Augmented Reality for Privacy-Sensitive Visual Monitoring

The paper presents a method for video anonymization and replacing real human silhouettes with virtual 3D figures rendered on the screen. Video stream is processed to detect and to track objects, whereas anonymization stage employs fast blurring method. Substitute 3D figures are animated accordingly to behavior of detected persons. Their location, movement speed, direction, and person height are taken into account during the animation and rendering phases. This approach requires a calibrated camera, and utilizes results of visual object tracking. In the paper a procedure for transforming objects visual features and bounding boxes into a script for animated figures is presented. This approach is validated subjectively, by assessing a correspondence between real image and the augmented one. Conclusions and future work perspectives are provided.