Proceedings of the 29th International Conference on Advances in Geographic Information Systems最新文献_第7页

Remote Sensing Image Captioning with Continuous Output Neural Models 基于连续输出神经模型的遥感图像字幕

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3483631

R. Ramos, Bruno Martins

引用次数: 2

Handling Fuzzy Spatial Data in R Using the fsr Package 使用fsr包处理R中的模糊空间数据

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3484255

A. Carniel, Felippe Galdino, J. S. Philippsen, Markus Schneider

{"title":"Handling Fuzzy Spatial Data in R Using the fsr Package","authors":"A. Carniel, Felippe Galdino, J. S. Philippsen, Markus Schneider","doi":"10.1145/3474717.3484255","DOIUrl":"https://doi.org/10.1145/3474717.3484255","url":null,"abstract":"GIS and spatial data science (SDS) tools have been recently approaching each other by establishing bridge technologies between them. R as one of the most prominent programming languages used in SDS projects has been granted access to GIS infrastructure, while R scripts can be integrated and executed in GIS functions. Unfortunately, the treatment of spatial fuzziness has so far not been considered in SDS projects and bridge technologies due to a lack of software packages that can handle fuzzy spatial objects. This paper introduces an R package named fsr as an implementation of the fuzzy spatial data types, operations, and predicates of the Spatial Plateau Algebra that is based on the abstract Fuzzy Spatial Algebra. This R package solves the problem of constructing fuzzy spatial objects as spatial plateau objects from real datasets and describes how to conduct exploratory spatial data analysis by issuing geometric operations and topological predicates on fuzzy spatial objects. Further, fsr provides the possibility of designing fuzzy spatial inference models to discover new findings from fuzzy spatial objects. It optimizes the inference process by deploying the particle swarm optimization to obtain the point locations with the maximum or minimum inferred values that answer a specific user request.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"293 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131832401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

STAR 明星

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3484265

Zhida Chen, Gao Cong, Walid G. Aref

引用次数: 3

Estimated Time of Arrival Prediction via Modeling the Spatial-Temporal Interactions between Links and Crosses 基于链接和交叉时空相互作用模型的估计到达时间预测

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3488373

Xiaowei Mao, Tianyu Cai, Wenchuang Peng, Huaiyu Wan

{"title":"Estimated Time of Arrival Prediction via Modeling the Spatial-Temporal Interactions between Links and Crosses","authors":"Xiaowei Mao, Tianyu Cai, Wenchuang Peng, Huaiyu Wan","doi":"10.1145/3474717.3488373","DOIUrl":"https://doi.org/10.1145/3474717.3488373","url":null,"abstract":"The ACM SIGSPATIAL GIS CUP 2021 focuses on Estimated Time of Arrival (ETA) prediction, which is important to the travel scheduling and decision-making of ride-hailing platforms. Accurate ETA prediction is very challenging since ETA is affected by many heterogeneous influencing factors, including static features (e.g., number of links) and dynamic features (e.g., real-time road conditions). Meanwhile, ETA can also be affected by complex spatial-temporal dependencies between links and crosses in the route. To tackle the above challenges, we propose a deep learning method based on the Wide-Deep-Recurrent (WDR) architecture while modeling the interactions between links and crosses. We adopt Neural Factorization Machines (NFM) to memorize the historical patterns and a multiple layer perceptron (MLP) to integrate various heterogeneous influencing factors. We also model links and crosses jointly to learn their spatial-temporal dependencies in the route. Extensive experiments conducted on a real dataset show that our method achieves a high prediction accuracy. The source code is available at: https://github.com/wanhuaiyu/WDR-LC.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121973507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

TrajNet

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3486806

Sumanto Dutta

引用次数: 0

Point in Polygon Tests Using Hardware Accelerated Ray Tracing 使用硬件加速光线追踪的多边形测试中的点

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3486796

Moritz Laass

引用次数: 1

Multimodal Fusion of Satellite Images and Crowdsourced GPS Traces for Robust Road Attribute Detection 基于多模态融合的卫星图像和众包GPS轨迹鲁棒道路属性检测

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3483917

Yifang Yin, An Tran, Ying Zhang, Wenmiao Hu, Guanfeng Wang, Jagannadan Varadarajan, Roger Zimmermann, See-Kiong Ng

{"title":"Multimodal Fusion of Satellite Images and Crowdsourced GPS Traces for Robust Road Attribute Detection","authors":"Yifang Yin, An Tran, Ying Zhang, Wenmiao Hu, Guanfeng Wang, Jagannadan Varadarajan, Roger Zimmermann, See-Kiong Ng","doi":"10.1145/3474717.3483917","DOIUrl":"https://doi.org/10.1145/3474717.3483917","url":null,"abstract":"Automatic inference of missing road attributes (e.g., road type and speed limit) for enriching digital maps has attracted significant research attention in recent years. A number of machine learning based approaches have been proposed to detect road attributes from GPS traces, dash-cam videos, or satellite images. However, existing solutions mostly focus on a single modality without modeling the correlations among multiple data sources. To bridge the gap, we present a multimodal road attribute detection method, which improves the robustness by performing pixel-level fusion of crowdsourced GPS traces and satellite images. A GPS trace is usually given by a sequence of location, bearing, and speed. To align it with satellite imagery in the spatial domain, we render GPS traces into a sequence of multi-channel images that simultaneously capture the global distribution of the GPS points, the local distribution of vehicles' moving directions and speeds, and their temporal changes over time, at each pixel. Unlike previous GPS based road feature extraction methods, our proposed GPS rendering does not require map matching in the data preprocessing step. Moreover, our multimodal solution addresses single-modal challenges such as occlusions in satellite images and data sparsity in GPS traces by learning the pixel-wise correspondences among different data sources. Extensive experiments have been conducted on two real-world datasets in Singapore and Jakarta. Compared with previous work, our method is able to improve the detection accuracy on road attributes by a large margin.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130361980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

AIS Data as Trajectories and Heat Maps AIS数据轨迹和热图

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3484208

Andreas S. Andersen, Andreas D. Christensen, Philip Michaelsen, Shpend Gjela, K. Torp

{"title":"AIS Data as Trajectories and Heat Maps","authors":"Andreas S. Andersen, Andreas D. Christensen, Philip Michaelsen, Shpend Gjela, K. Torp","doi":"10.1145/3474717.3484208","DOIUrl":"https://doi.org/10.1145/3474717.3484208","url":null,"abstract":"All large ships are by international law required to provide their position, speed, and course while sailing. This data is called AIS data. Several maritime organizations make this data freely available. In this paper, we present two approaches to querying AIS data. The first approach combines the individual AIS data records into trajectories and the second approach is to combine many trajectories into heat maps. The first approach is well suited, e.g., to find the complete route of a few ships or study how many ships are navigating in a smaller area known to be complicated to sail. The heat-map approach is particularly well suited to provide an overview of ship movements in large areas. For the trajectory approach, we introduce and define a novel way to query AIS data called a trident query. This query type is developed in close collaboration with domain experts. The core idea with a trident query is to visualize route choices. The heat-map approach works both for user-defined areas and for predefined Areas Of Interest (AOI) cells. The trajectory approach is difficult to scale and we show how the trajectories can be simplified to make querying and visualization more efficient. We present data on a map and statistical details are provided in graphs and tables, e.g., the distribution of ship types and ship dimensions (length, width, and draught). End-users can filter on attributes such as ship IDs, ship types, and ship dimensions for both the trajectory and heap-map approaches.","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128604626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Scalable Spatio-Temporal Top-k Community Interactions Query 可扩展时空Top-k社区交互查询

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3483962

Abdulaziz Almaslukh, Yongyi Liu, A. Magdy

引用次数: 0

Attention-Based Spatial Interpolation for House Price Prediction 基于注意力的房价空间插值预测

Proceedings of the 29th International Conference on Advances in Geographic Information Systems Pub Date : 2021-11-02 DOI: 10.1145/3474717.3484257

Darniton Viana, Luciano Barbosa

{"title":"Attention-Based Spatial Interpolation for House Price Prediction","authors":"Darniton Viana, Luciano Barbosa","doi":"10.1145/3474717.3484257","DOIUrl":"https://doi.org/10.1145/3474717.3484257","url":null,"abstract":"Estimating the market price of a house is important for many businesses such as real estate and mortgage lending companies. The price of a house depends not only on its structural features (e.g. area and number of bedrooms) but also on the spatial context where it is located. In this work we estimate the price of a house based solely on its structural features and the characteristics and price of its neighbors. For that, we propose a hybrid attention mechanism that weights neighbors based on their similarity to the house in terms of structural features and geographic location. For the structural features, we apply an euclidean-based attention and, for the geographic location, we propose an attention layer based on a radial basis function kernel. Those attention mechanisms are then used by a neural network regressor to predict the price of a house and to generate a vector representation of the house based on its implicit context: the house embedding, which can be used as a feature set by any regressor to perform house price prediction. We have performed an extensive experimental evaluation on real-world datasets that shows that: (1) regressors using house embedding obtained the best results on all 4 datasets, outperforming baseline models; (2) the learned house embedding improves the performance of the evaluated regressors in almost all scenarios in comparison to raw features; and (3) simple regressor models such as Linear Regression using house embedding achieved comparable results to more competitive algorithms (e.g. Random Forest and Xgboost).","PeriodicalId":340759,"journal":{"name":"Proceedings of the 29th International Conference on Advances in Geographic Information Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117235189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2