3D Camouflaging Object using RGB-D Sensors
This addresses the problem of visual concealment in augmented reality or surveillance applications, but it appears incremental as it builds on existing camouflage and sensor-based tracking methods.
The paper tackles the problem of concealing an object behind a display in a 3D environment by proposing an optical camouflage system that uses RGB-D sensors to track an observer's eyes and estimate shadow shapes on background objects, enabling effective concealment.
This paper proposes a new optical camouflage system that uses RGB-D cameras, for acquiring point cloud of background scene, and tracking observers eyes. This system enables a user to conceal an object located behind a display that surrounded by 3D objects. If we considered here the tracked point of observer s eyes is a light source, the system will work on estimating shadow shape of the display device that falls on the objects in background. The system uses the 3d observer s eyes and the locations of display corners to predict their shadow points which have nearest neighbors in the constructed point cloud of background scene.