers to further explore the landscape of digital risks in Industry 4.0.

Ciro Federico Tipaldi, Kaspars Vitols, Tots Kokis et al.

The following research paper concerns the analysis and characterisation of commercially available surface-enhanced Raman scattering (SERS) substrates. SERS has long been a potentially very powerful method with a great deal of interest around it; however, there are still many obstacles which do not allow SERS to be easily applied to real-world detection and analysis problems. As such, research around the various types of substrates is ongoing, in the hope of streamlining and improving the Raman enhancement mechanism. Scanning electron microscope images were obtained for each of the three substrates, and their features and scales were described. Enhanced Raman spectra for Rhodamine B were obtained for a range of concentrations using each of the three substrates, and, in addition, surface enhancement maps are presented. Enhancement factors were calculated for the 1358 cm⁻¹ peak of Rhodamine B. Complementing the experimental work, theoretical FEM modelling in <i>COMSOL Multiphysics</i> was performed, with the resulting calculations yielding an enhancement prediction adequately accurate to the real substrates.

Miroslav Hristov, Atanas Ilchev, Petar Kopanov et al.

We investigate fixed points for <i>p</i> cyclic maps by introducing a new notion of <i>p</i>–cyclic infimum summing maps and a generalized best proximity point for <i>p</i>–cyclic maps. The idea generalizes some results about best proximity points in order to widen the class of sets and maps for which we can ensure the existence and uniqueness of best proximity points. The replacement of the classical notions of best proximity points and distance between the consecutive set arises from the well-known group traveling salesman problem and presents a different approach to solving it. We illustrate the new result with a map that does not satisfy the known results about best proximity maps for <i>p</i>–cyclic maps.

Ali Pakdaman

In this paper we introduce notions of digital semicovering and digital quasicovering maps. We show that these are generalizations of digital covering maps and investigate their relations. We will also clarify the relationship between these generalizations and digital path lifting.

C. Scotese, R. Bambach, C. Barton et al.

Seán McGarraghy, Gudrun Olafsdottir, Rossen Kazakov et al.

System dynamics and agent-based simulation modelling approaches have a potential as tools to evaluate the impact of policy related decision making in food value chains. The context is that a food value chain involves flows of multiple products, financial flows and decision making among the food value chain players. Each decision may be viewed from the level of independent actors, each with their own motivations and agenda, but responding to externalities and to the behaviours of other actors. The focus is to show how simulation modelling can be applied to problems such as fairness and power asymmetries in European food value chains by evaluating the outcome of interventions in terms of relevant operational indicators of interorganisational fairness (e.g., profit distribution, market power, bargaining power). The main concepts of system dynamics and agent-based modelling are introduced and the applicability of a hybrid of these methods to food value chains is justified. This approach is outlined as a research agenda, and it is demonstrated how cognitive maps can help in the initial conceptual model building when implemented for specific food value chains studied in the EU Horizon 2020 VALUMICS project. The French wheat to bread chain has many characteristics of food value chains in general and is applied as an example to formulate a model that can be extended to capture the functioning of European FVCs. This work is to be further progressed in a subsequent stream of research for the other food value chain case studies with different governance modes and market organisation, in particular, farmed salmon to fillet, dairy cows to milk and raw tomato to processed tomato.

D. Wood