Digital maps have become a part of our daily life with a number of commercialand free map services. These services have still a huge potential forenhancement with rich semantic information to support a large class of mappingapplications. In this paper, we present Map++, a system that leverages standardcell-phone sensors in a crowdsensing approach to automatically enrich digitalmaps with different road semantics like tunnels, bumps, bridges, footbridges,crosswalks, road capacity, among others. Our analysis shows that cell-phonessensors with humans in vehicles or walking get affected by the different roadfeatures, which can be mined to extend the features of both free and commercialmapping services. We present the design and implementation of Map++ andevaluate it in a large city. Our evaluation shows that we can detect thedifferent semantics accurately with at most 3% false positive rate and 6% falsenegative rate for both vehicle and pedestrian-based features. Moreover, we showthat Map++ has a small energy footprint on the cell-phones, highlighting itspromise as a ubiquitous digital maps enriching service.
展开▼