Crowd Map Research Articles

Dynamic indoor mapping for AVP: Crowdsourcing mapping without prior maps

AbstractHigh‐definition maps are essential for autonomous vehicle navigation, but indoor parking lots remain poorly mapped due to high costs. To address this, a crowdsourcing model gathers data from consumer‐grade sensors in mass‐produced vehicles to create semantic maps. Indoor parking lots lack GNSS signals, and most of them do not have high‐definition maps or navigation maps as references, making it difficult to ensure the accuracy of the final mapping results. Additionally, the semantic information of indoor parking lots is relatively limited, and the geometric features are overly similar, which significantly impacts the accuracy of point cloud registration. Therefore, this article proposes a crowdsourcing‐based approach, where vehicles generate local semantic maps at the client end and upload them to the cloud. Leveraging the scene characteristics of indoor parking lots, the cloud optimizes and fits a large amount of crowdsourced data to obtain a high‐precision base map without prior information. Enhanced ICP point cloud registration merges subsequent maps with the base. Additionally, parking space occupancy information is provided. This map can furnish the necessary information for Autonomous Valet Parking (AVP) tasks. Evaluation on the BEVIS dataset shows a root mean square error of 0.482446 m for vehicle localization on the cloud‐based map.

The Divergent Effect of Competition on Platforms: Deterring Recruits, Motivating Converts

Knowledge platforms differ in how they source their knowledge; they can be categorized as traditional (e.g., Encyclopedia Britannica, Guide Michelin) or crowdsourced (e.g., Wikipedia, Yelp). Although research has compared and contrasted the two, we study how they compete with one another. In particular, we focus on how competition from traditional platforms affects volunteers’ contributions to crowdsourced platforms. We propose a divergent effect: competition increases individual contributions from volunteers who were already active before the entry of any competitor (pre-entry contributors). However, competition also hinders recruitment and therefore leads to a decrease in total contributions from the set of volunteers who are new to the platform in a given time period (newly recruited contributors). We suggest the first effect is driven by pre-entry contributors’ ideological attachment, whereas the second is driven by lower awareness of the platform postcompetitive entry. To test our theory, we leverage and examine how the phased entry of Google Maps in different countries affects contributions to OpenStreetMap, a crowdsourced mapping platform. We find the hypothesized divergent effects and provide suggestive evidence of the underlying mechanisms. We contribute to research on crowdsourcing, volunteers’ willingness to contribute, platform competition, and on the effect of competition on organizations more broadly. Funding: The authors acknowledge the financial support of the INSEAD Alumni Fund. Supplemental Material: The online appendices are available at https://doi.org/10.1287/stsc.2022.0125 .

High precision map crowdsource update technology and SLAM technology - Application in autonomous driving

In response to the challenges faced by real-time dynamic updates of high-precision maps for autonomous driving in terms of high precision, high reliability, and high safety, this paper summarizes the difficulties and challenges currently faced by high-precision map updates. Accelerate the large-scale commercialization of autonomous driving high-precision maps. Thus, improving the safety and stability of intelligent vehicles and providing critical support for high-level autonomous driving. Firstly, the definition and connotation of autonomous driving maps were described, and the data characteristics and functional applications of autonomous driving maps were pointed out. Secondly, the development status and trends of high-precision map updates were reviewed, and the advantages and disadvantages of centralized map updates and crowdsourced map updates were summarized. Pointing out that crowdsource updates have become a new trend in the development of map updates. Once again, the basic architecture and key core modules of current crowdsource updates were summarized, and an analysis was conducted on key core technologies, summarizing the current status and trends of key technologies involved in crowdsource updates. The results indicate that the current technology still faces 7 main challenges, including map modeling, high-precision positioning, 3D reconstruction, fusion updates, data security, rapid review, and standard laws and regulations to address these challenges.

EMERGING TECHNOLOGY-BASED INTERVENTIONS TO SUPPORT FAMILY CAREGIVERS

Abstract There are 53 million family caregivers in the U.S., most of whom experience difficulty coordinating care, health and mental health decline, social isolation, and loneliness. Furthermore, accessing community support services remains challenging. This gap in access can create a significant threat to caregivers’ wellbeing and quality of life. The need to develop innovative interventions to support family caregivers is urgent. This symposium will describe the potential of leveraging emerging technology-based interventions to support family caregivers. Speaker one will outline considerations for design and development of social engagement interventions for caregivers delivered via video-conferencing platforms. Speaker two will describe the development and initial testing of a touchscreen mobile application that supports communication between people living with dementia and their caregivers to promote person-centered care. Speaker three will describe the human-centered design of a digital health solution to improve symptom management in advanced cancer care for older adults, emphasizing specific strategies to incorporate evidence-based principles of digital inclusivity. Speaker four will present findings from a proof of concept study examining the acceptability of a virtual respite program for caregivers of individuals with dementia. Speaker five will explore the potential for crowdsourced mapping technologies to support caregivers of people living with dementia. The discussant will tie together themes, offer recommendations for future intervention research with family caregivers, and discuss implications of emerging technologies on practice, policy, and research.

THE POTENTIAL OF CROWDSOURCED ASSET MAPPING TECHNOLOGIES FOR SUPPORTING DEMENTIA CAREGIVERS

Abstract It is well-established that caregivers of people living with dementia (PLWD) often report having difficulty finding information about education and support that is available to them in their community. Caregiver support groups have demonstrated to be an effective approach to caregiver education through mutual support, though many caregivers are unable to participate in caregiver support groups due to time and geographic constraints. Crowdsourced technologies that rely on volunteered geographic information (VGI) are a viable way of community members to provide mutual support on a variety of issues, including disaster response, traffic conditions, health, and travel. These technologies often rely on a mobile app where users upload VGI that are of interest to others who use the app. There are benefits and drawbacks of crowdsourced technologies. For example, they may be an easy way for community members to share needed information, though there may be challenges in the quality of data that users provide. This presentation will report findings from a project that examined dementia caregivers’ interest in using crowdsourced mapping technologies to share information about services and resources in their community that they have found helpful. Data were collected from a diverse sample of dementia caregivers living in Alabama through an online survey that was administered between June and November of 2022. Overall, it was found that caregivers were interested in using a crowdsourcing technology for support and education. Additional findings provide guidance for developing a crowdsourcing protocol that is based on caregivers’ reported information needs.

Traffic Flow-Based Crowdsourced Mapping in Complex Urban Scenario

Traffic Flow-Based Crowdsourced Mapping in Complex Urban Scenario

Getting People with Dementia onto the Map: Scaffolding Qualitative GIS

A deficit framing continues to surround the perceived capabilities of people with dementia to comprehend and engage with cartographic maps. While some people with dementia might experience issues with wayfinding and spatial orientation, this has frequently been unfairly extended to all people living with dementia. From the perspective of qualitative research, the potentials for how mapping might contribute methodologically to understanding how some people with dementia negotiate and experience place has yet to be fully realised. A nascent turn towards geographic concepts of space and place has seen social health and dementia researchers acknowledging the vitality of place and neighbourhoods for understanding how everyday life unfolds relationally for people with dementia. However, creative methods to capture these spatial experiences are needed. This paper describes the nature of the scaffolds that supported involvement of people with dementia into a qualitative GIS project. These scaffolds were essential for supporting participants to trace out their narratives, histories, connections and barriers to engagement in their familiar neighbourhoods. We demonstrate via an Australian example how scaffolded sketch mapping interviews and crowdsourced maps offer tangible and evocative means to pin their lived experiences to the map. For place-based dementia research, qualitative GIS offers two paths forward. First, with the relevant scaffolds in place, the imaginative power of the map can engage people with dementia in qualitative research about the places they know and frequent. Second, spatial visualisations are imbued with political agency, acting as a conduit toward meaningful change in their local communities.

Online transportation network cyber-attack detection based on stationary sensor data

Penetration of connected vehicles and crowdsourced mapping applications give rise to security vulnerabilities in transportation networks. Accurate detection of cyber-attacks on transportation networks is critical to minimize impacts on transportation systems. This task is particularly challenging because the impacts of regional cyber-attacks can be invisible on aggregated traffic data, especially when only sensor data is accessible to transportation agencies. We propose an analytical framework that leverages real-time road link sensory data to conduct online data-driven transportation network anomaly detection using non-parametric long short-term memory (LSTM) and parametric Gaussian process model. The online anomaly detection models can continuously update model coefficients as real-time sensory data arrives. We utilize a city-scale microscopic traffic simulation to validate our cyber-attack detecting framework. The cyber-attack detection model achieves a F1 score, which is a harmonic mean of the precision and recall of classifiers, between 84% to 96% considering different initial training data sizes. We compare with major offline models to demonstrate the effectiveness and robustness of online models. In addition, we devised a meta-heuristic method to solve the multi-objective sensor location problem to simultaneously enhance anomaly detection efficiency and maximize traffic information gain. This study demonstrates a systematic approach to address the emerging concerns of cyber-security in transportation networks with minimum requirements for infrastructure upgrades. Our results can help transportation security authorities identify potential cyber-attacks and protect transportation infrastructure from malicious cyber-hackers.

Efficacy of Low-Cost Sensor Networks at Detecting Fine-Scale Variations in Particulate Matter in Urban Environments.

The negative health impacts of air pollution are well documented. Not as well-documented, however, is how particulate matter varies at the hyper-local scale, and the role that proximal sources play in influencing neighborhood-scale patterns. We examined PM2.5 variations in one airshed within Indianapolis (Indianapolis, IN, USA) by utilizing data from 25 active PurpleAir (PA) sensors involving citizen scientists who hosted all but one unit (the control), as well as one EPA monitor. PA sensors report live measurements of PM2.5 on a crowd sourced map. After calibrating the data utilizing relative humidity and testing it against a mobile air-quality unit and an EPA monitor, we analyzed PM2.5 with meteorological data, tree canopy coverage, land use, and various census variables. Greater proximal tree canopy coverage was related to lower PM2.5 concentrations, which translates to greater health benefits. A 1% increase in tree canopy at the census tract level, a boundary delineated by the US Census Bureau, results in a ~0.12 µg/m3 decrease in PM2.5, and a 1% increase in "heavy industry" results in a 0.07 µg/m3 increase in PM2.5 concentrations. Although the overall results from these 25 sites are within the annual ranges established by the EPA, they reveal substantial variations that reinforce the value of hyper-local sensing technologies as a powerful surveillance tool.

An effective online platform for crowd classification of coastal wetland loss

AbstractWetland loss is increasing rapidly, and there are gaps in public awareness of the problem. By crowdsourcing image analysis of wetland morphology, academic and government studies could be supplemented and accelerated while engaging and educating the public. The Land Loss Lookout (LLL) project crowdsourced mapping of wetland morphology associated with wetland loss and restoration. We demonstrate that volunteers can be trained relatively easily online to identify characteristic wetland morphologies, or patterns present on the landscape that suggest a specific geomorphological process. Results from a case study in coastal Louisiana revealed strong agreement among nonexpert and expert assessments who agreed on classifications at least 83% and at most 94% of the time. Participants self‐reported increased knowledge of wetland loss after participating in the project. Crowd‐identified morphologies are consistent with expectations, although more work is needed to directly compare LLL results with previous studies. This work provides a foundation for using crowd‐based wetland loss analysis to increase public awareness of the issue, and to contribute to land surveys or train machine learning algorithms.

Crowdsourcing Women’s Experiences of Space: Empowerment, (In)Visibility, and Exclusions – A Critical Reading of Safetipin Map

As a crowdsourced visual-based technique, participatory mapping has generally been lauded as an innovative method to identify place-based inequities and shape a more inclusive urban world. In the context of sexual violence in public spaces, there is a growing number of mapping initiatives that aim to advocate for spatial justice by involving women in collaborative map production. These initiatives train women to use geographic information system (GIS) to visualise women’s spatial knowledge grounded in their experience of navigating public spaces. Using Safetipin, an Indian-based mapping initiative, as a case study, I seek to challenge the simplistic reading that the crowdsourced map provides a transparent pathway to understanding spatial patterns of gender violence in urban space. I argue that this street-level mapping is a performative technique insofar as it materialises our experiences in different ways. Most importantly, it renders an imagination of space as operational—that is, calculable and malleable space that can be operated upon to prevent sexual violence. Significantly, as its visualisation of spatial distribution of safety reterritorialises public spaces, it reproduces other forms of socio-economic exclusion. This article thus argues for a reading of the crowdsourced map not as an inherently politically transformative project. Instead, it calls for an acknowledgment of hegemonic regimes of knowledge production that feminist activism like the Safetipin map is intimately bound up with and may help reproduce. Consequently, this involves attending to diverse regimes of (in)visibilities and marginalisation that such projects may stage.

Visual Mapping and Localization System Based on Compact Instance-Level Road Markings With Spatial Uncertainty

High-definition (HD) map is crucial for intelligent vehicles to perform high-level localization and navigation. To improve the availability and usability of HD map, it is meaningful to investigate crowd-sourced mapping solutions and low-cost map-aided localization schemes which don't rely on high-end sensors. In this letter, we propose a novel vision-based mapping and localization system, which could generate compact instance-level road maps automatically and provide high-availability map-aided localization. The spatial uncertainties of the map elements are taken into consideration by analyzing the inverse perspective mapping (IPM) model, which enables more flexible map usages in both mapping and localization phases of the system. Besides, a pose graph optimization framework is developed for accurate pose estimation by fusing global positioning (GNSS), local navigation (odometry) and map matching information together. Real-world experiments in urban environment were conducted to validate different phases of the system, including on-vehicle mapping, multi-source map merging and map-aided localization.

Geospatial Blockchain: review of decentralized geospatial data sharing systems

Abstract. Blockchain technologies are driving the internet infrastructures into a transformation from Web 2.0 to Web 3.0. This remodels the internet foundations from a centralized approach, where data is hosted by a single actor, to a decentralized one in which data is distributed among peers in a network. Thanks to blockchain technologies, the evolution from centralized to decentralized applications (dApps) eliminate single points of failure, data censorship and data tampering. This transformation is not only important in the financial sector, where the technology is more evolved, but also in geospatial crowdsourcing activities. The objective of this work is to perform a literature review of current blockchain technologies used for sharing and crowdsourcing activities involving geospatial data. This study serves as a starting point for future works where the main purpose is to develop a geospatial sharing blockchain platform. At the present, two platforms have been developed for this purpose, FOAM and D-GIS. The former is a fully deployed implementation whose objective is to create a crowdsourced map. The latter is a platform designed to share geospatial studies publicly, however, it is only developed conceptually and not deployed. Additional to these works, other blockchain data sharing examples exist and are reviewed in this study as a baseline for future developments in the geospatial area. The output of this research indicates that it is feasible to use blockchain technology for the development of a crowdsourcing geospatial data-sharing platform.

Undoing disaster colonialism: a pilot map of the pandemic's first wave in the Mapuche territories of Southern Chile

PurposeThe authors use media research and crowdsourced mapping to document how the first wave of the pandemic (April–August 2020) affected the Mapuche, focussing on seven categories of events: territorial control, spiritual defence, food sovereignty, traditional health practices, political violence, territorial needs and solidarity, and extractivist expansion.Design/methodology/approachResearch on the effects of the pandemic on the Mapuche and their territories is lacking; the few existing studies focus on death and infection rates but overlook how the pandemic interacts with ongoing processes of extractivism, state violence and community resistance. The authors’ pilot study addresses this gap through a map developed collaboratively by disaster scholars and Mapuche journalists.FindingsThe map provides a spatial and chronological overview of this period, highlighting the interconnections between the pandemic and neocolonialism. As examples, the authors focus on two phenomena: the creation of “health barriers” to ensure local territorial control and the state-supported expansion of extractive industries during the first months of the lockdown.Research limitations/implicationsThe authors intersperse our account of the project with reflections on its limitations and, specifically, on how colonial formations shape the research. Decolonising disaster studies and disaster risk reduction practice, the authors argue, is an ongoing process, bound to be flawed and incomplete but nevertheless an urgent pursuit.Originality/valueIn making this argument, the paper responds to the Disaster Studies Manifesto that inspires this special issue, taking up its invitation to scholars to be more reflexive about their research practice and to frame their investigations through grounded perspectives.

Tobacco Tracker: A New Tool to Support College Smoke and Tobacco Free Policies.

University community members are critical to the success of their smoke and tobacco free (STF) policies. The present study evaluates changes in social enforcement-related attitudes and behaviors following introduction of a new online Tobacco Tracker tool in two university settings. Campus wide surveys were administered to current students, faculty, and staff at two California public universities with 100% STF policies before (November 2018; N = 5078) and after (December 2019-January 2020; N = 4853) introduction of Tobacco Tracker in February 2019. Prospective surveillance reports over 12 months from Tobacco Tracker, a GIS tool for the campus community to report tobacco use and related litter that displays crowdsourced maps of hotspots, were analyzed. Outcomes included awareness and self-reported use of a tobacco reporting tool, readiness for policy social enforcement, an Intellectual Social Affective (ISA) Engagement scale, and environmental surveillance reports from Tobacco Tracker. In campus surveys, awareness of a tobacco reporting tool doubled (8.0%-16.9%, p < .0001), use of an online reporting tool tripled (1.1%-3.2%, p < .0001), and readiness to enforce the policy increased (p = .0008). ISA engagement did not change (p = .72). In Tobacco Tracker campus reports (N = 1163), active tobacco use was reported more frequently than tobacco-related litter. Tobacco Tracker is a promising tool for college communities to support STF policy. Introduction of Tobacco Tracker was associated with an increase in campus awareness and utilization of a reporting tool, readiness to enforce policy, and campus tobacco surveillance. Future research should determine how Tobacco Tracker may improve policy compliance. Tobacco Tracker is a promising tool for college communities to support smoke and tobacco free (STF) policy through active surveillance of smoking, vaping, and related litter on campus. Introduction of Tobacco Tracker was associated with changes in social enforcement-related attitudes and behaviors critical to realizing the preventive potential of STF policies. A crowdsourcing-based tool for monitoring tobacco use on college campuses can address a major barrier to social enforcement: discomfort confronting tobacco users. Further, it provides an alternative to punitive enforcement approaches and promises a sustainable solution to an infrastructure issue faced by many universities lacking resources to collect data on campus tobacco use and related litter.

Automatic Detection of Impervious Surfaces from Remotely Sensed Data Using Deep Learning

The large scale quantification of impervious surfaces provides valuable information for urban planning and socioeconomic development. Remote sensing and GIS techniques provide spatial and temporal information of land surfaces and are widely used for modeling impervious surfaces. Traditionally, these surfaces are predicted by computing statistical indices derived from different bands available in remotely sensed data, such as the Landsat and Sentinel series. More recently, researchers have explored classification and regression techniques to model impervious surfaces. However, these modeling efforts are limited due to lack of labeled data for training and evaluation. This in turn requires significant effort for manual labeling of data and visual interpretation of results. In this paper, we train deep learning neural networks using TensorFlow to predict impervious surfaces from Landsat 8 images. We used OpenStreetMap (OSM), a crowd-sourced map of the world with manually interpreted impervious surfaces such as roads and buildings, to programmatically generate large amounts of training and evaluation data, thus overcoming the need for manual labeling. We conducted extensive experimentation to compare the performance of different deep learning neural network architectures, optimization methods, and the set of features used to train the networks. The four model configurations labeled U-Net_SGD_Bands, U-Net_Adam_Bands, U-Net_Adam_Bands+SI, and VGG-19_Adam_Bands+SI resulted in a root mean squared error (RMSE) of 0.1582, 0.1358, 0.1375, and 0.1582 and an accuracy of 90.87%, 92.28%, 92.46%, and 90.11%, respectively, on the test set. The U-Net_Adam_Bands+SI Model, similar to the others mentioned above, is a deep learning neural network that combines Landsat 8 bands with statistical indices. This model performs the best among all four on statistical accuracy and produces qualitatively sharper and brighter predictions of impervious surfaces as compared to the other models.

Automated detecting and placing road objects from street-level images

Navigation services utilized by autonomous vehicles or ordinary users require the availability of detailed information about road-related objects and their geolocations, especially at road intersections. However, these road intersections are generally represented as point elements without detailed information, or are even not available in current versions of crowdsourced mapping databases including OpenStreetMap (OSM). This study proposes an approach to automatically detect road objects from street-level images and place them to correct locations according to urban rules. Our processing pipeline relies on two convolutional neural networks: the first one segments the images, while the second one detects and classifies the specific objects. Moreover, to locate the detected objects, we propose an attributed topological binary tree (ATBT) based on urban rules for each image in an image sequence to depict the coherent relations of topologies, attributes and semantics of the road objects. Then the ATBT is further matched with map features on OSM to determine the right placed location. The proposed method has been applied to a case study in Berlin, Germany. We validate the effectiveness of the proposed method on two object classes: traffic signs and traffic lights. Experimental results demonstrate that the proposed app roach provides promising results in terms of completeness and positional accuracy.

Geo-tagged environmental noise measurement with smartphones: Accuracy and perspectives of crowdsourced mapping

Environmental noise affects life and health within urban environments through interfering with sleep, rest, study and personal communication. Noise mapping is an important issue of local authorities but due to its requirements (staff, costs and frequency), the available data are limited or outdated. Our aim was to involve people with smartphones in the mapping process and to determine the accuracy of the measurements performed with these devices in a natural environment. The main questions were whether the measured data were dependent on the type of applied software and smartphones. We tested three software (Noise Watch, Noise Meter and Sound Level Meter) and 12 different smartphones. We evaluated the measurements with hypothesis testing and correlation analysis. Although the accuracy of smartphones was below the professional equipment, measurements can be conducted easily due to their availability; thus, a reliability analysis is important. We found that comparison between professional devices and smartphones in a laboratory was misleading as it lacks the environmental factors biasing the measurements. The best method to compare the measurements carried out with smartphones and professional Noise Meters was to use large number of measuring points in a heterogenic outdoor environment where the noise ranged from the low to large values. We revealed that both the applied software and smartphones have relevant effect on the measurements, and, although it is possible to use these devices for noise mapping, one should consider not to apply different software and smartphones. Accordingly, crowdsourcing is not a reliable data collection method because: (1) measurements should be supervised, (2) smartphones’ accuracy should be tested and (3) measurement circumstances should be the same. If any of these requirements are violated, the quality of the resulting maps can be questioned.

Any Portal in a Storm? Collaborative and crowdsourced maps in response to Typhoon Yolanda/Haiyan, Philippines

AbstractThe promises of crowdsourcing volunteered geographic information (VGI) for providing timely information about crises were recognized at least a decade ago. While cartographers and developers hone the accuracy of maps and data, social scientists critique these technologies through various theoretical lenses: in terms of knowledge politics of digital humanitarianism; as tools of neoliberal governance; and as examples of datification supporting automated or remote government. Amidst all these claims, it is time to return to the maps themselves, as empirical examples, considering the information they actually provide. This paper examines crowdsourced and collaborative maps from late 2013 following Typhoon Yolanda/Haiyan in the Philippines. Various humanitarian, mapping, and media organizations produced maps in response to the typhoon. Close qualitative analysis of map content queries what these maps reveal about the disaster and whether the maps really produce the information that proponents claim. Analysis of data curated in each map reveals that much of the situational information being mapped is already available elsewhere and that few new ground truths have emerged through these projects. By demonstrating the limitations of the information mediated in these maps, the findings have practical and policy implications for disaster practitioners and digital volunteers intending to help disaster response.

A weighting system to build physical layer measurements maps by crowdsourcing data from smartphones

&lt;p&gt;Mobile devices can sense different types of radio signals. For example, broadcast signals. These broadcasted signals allow the device to establish a connection to the access point broadcasting it. Moreover, mobile devices can record different physical layer measurements. These measurements are an indication of the service quality at the point they were collected. These measurements data can be aggregated to form physical layer measurement maps. These maps are useful for several applications such as location fixing, navigation, access control, and evaluating network coverage and performance. Crowdsourcing can be an efficient way to create such maps. However, users in a crowdsourcing application tend to have different devices with different capabilities, which might impact the overall accuracy of the generated maps. In this paper, we propose a method to build physical layer measurements maps by crowdsourcing physical layer measurements, GPS locations, from participating mobile devices. The proposed system gives different weights to each data point provided by the participating devices based on the data source’s trustworthiness. Our tests showed that the different models of mobile devices return GPS location with different location accuracies. Consequently, when building the physical layer measurements maps our algorithm assigns a higher weight to data points coming from devices with higher GPS location accuracy. This allows accommodating a wide range of mobile devices with different capabilities in crowdsourcing applications. An experiment and a simulation were performed to test the proposed method. The results showed improvement in crowdsourced map accuracy when the proposed method is implemented.&lt;/p&gt;