Abstract
Industrial exoskeletons (a.k.a. wearable robots) have been developed to reduce musculoskeletal fatigue and work injuries. Human joint kinematics and human-robot alignment are important measurements in understanding the effects of industrial exoskeletons. Recently, markerless pose estimation systems based on monocular color (red, green, blue-RGB) and depth cameras are being used to estimate human joint positions. This study analyzes the performance of monocular markerless pose estimation systems on human skeletal joint estimation while wearing exoskeletons. Two pose estimation systems producing RGB and depth images from ten viewpoints are evaluated for one subject in 14 industrial poses. The experiment was repeated for three different types of exoskeletons on the same subject. An optical tracking system (OTS) was used as a reference system. The image acceptance rate was 56% for the RGB, 22% for the depth, and 78% for the OTS pose estimation system. The key sources of pose estimation error were the occlusions from the exoskeletons, industrial poses, and viewpoints. The reference system showed decreased performance when the optical markers were occluded by the exoskeleton or when the markers' position shifted with the exoskeleton. This study performs a systematic comparison of two types of monocular markerless pose estimation systems and an optical tracking system, as well as a proposed metric, based on a tracking quality ratio, to assess whether a skeletal joint estimation would be acceptable for human kinematics analysis in exoskeleton studies.