Understanding Urban Land Use through the Visualization of Points of Interest



Semantic data regarding points of interest in urban areas are hard to visualize. Due to
the high number of points and categories they belong, as well as the associated textual
information, maps become heavily cluttered and hard to read. Using traditional visualization techniques (e.g. dot distribution maps, typographic maps) partially solve this problem. Although, these techniques address different issues of the problem, their combination is hard and typically results in an efficient visualization. In our approach, we present a method to represent clusters of points of interest as shapes, which is based on vacuum package metaphor. The calculated shapes characterize sets of points and allow their use as containers for textual information. Additionally, we present a strategy for placing text onto polygons. The suggested method can be used in interactive visual exploration of semantic data distributed in space, and for creating maps with similar characteristics of dot distribution maps, but using shapes instead of points.


Information Visualization, Land-Use Analysis, Information Extraction


Visualization; Ambient Intelligence; Information Extraction

Related Project

InfoCrowds - Social Web Information Retrieval for crowds mobility management


Fourth Workshop on Vision and Language (VL'15), part of 2015 Conference on Empirical Methods for Natural Language Processing (EMNLP15), September 2015

PDF File


Cited by

Year 2018 : 2 citations

 Cheng, T., & Shen, J. (2018). Grouping people in cities: From space-time to place-time based profiling. In Human Dynamics Research in Smart and Connected Communities (pp. 181-201). Springer, Cham.

 da Costa Rainho, F., & Bernardino, J. (2018, June). Web GIS: A new system to store spatial data using GeoJSON in MongoDB. In 2018 13th Iberian Conference on Information Systems and Technologies (CISTI) (pp. 1-6). IEEE.