Traffic trajectories collected from GPS-enabled mobile devices or vehicles are widely used in urban planning, traffic management, and location based services. Their performance often relies on having dense trajectories. However, due to the power and bandwidth limitation on these devices, collecting dense trajectory is too costly on a large scale. We show that by exploiting structural regularity in large trajectory data, the complete geometry of trajectories can be inferred from sparse GPS samples without information about the underlying road network - a process called trajectory completion. In this paper, we present a knowledge-based approach for completing traffic trajectories. Our method extracts a network of road junctions and estimates traffic flows across junctions. GPS samples within each flow cluster are then used to achieve fine-level completion of individual trajectories. Finally, we demonstrate that our method is effective for trajectory completion on both synthesized and real traffic trajectories. On average 72.7% of real trajectories with sampling rate of 60 seconds/sample are completed without map information. Comparing to map matching, over 89% of points on completed trajectories are within 15 meters from the map matched path.
{"title":"Knowledge-based trajectory completion from sparse GPS samples","authors":"Yongni Li, Yangyan Li, D. Gunopulos, L. Guibas","doi":"10.1145/2996913.2996924","DOIUrl":"https://doi.org/10.1145/2996913.2996924","url":null,"abstract":"Traffic trajectories collected from GPS-enabled mobile devices or vehicles are widely used in urban planning, traffic management, and location based services. Their performance often relies on having dense trajectories. However, due to the power and bandwidth limitation on these devices, collecting dense trajectory is too costly on a large scale. We show that by exploiting structural regularity in large trajectory data, the complete geometry of trajectories can be inferred from sparse GPS samples without information about the underlying road network - a process called trajectory completion. In this paper, we present a knowledge-based approach for completing traffic trajectories. Our method extracts a network of road junctions and estimates traffic flows across junctions. GPS samples within each flow cluster are then used to achieve fine-level completion of individual trajectories. Finally, we demonstrate that our method is effective for trajectory completion on both synthesized and real traffic trajectories. On average 72.7% of real trajectories with sampling rate of 60 seconds/sample are completed without map information. Comparing to map matching, over 89% of points on completed trajectories are within 15 meters from the map matched path.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73051988","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}
B. Budig, Thomas C. van Dijk, F. Feitsch, M. Arteaga
Over the course of three years, the New York Public Library has run a crowdsourcing project to extract polygonal representation of the building footprints from insurance atlases of the 19th and early-20th century. As is common in crowd-sourcing projects, the overall problem was decomposed into small user tasks and each task was given to multiple users. In the case of polygons representing building footprints, it is unclear how best to integrate the answers into a majority vote: given a set of polygons ostensibly describing the same footprint, what is the consensus? We discuss desirable properties of such a "consensus polygon" and arrive at an efficient algorithm. We have manually evaluated the algorithm on approximately 3,000 polygons corresponding to 200 footprints and observe that our algorithmic consensus polygons are correct for 96% of the footprints whereas only 85% of the (input) crowd polygons are correct.
{"title":"Polygon consensus: smart crowdsourcing for extracting building footprints from historical maps","authors":"B. Budig, Thomas C. van Dijk, F. Feitsch, M. Arteaga","doi":"10.1145/2996913.2996951","DOIUrl":"https://doi.org/10.1145/2996913.2996951","url":null,"abstract":"Over the course of three years, the New York Public Library has run a crowdsourcing project to extract polygonal representation of the building footprints from insurance atlases of the 19th and early-20th century. As is common in crowd-sourcing projects, the overall problem was decomposed into small user tasks and each task was given to multiple users. In the case of polygons representing building footprints, it is unclear how best to integrate the answers into a majority vote: given a set of polygons ostensibly describing the same footprint, what is the consensus? We discuss desirable properties of such a \"consensus polygon\" and arrive at an efficient algorithm. We have manually evaluated the algorithm on approximately 3,000 polygons corresponding to 200 footprints and observe that our algorithmic consensus polygons are correct for 96% of the footprints whereas only 85% of the (input) crowd polygons are correct.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79402270","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}
Bo Xu, Tiffany Barkley, Andrew P. Lewis, Jane Macfarlane, D. Pietrobon, Matei Stroila
In this paper we present our experience on detecting and classifying traffic jams in real time from probe data. We classify traffic jams at two levels. At a higher level, we classify traffic jams into recurring and non-recurring jams. Then at a lower level we identify accidents out of non-recurring jams based on features that characterize upstream and downstream traffic patterns. Accidents are highly unpredictable and usually create heavy and long lasting congestion, and therefore are particularly worth detecting. We discuss the challenges of detecting accidents in real time as well as our approaches and results.
{"title":"Real-time detection and classification of traffic jams from probe data","authors":"Bo Xu, Tiffany Barkley, Andrew P. Lewis, Jane Macfarlane, D. Pietrobon, Matei Stroila","doi":"10.1145/2996913.2996988","DOIUrl":"https://doi.org/10.1145/2996913.2996988","url":null,"abstract":"In this paper we present our experience on detecting and classifying traffic jams in real time from probe data. We classify traffic jams at two levels. At a higher level, we classify traffic jams into recurring and non-recurring jams. Then at a lower level we identify accidents out of non-recurring jams based on features that characterize upstream and downstream traffic patterns. Accidents are highly unpredictable and usually create heavy and long lasting congestion, and therefore are particularly worth detecting. We discuss the challenges of detecting accidents in real time as well as our approaches and results.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74770665","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}
Dynamic time warping (DTW) is a widely used curve similarity measure. We present a simple and efficient (1 + ε)- approximation algorithm for DTW between a pair of point sequences, say, P and Q, each of which is sampled from a curve. We prove that the running time of the algorithm is O([EQUATION]n log σ) for a pair of k-packed curves with a total of n points, assuming that the spreads of P and Q are bounded by σ. The spread of a point set is the ratio of the maximum to the minimum pairwise distance, and a curve is called K- packed if the length of its intersection with any disk of radius r is at most Kr. Although an algorithm with similar asymptotic time complexity was presented in [1], our algorithm is considerably simpler and more efficient in practice. We have implemented our algorithm. Our experiments on both synthetic and real-world data sets show that it is an order of magnitude faster than the standard exact DP algorithm on point sequences of length 5, 000 or more while keeping the approximation error within 5--10%. We demonstrate the efficacy of our algorithm by using it in two applications - computing the k most similar trajectories to a query trajectory, and running the iterative closest point method for a pair of trajectories. We show that we can achieve 8--12 times speedup using our algorithm as a subroutine in these applications, without compromising much in accuracy.
{"title":"A simple efficient approximation algorithm for dynamic time warping","authors":"Rex Ying, Jiangwei Pan, K. Fox, P. Agarwal","doi":"10.1145/2996913.2996954","DOIUrl":"https://doi.org/10.1145/2996913.2996954","url":null,"abstract":"Dynamic time warping (DTW) is a widely used curve similarity measure. We present a simple and efficient (1 + ε)- approximation algorithm for DTW between a pair of point sequences, say, P and Q, each of which is sampled from a curve. We prove that the running time of the algorithm is O([EQUATION]n log σ) for a pair of k-packed curves with a total of n points, assuming that the spreads of P and Q are bounded by σ. The spread of a point set is the ratio of the maximum to the minimum pairwise distance, and a curve is called K- packed if the length of its intersection with any disk of radius r is at most Kr. Although an algorithm with similar asymptotic time complexity was presented in [1], our algorithm is considerably simpler and more efficient in practice. We have implemented our algorithm. Our experiments on both synthetic and real-world data sets show that it is an order of magnitude faster than the standard exact DP algorithm on point sequences of length 5, 000 or more while keeping the approximation error within 5--10%. We demonstrate the efficacy of our algorithm by using it in two applications - computing the k most similar trajectories to a query trajectory, and running the iterative closest point method for a pair of trajectories. We show that we can achieve 8--12 times speedup using our algorithm as a subroutine in these applications, without compromising much in accuracy.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75636172","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}
Twitter is one of the most popular social media platforms where people can share their opinions, thoughts, interests, and whereabouts. In this work, we propose a Local Event Discovery and Summarization (LEDS) framework to detect local events from Twitter. Many existing algorithms for event detection focus on larger-scale events and are not sensitive to smaller-scale local events. Most of the local events detected by these methods are major events such as important sports, shows, or large natural disasters. In this paper, we propose the LEDS framework to detect both larger and smaller events. LEDS contains three key steps: 1) Detecting possible event related terms by monitoring abnormal distribution in different locations and times; 2) Clustering tweets based on their key terms, time, and location distribution; and 3) Extracting descriptions including time, location, and key sentences of local events from clusters. The framework is evaluated on a real world Twitter dataset with more than 60 million tweets. The results show that compared with previous work, LEDS can detect smaller-scale and greater variety of local events. More than 43 percent of detected local events do not have an official organizer, cannot be seen on news media, and only attract the attention from a small group of people.
{"title":"LEDS","authors":"Zhi Liu, Yan Huang, Joshua R. Trampier","doi":"10.1145/2996913.2996928","DOIUrl":"https://doi.org/10.1145/2996913.2996928","url":null,"abstract":"Twitter is one of the most popular social media platforms where people can share their opinions, thoughts, interests, and whereabouts. In this work, we propose a Local Event Discovery and Summarization (LEDS) framework to detect local events from Twitter. Many existing algorithms for event detection focus on larger-scale events and are not sensitive to smaller-scale local events. Most of the local events detected by these methods are major events such as important sports, shows, or large natural disasters. In this paper, we propose the LEDS framework to detect both larger and smaller events. LEDS contains three key steps: 1) Detecting possible event related terms by monitoring abnormal distribution in different locations and times; 2) Clustering tweets based on their key terms, time, and location distribution; and 3) Extracting descriptions including time, location, and key sentences of local events from clusters. The framework is evaluated on a real world Twitter dataset with more than 60 million tweets. The results show that compared with previous work, LEDS can detect smaller-scale and greater variety of local events. More than 43 percent of detected local events do not have an official organizer, cannot be seen on news media, and only attract the attention from a small group of people.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76081045","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}
S. F. Boubrahimi, Berkay Aydin, Dustin J. Kempton, R. Angryk
One of the main strengths of Geographical Information Systems (GIS) is the analysis of spatial and attributive data. Spatiotemporal interpolation techniques allow the expansion of the collected data to the sites where no samples are available. In the context of GIS, the data, be it interpolated or collected, are visual in nature and hard to understand in raw forms. Visualization of complex evolving region trajectories is often times used as an aid to better understand the data and its underlying patterns. In this work, we created SOLEV, a solar event video generation framework that integrates multiple data sources of solar images. This is the first framework of this kind that not only visualizes spatial solar event boundaries, but also the tracked and interpolated spatiotemporal trajectories they form over time.
{"title":"SOLEV: a video generation framework for solar events from mixed data sources (demo paper)","authors":"S. F. Boubrahimi, Berkay Aydin, Dustin J. Kempton, R. Angryk","doi":"10.1145/2996913.2996963","DOIUrl":"https://doi.org/10.1145/2996913.2996963","url":null,"abstract":"One of the main strengths of Geographical Information Systems (GIS) is the analysis of spatial and attributive data. Spatiotemporal interpolation techniques allow the expansion of the collected data to the sites where no samples are available. In the context of GIS, the data, be it interpolated or collected, are visual in nature and hard to understand in raw forms. Visualization of complex evolving region trajectories is often times used as an aid to better understand the data and its underlying patterns. In this work, we created SOLEV, a solar event video generation framework that integrates multiple data sources of solar images. This is the first framework of this kind that not only visualizes spatial solar event boundaries, but also the tracked and interpolated spatiotemporal trajectories they form over time.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90798279","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}
M. Asghari, Dingxiong Deng, C. Shahabi, Ugur Demiryurek, Yaguang Li
Real-time ride-sharing, which enables on-the-fly matching between riders and drivers (even en-route), is an important problem due to its environmental and societal benefits. With the emergence of many ride-sharing platforms (e.g., Uber and Lyft), the design of a scalable framework to match riders and drivers based on their various constraints while maximizing the overall profit of the platform becomes a distinguishing business strategy. A key challenge of such framework is to satisfy both types of the users in the system, e.g., reducing both riders' and drivers' travel distances. However, the majority of the existing approaches focus only on minimizing the total travel distance of drivers which is not always equivalent to shorter trips for riders. Hence, we propose a fair pricing model that simultaneously satisfies both the riders' and drivers' constraints and desires (formulated as their profiles). In particular, we introduce a distributed auction-based framework where each driver's mobile app automatically bids on every nearby request taking into account many factors such as both the driver's and the riders' profiles, their itineraries, the pricing model, and the current number of riders in the vehicle. Subsequently, the server determines the highest bidder and assigns the rider to that driver. We show that this framework is scalable and efficient, processing hundreds of tasks per second in the presence of thousands of drivers. We compare our framework with the state-of-the-art approaches in both industry and academia through experiments on New York City's taxi dataset. Our results show that our framework can simultaneously match more riders to drivers (i.e., higher service rate) by engaging the drivers more effectively. Moreover, our frame-work schedules shorter trips for riders (i.e., better service quality). Finally, as a consequence of higher service rate and shorter trips, our framework increases the overall profit of the ride-sharing platforms.
{"title":"Price-aware real-time ride-sharing at scale: an auction-based approach","authors":"M. Asghari, Dingxiong Deng, C. Shahabi, Ugur Demiryurek, Yaguang Li","doi":"10.1145/2996913.2996974","DOIUrl":"https://doi.org/10.1145/2996913.2996974","url":null,"abstract":"Real-time ride-sharing, which enables on-the-fly matching between riders and drivers (even en-route), is an important problem due to its environmental and societal benefits. With the emergence of many ride-sharing platforms (e.g., Uber and Lyft), the design of a scalable framework to match riders and drivers based on their various constraints while maximizing the overall profit of the platform becomes a distinguishing business strategy. A key challenge of such framework is to satisfy both types of the users in the system, e.g., reducing both riders' and drivers' travel distances. However, the majority of the existing approaches focus only on minimizing the total travel distance of drivers which is not always equivalent to shorter trips for riders. Hence, we propose a fair pricing model that simultaneously satisfies both the riders' and drivers' constraints and desires (formulated as their profiles). In particular, we introduce a distributed auction-based framework where each driver's mobile app automatically bids on every nearby request taking into account many factors such as both the driver's and the riders' profiles, their itineraries, the pricing model, and the current number of riders in the vehicle. Subsequently, the server determines the highest bidder and assigns the rider to that driver. We show that this framework is scalable and efficient, processing hundreds of tasks per second in the presence of thousands of drivers. We compare our framework with the state-of-the-art approaches in both industry and academia through experiments on New York City's taxi dataset. Our results show that our framework can simultaneously match more riders to drivers (i.e., higher service rate) by engaging the drivers more effectively. Moreover, our frame-work schedules shorter trips for riders (i.e., better service quality). Finally, as a consequence of higher service rate and shorter trips, our framework increases the overall profit of the ride-sharing platforms.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83949120","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}
Today's 'Big' spatial computing and analytics are largely processed in-memory. Still, evaluation in prominent spatial query engines is neither fully optimized for modern-class platforms nor taking full advantage of compilation (i.e., generating low-level query code). Query compilation has been rapidly rising inside in-memory relational database management systems (RDBMSs) achieving remarkable speedups; how can we bring similar benefits to spatial query engines? In this research, we bring in proven Programming Languages (PL) approaches e.g., partial evaluation, generative programming, etc. and leverage the power of modern hardware to extend query compilation inside spatial query engines. We envision a fully compiled spatial query engine that is efficient and feasible to implement in a high-level language. We describe LB2-Spatial; a prototype for a fully compiled spatial query engine that employs generative and multi-stage programming to realize query compilation. Furthermore, we discuss challenges, and conduct a preliminary experiment to highlight potential gains of compilation. Finally, we sketch potential avenues for supporting spatial query compilation in Postgres/ PostGIS; a traditional RDBMS and Spark/ Spark SQL; a main-memory cluster computing framework.
{"title":"On supporting compilation in spatial query engines: (vision paper)","authors":"Ruby Y. Tahboub, Tiark Rompf","doi":"10.1145/2996913.2996945","DOIUrl":"https://doi.org/10.1145/2996913.2996945","url":null,"abstract":"Today's 'Big' spatial computing and analytics are largely processed in-memory. Still, evaluation in prominent spatial query engines is neither fully optimized for modern-class platforms nor taking full advantage of compilation (i.e., generating low-level query code). Query compilation has been rapidly rising inside in-memory relational database management systems (RDBMSs) achieving remarkable speedups; how can we bring similar benefits to spatial query engines? In this research, we bring in proven Programming Languages (PL) approaches e.g., partial evaluation, generative programming, etc. and leverage the power of modern hardware to extend query compilation inside spatial query engines. We envision a fully compiled spatial query engine that is efficient and feasible to implement in a high-level language. We describe LB2-Spatial; a prototype for a fully compiled spatial query engine that employs generative and multi-stage programming to realize query compilation. Furthermore, we discuss challenges, and conduct a preliminary experiment to highlight potential gains of compilation. Finally, we sketch potential avenues for supporting spatial query compilation in Postgres/ PostGIS; a traditional RDBMS and Spark/ Spark SQL; a main-memory cluster computing framework.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81019350","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}
Dong Xie, Feifei Li, Bin Yao, Gefei Li, Zhongpu Chen, Liang Zhou, M. Guo
We present the Simba (Spatial In-Memory Big data Analytics) system, which offers scalable and efficient in-memory spatial query processing and analytics for big spatial data. Simba natively extends the Spark SQL engine to support rich spatial queries and analytics through both SQL and DataFrame API. It enables the construction of indexes over RDDs inside the engine in order to work with big spatial data and complex spatial operations. Simba also comes with an effective query optimizer, which leverages its indexes and novel spatial-aware optimizations, to achieve both low latency and high throughput in big spatial data analysis. This demonstration proposal describes key ideas in the design of Simba, and presents a demonstration plan.
{"title":"Simba: spatial in-memory big data analysis","authors":"Dong Xie, Feifei Li, Bin Yao, Gefei Li, Zhongpu Chen, Liang Zhou, M. Guo","doi":"10.1145/2996913.2996935","DOIUrl":"https://doi.org/10.1145/2996913.2996935","url":null,"abstract":"We present the Simba (Spatial In-Memory Big data Analytics) system, which offers scalable and efficient in-memory spatial query processing and analytics for big spatial data. Simba natively extends the Spark SQL engine to support rich spatial queries and analytics through both SQL and DataFrame API. It enables the construction of indexes over RDDs inside the engine in order to work with big spatial data and complex spatial operations. Simba also comes with an effective query optimizer, which leverages its indexes and novel spatial-aware optimizations, to achieve both low latency and high throughput in big spatial data analysis. This demonstration proposal describes key ideas in the design of Simba, and presents a demonstration plan.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89320748","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}
Geotagged imagery, from satellite, aerial, and ground-level cameras, provides a rich record of how the appearance of scenes and objects differ across the globe. Modern web- based mapping software makes it easy to see how different places around the world look, both from satellite and ground-level views. Unfortunately, interfaces for exploring how the appearance of objects depend on geographic location are quite limited. In this work, we focus on a particularly common object, the human face, and propose learning generative models that relate facial appearance and geographic location. We train these models using a novel dataset of geotagged face imagery we constructed for this task. We present qualitative and quantitative results that demonstrate that these models capture meaningful trends in appearance. We also describe a framework for constructing a web-based visualization that captures the geospatial distribution of human facial appearance.
{"title":"Who goes there?: approaches to mapping facial appearance diversity","authors":"Zachary Bessinger, C. Stauffer, Nathan Jacobs","doi":"10.1145/2996913.2996997","DOIUrl":"https://doi.org/10.1145/2996913.2996997","url":null,"abstract":"Geotagged imagery, from satellite, aerial, and ground-level cameras, provides a rich record of how the appearance of scenes and objects differ across the globe. Modern web- based mapping software makes it easy to see how different places around the world look, both from satellite and ground-level views. Unfortunately, interfaces for exploring how the appearance of objects depend on geographic location are quite limited. In this work, we focus on a particularly common object, the human face, and propose learning generative models that relate facial appearance and geographic location. We train these models using a novel dataset of geotagged face imagery we constructed for this task. We present qualitative and quantitative results that demonstrate that these models capture meaningful trends in appearance. We also describe a framework for constructing a web-based visualization that captures the geospatial distribution of human facial appearance.","PeriodicalId":20525,"journal":{"name":"Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89375012","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：