Automatic Synchronization of Markerless Video and Wearable Sensors for Walking Assessment

Abstract

As walking assessment is commonly done through visual inspection, it is beneficial to make joint angle information available to the clinicians for better assessment. The main challenge is that the video camera and inertial sensor are usually two separate systems, and the recordings are hard to be initialized at the same time manually. This creates a problem that the inertial sensor data is not temporally synchronized with the video camera. This paper proposes a method to synchronize the video and sensor data by detecting and matching the maximum backward swings of the leg. The proposed method is validated by blinking LED and transmitting LED flag to the computer at the same time. The synchronization error of the proposed method is low at about 0±2 frames compared to the validation method.

Comparison of Methods for Determining Activity from Physical Movements

“…Activity detection studies have been developed with the help of the inertial sensor with less constraint than the visual systems [2]. Some studies have compared the video cameras with inertial sensor data [3]. Studies focused on the detection of various human activity, especially daily life monitoring for pedestrian status with inertial sensors [4], personal biometric signature and navigation [5], detection of fall conditions [6], rehabilitation and physical therapy [7], detect the type of transportation [8].…”