Autonomous Footstep Counting and Traveled Distance Calculation by Mobile Devices Incorporating Camera and Accelerometer Data

Step counting is being increasingly used as an activity-level measure, which is evidenced by different types of widely available commercial wristbands, pedometers, and applications (apps) developed for smart phones and smart watches. In addition to measuring daily activity levels and keeping logs for health monitoring, an accurate and reliable count of footsteps can be used for motion estimation, calculating traveled distance and indoor navigation. Yet, most of the available devices and approaches for step counting rely only on accelerometer data, and thus are prone to over-counting. Moreover, most existing devices calculate the traveled distance based on the counted number of steps and a preset stride length, or rely on GPS data, which might not be suitable for GPS-denied areas and indoor environments. In this paper, we present an autonomous and robust method for counting footsteps, and tracking and calculating stride length by using both accelerometer and camera data from smart phones or Google™ glass. To provide higher precision, instead of using a preset stride length, the proposed method calculates the distance traveled with each step by using the camera data. Experiments are performed with different subjects, either holding a smart phone, or carrying it in a holder around waist, or wearing a Google™ glass. The proposed method is compared with the commercially available accelerometer-based step counter apps. The results show that the proposed method provides a significant increase in accuracy, and has the lowest average error rate both in number of steps taken and the distance traveled.