Automatically recognizing places of interest from unreliable GPS data using spatio-temporal density estimation and line intersections

作者：Bhattacharya Tanusri^*; Kulik Lars; Bailey James

来源：Pervasive and Mobile Computing, 2015, 19: 86-107.

DOI：10.1016/j.pmcj.2014.08.003

• Indoor GPS
• Urban canyons
• Trajectory mining
• Significant places

Stay points are important for recognizing significant places from a mobile user's GPS trajectory. Such places are often located indoors and in urban canyons, where GPS is unreliable. Consequently, mapping a user's stay point to a Place of Interest (POI) using only GPS data is particularly challenging. Our novel algorithm employs both spatio-temporaldensity estimation and line count inference to predict and rank a user's POI(s) at building level accuracy from noisy time-annotated GPS data points. An experimental study demonstrates the superiority of our algorithm against several baseline approaches with a recall of 96.5% for the top 5 retrieved locations.

• 出版日期2015-5