Video object trajectory perturbation based data hiding satisfying statistical and perceptual invisibility

A new semantic steganographic algorithm for hiding data in the motion trajectories of Video Objects (VOs) is presented. First, a set of primitives (objects bounding-box coordinates and its centroid) are used to dene a VO. The centroid of VO is tracked in each frame and its coordinate is stored in a trajectory vector. The proposed algorithm embeds data in the VO object trajectory by presenting a relationship between the hidden data and the trajectory data in the form of a motion drift or perturbation. The perturbation introduced by the embedding algorithm is implemented by motion compensating the pixels in the VO bounding box. Assessment of the steganographic algorithm is done by both subjective judgments based on the perceived quality of the perturbed video sequence and by some commonly used statistical steganalysis metrics. Both subjective assessments and statistical measures indicate visual and statistical invisibility.