.png){kind=icon}
.png){kind=icon}
Return
Automatic Rich Map Semantics Identification Through Smartphone-Based Crowd-Sensing
.png){kind=icon}
PRE
AI
DOI：10.1109/TMC.2016.2645150.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Digital maps have become a part of our daily lives with a growing number of commercial and free map services. However, these services still have a huge potential for enhancement with rich semantic information to support a large class of mapping applications. In this paper, we present Map++, a system that leverages commodity off-the-shelf smartphones in a crowd-sensing approach to automatically enrich digital maps with different road semantics like tunnels, bumps, bridges, footbridges, crosswalks, road capacity, among others. Our analysis shows that the smartphones sensors, whether with a user riding a vehicle or walking, get affected by the different road features which can be mined to extend the features of both free and commercial mapping services. Map++ leverages these detected features and employs a probabilistic framework that can handle the heterogeneity and uncertainty in the crowd-sensed data to update the digital maps. We present the design and implementation of Map++ and evaluate it in four cities. Our evaluation shows that we can detect different map features accurately with 4 percent false positive and 8 percent false negative rates for in-vehicle traces, and 3 percent false positive and 4 percent false negative rates for pedestrian traces. Moreover, we show that Map++ has a small energy footprint on the cell-phones, highlighting its promise as a ubiquitous digital maps enriching service.
Keywords:
Mobile computing
smartphone sensing
road maps
probabilistic map inference
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.2
Papers:
5.6K
Citations:
1.8W