Search

Abstract: As we are facing the dawn of ubiquitous computing (UbiComp) by emerging mobile devices and distributed applications, personalization is leaving the desktop domain, because adaptation and context-awareness play a major role in UbiComp in order to realize the user friendliness postulated for UbiComp applications. Adaptation is a relatively new concept for GI services. Therefore we introduce the related research areas. The two most important factors for adaptation are (a) context as the representation of the current situation and (b) the user itself. In particular how to dynamically derive information on the users’ properties is a research area applying learning strategies introduced shortly. We see these two concepts not isolated but propose an integrated situation model including several types of context as well as user parameters. After this introduction we present several approaches to realizing adaptive mobile GI services in the domain of pedestrian navigation and tourist information – representing first steps towards UbiGIS (www.ubigis.org). These include context and user-aware proactive tips, personalized tour planning and adaptive maps. Implementations and new concepts for extensions of these are presented. The paper closes by an outlook on open research issues related to adaptive GI services. [Copyright &y& Elsevier]

Artificial intelligence (AI) approaches nowadays have gained remarkable success in single-modality-dominated remote sensing (RS) applications, especially with an emphasis on individual urban environments (e.g., single cities or regions). Yet these AI models tend to meet the performance bottleneck in the case studies across cities or regions, due to the lack of diverse RS information and cutting-edge solutions with high generalization ability. To this end, we build a new set of multimodal remote sensing benchmark datasets (including hyperspectral, multispectral, SAR) for the study purpose of the cross-city semantic segmentation task (called C2Seg dataset), which consists of two cross-city scenes, i.e., Berlin-Augsburg (in Germany) and Beijing-Wuhan (in China). Beyond the single city, we propose a high -resolution d omain a daptation n etwork, HighDAN for short, to promote the AI model's generalization ability from the multi-city environments. HighDAN is capable of retaining the spatially topological structure of the studied urban scene well in a parallel high-to-low resolution fusion fashion but also closing the gap derived from enormous differences of RS image representations between different cities by means of adversarial learning. In addition, the Dice loss is considered in HighDAN to alleviate the class imbalance issue caused by factors across cities. Extensive experiments conducted on the C2Seg dataset show the superiority of our HighDAN in terms of segmentation performance and generalization ability, compared to state-of-the-art competitors. The C2Seg dataset and the semantic segmentation toolbox (involving the proposed HighDAN) will be available publicly at https://github.com/danfenghong/RSE_Cross-city. • A new multimodal remote sensing benchmark for cross-city semantic segmentation. • Propose a high-resolution domain adaptation network for semantic segmentation. • Balance spatial topology, domain gaps, eases city class imbalance with Dice loss. [ABSTRACT FROM AUTHOR]

Abstract Understanding how citizens interact with transportation system is a key to solving a variety of urban issues in general and traffic congestion in particular. Recently, scholars have put efforts on the pertinent work ranging from developing traffic predictors to understanding human mobility and activity patterns. Multiple types of data have been used, of which crowdsourced data (e.g. social media data) plays an essential role. Due to the limitation of traffic information extraction from social media data raised in the existing work, this paper aims to develop an approach which allows us to explore the potential influence of human activities on daily traffic congestions through linking human activities derived from geotagged tweets to the daily traffic conditions. The result of a case study of Toronto, Canada exhibits that entertainment related activities are more likely to appear during evening peak hours, while it seems that morning rush hours are less sensitive to human activities. In addition, it is learned that the activities involved in international events tend to have a long-term impact on urban traffic. This work provides a new tool for urban planners and policy makers to deal with complex urban issues effectively using low-cost social media data and sheds light on the research on analyzing urban traffic and urban dynamics based on crowdsourced data. Highlights • We investigate the limitation of extracting urban traffic related information from social media data. • We develop a solution to study the potential influence of human activities on daily traffic congestions. • The interaction between human activities and daily traffic congestions in Toronto, Canada is explored as an example. • Findings and contributions to urban planning and policy making are discussed. [ABSTRACT FROM AUTHOR]

Cities are complex systems, where related Human activities are increasingly difficult to explore within. In order to understand urban processes and to gain deeper knowledge about cities, the potential of location-based social networks like Twitter could be used a promising example to explore latent relationships of underlying mobility patterns. In this paper, we therefore present an approach using a geographic self-organizing map (Geo-SOM) to uncover and compare previously unseen patterns from social media and authoritative data. The results, which we validated with Live Traffic Disruption (TIMS) feeds from Transport for London, show that the observed geospatial and temporal patterns between special events ( r = 0.73), traffic incidents ( r = 0.59) and hazard disruptions ( r = 0.41) from TIMS, are strongly correlated with traffic-related, georeferenced tweets. Hence, we conclude that tweets can be used as a proxy indicator to detect collective mobility events and may help to provide stakeholders and decision makers with complementary information on complex mobility processes. [ABSTRACT FROM AUTHOR]

Detailed knowledge regarding the whereabouts of people and their social activities in urban areas with high spatial and temporal resolution is still widely unexplored. Thus, the spatiotemporal analysis of Location Based Social Networks (LBSN) has great potential regarding the ability to sense spatial processes and to gain knowledge about urban dynamics, especially with respect to collective human mobility behavior. The objective of this paper is to explore the semantic association between georeferenced tweets and their respective spatiotemporal whereabouts. We apply a semantic topic model classification and spatial autocorrelation analysis to detect tweets indicating specific human social activities. We correlated observed tweet patterns with official census data for the case study of London in order to underline the significance and reliability of Twitter data. Our empirical results of semantic and spatiotemporal clustered tweets show an overall strong positive correlation in comparison with workplace population census data, being a good indicator and representative proxy for analyzing workplace-based activities. [ABSTRACT FROM AUTHOR]

Geotagged photos on social media like Flickr explicitly indicate the trajectories of tourists. They can be employed to reveal the tourists’ preference on landmarks and routings of tourism. Most of existing works on routing searches are based on the trajectories of GPS-enabled devices’ users. From a distinct point of view, we attempt to propose a novel approach in which the basic unit of routing is separate road segment instead of GPS trajectory segment. In this paper, we build a recommendation system that provides users with the most popular landmarks as well as the best travel routings between the landmarks. By using Flickr geotaggged photos, the top ranking travel destinations in a city can be identified and then the best travel routes between the popular travel destinations are recommended. We apply a spatial clustering method to identify the main travel landmarks and subsequently rank these landmarks. Using machine learning method, we calculate the tourism popularity of the road in terms of relevant parameters, e.g., the number of users and the number of Point-of-Interests. These popularity assessments are integrated into the routing recommendation system. The routing recommendation system takes into consideration both the popularity assessment and the length of the road. The best route recommended to the user minimizes the distance while including maximal tourism popularity. Experiments were conducted in two different scenarios. The empirical results show that the recommendation system is able to provide the user good travel planning including both top ranking landmarks and suitable routings in a city. Besides, the system offers user-generated semantic information for the recommended routes. [ABSTRACT FROM AUTHOR]

Over the last two years, we have witnessed the ever-fast growth of micro-mobility services (e.g., e-bikes and e-scooters), which brings both challenges and innovations to the traditional urban transportation systems. For example, they provide an opportunity to better address the "last mile" problem due to their convenience, flexibility and zero emission. As such, it is essential to understand why and how urban dwellers use these micro-mobility services across space and time. In this paper, we aim to understand spatiotemporal trip purposes of urban micro-mobility through the lens of dockless e-scooter user behavior. We first develop a spatiotemporal topic modeling method to infer the underlying trip purpose of dockless e-scooter usage. Then, using Washington, D.C. as a case study, we apply the model to a dataset including 83,002 valid user trips together with 19,370 POI venues and land use land cover data to systematically explore the trip purposes of micro-mobility across space and time in the city. The results confirm a set of uncovered 100 Trips Topics as an informative and effective proxy of the spatiotemporal trip purposes of micro-mobility users. The findings in this paper provide important insights for city authorities and dockless e-scooter companies into more sustainable urban transportation planning and more efficient vehicle fleet reallocation in future smart cities. • Understand trip purpose by mining dockless e-scooter OD trips and POI data via LDA. • 100 Trips Topics as proxies of trip purpose and related urban activities. • Discover spatiotemporal patterns of trip purpose regarding rush-hour and LULC classes. • Generally applicable approach with low-cost data independent of the user survey. [ABSTRACT FROM AUTHOR]

Abstract: Most algorithms performing segmentation of 3D point cloud data acquired by, e.g. Airborne Laser Scanning (ALS) systems are not suitable for large study areas because the huge amount of point cloud data cannot be processed in the computer’s main memory. In this study a new workflow for seamless automated roof plane detection from ALS data is presented and applied to a large study area. The design of the workflow allows area-wide segmentation of roof planes on common computer hardware but leaves the option open to be combined with distributed computing (e.g. cluster and grid environments). The workflow that is fully implemented in a Geographical Information System (GIS) uses the geometrical information of the 3D point cloud and involves four major steps: (i) The whole dataset is divided into several overlapping subareas, i.e. tiles. (ii) A raster based candidate region detection algorithm is performed for each tile that identifies potential areas containing buildings. (iii) The resulting building candidate regions of all tiles are merged and those areas overlapping one another from adjacent tiles are united to a single building area. (iv) Finally, three dimensional roof planes are extracted from the building candidate regions and each region is treated separately. The presented workflow reduces the data volume of the point cloud that has to be analyzed significantly and leads to the main advantage that seamless area-wide point cloud based segmentation can be performed without requiring a computationally intensive algorithm detecting and combining segments being part of several subareas (i.e. processing tiles). A reduction of 85% of the input data volume for point cloud segmentation in the presented study area could be achieved, which directly decreases computation time. [Copyright &y& Elsevier]