Wide-baseline multi-camera calibration from a room filled with people

When a precise 3D reconstruction of an object or person is attempted, one typically starts from a multi-view setup with cameras spread out all around the investigation area. A triangulation of the matching joints is then performed to retrieve the 3D coordinates. However, calibrating such a setup typically requires dedicated equipment and elaborated test procedures. In this paper, we will demonstrate a calibration method based only on the detection of one or more people walking through the field of view. This, in effect, allows the calibration to happen simultaneously with the measurements being taken, which is practical when dealing with uncontrolled environments. We will also show that this calibration procedure is more accurate than a typical incremental calibration procedure using a chessboard. Conceptually, the novelty that we propose is in using semantic information (e.g. the position of the left shoulder) rather than appearance-based information to drive the calibration, as this type of information is less viewpoint dependent. Note that here we use human pose keypoints but for larger outdoor scenes, car keypoints could be used as well.