EstimatestheDistanceWalked创新.PDFVIP

AutoGait: A Mobile Platform that Accurately Estimates the Distance Walked † ‡ Dae-Ki Cho, Min Mun, Uichin Lee , William J. Kaiser , Mario Gerla UCLA Computer Science Department, †Alcatel-Lucent Bell Labs, ‡UCLA Electrical Engineering Department {dkcho, bobbymun, gerla}@ † uichin.lee@ ‡ kaiser@ Abstract—AutoGait is a mobile platform that autonomously misalignment [8], the major problem is that these systems discovers a user’s walking profile and accurately estimates the assume a constant stride length while estimating the distance distance walked. The discovery is made by utilizing the GPS in walked. Most pedometer systems ask the user to manually the user’s mobile device when the user is walking outdoors. This profile can then be used both indoors and outdoors to estimate the calibrate the average stride length; e.g., after walking a known distance walked. To model the person’s walking profile, we take distance, a user finds the average stride length by dividing advantage of the fact that a linear relationship exists between step the distance by the measured step count. This makes the frequency and stride length, which is unique to individuals and distance estimation severely biased towards dominant walking applies to everyone regardless of age. Autonomous calibration patterns. Considering the fact that human walking patterns are invisible to users allows the system to maintain a high level of accuracy under changing conditions. AutoGait can be integrated not uniform and the stride length is variable, such manual into any pedometer or