Abstract: A system and method are provided for selecting frames of a compressed video stream that may be used for client-side watermarking. In general, a content source evaluates a number of Intra-Frames (I-Frames) in the compressed video stream using a sample watermark that is similar to actual watermarks that may be used for client-side watermarking. More specifically, each of a number of I-Frames in the compressed video stream is evaluated by first watermarking the I-Frame with the sample watermark. Associated frames in the compressed video stream are then decoded using the watermarked I-Frame. An error value for the decoded video frames is then computed. If the error value is outside of a predetermined error threshold range, the I-Frame is selected as an I-Frame that may be used for client-side watermarking.

Abstract: Detection of the salient points in an image enable the improvement of further steps such as coding or image indexing, watermarking, video quality estimation. The methods rely on the fact that a model is fully based on the human visual system (HVS) such as the computation of early visual features, and the methods compute a saliency map for video images taking into account motion and the velocity of the eye.