Metric Pose Estimation for Human-Machine Interaction Using Monocular Vision
This addresses the need for automation technologies that consider both humans and machines in production settings, but it appears incremental as it builds on existing pose estimation methods.
The paper tackles the problem of detecting human-machine interactions in collaborative robotics by predicting poses of humans and robots from a single wide-angle color image and lifting them to metric 3D space, demonstrating advantages in three use cases.
The rapid growth of collaborative robotics in production requires new automation technologies that take human and machine equally into account. In this work, we describe a monocular camera based system to detect human-machine interactions from a bird's-eye perspective. Our system predicts poses of humans and robots from a single wide-angle color image. Even though our approach works on 2D color input, we lift the majority of detections to a metric 3D space. Our system merges pose information with predefined virtual sensors to coordinate human-machine interactions. We demonstrate the advantages of our system in three use cases.