Abstract: A video coder includes a processing resource and a non-transitory storage device containing instructions executable by the processing resource to compute a weighted ? frame based on a saliency map and a ? frame. The saliency map is to indicate the relative importance of each pixel in a current frame based on its perceptual significance. The ? frame is to include differences between corresponding pixels in a current frame and a motion predicted frame.

Abstract: A pose estimation system may be embodied as hardware, firmware, software, or combinations thereof to receive an image of an object. The system may determine a first pose estimate of the object via a multi-view matching neural network and then determine a final pose estimate of the object via analysis by an iteratively-refining single-view matching neural network.

Abstract: In example implementations, a method executed by a processor is provided. The method determines an amount of video information that is lost in a video frame due to compression. A drift correction is applied to the video frame to add back a percentage of the amount of video information that is lost. The video frame is encoded with the drift correction.

Abstract: A video coder includes a processing resource and a non-transitory storage device containing instructions executable by the processing resource to compute a weighted ? frame based on a saliency map and a ? frame. The saliency map is to indicate the relative importance of each pixel in a current frame based on its perceptual significance. The ? frame is to include differences between corresponding pixels in a current frame and a motion predicted frame.

Abstract: A video coder includes a processing resource and a non-transitory storage device containing instructions executable by the processing resource to compute a weighted ? frame based on a saliency map and a ? frame. The saliency map is to indicate the relative importance of each pixel in a current frame based on its perceptual significance. The ? frame is to include differences between corresponding pixels in a current frame and a motion predicted frame.

Abstract: In example implementations, a method executed by a processor is provided. The method determines an amount of video information that is lost in a video frame due to compression. A drift correction is applied to the video frame to add back a percentage of the amount of video information that is lost. The video frame is encoded with the drift correction.

Abstract: A video coder includes a processing resource and a non-transitory storage device containing instructions executable by the processing resource to compute a weighted ? frame based on a saliency map and a ? frame. The saliency map is to indicate the relative importance of each pixel in a current frame based on its perceptual significance. The ? frame is to include differences between corresponding pixels in a current frame and a motion predicted frame.

Abstract: A method for synchronization of a digital watermark generates a digital watermark based on feature extraction and a key generator. The synchronization method is adapted for both temporal and spatial synchronization. Statistical features of the watermarked signal along with key generators are used to compute keys used to detect embedded digital watermarks that vary over time or space. For spatial synchronization, spatial redundancy is used to detect geometric distortion of a signal in which the watermark is embedded using an autocorrelation method to detect peaks caused by the redundancy of the watermark structure. These peaks are then analyzed with a histogram method to detect rotation and scaling of the host media signal. The spatial synchronization process is applied to watermarks for both intra-coded frames of video (I-frames) as well as still images.

Abstract: Provided is a technology which can prevent deterioration of image quality when enhancing resolution of a predetermined key frame in a video sequence. Specifically, an apparatus to enhance resolution of a video frame is provided. The apparatus includes a frame extraction unit which extracts a key frame and one or more neighboring frames of the key frame from a video sequence; an upsampling unit which upsamples the key frame and the neighboring frames; a motion-vector search unit which calculates a motion vector of the upsampled key frame using the upsampled neighboring frames as reference frames; and a key-frame estimation unit which enhances quality of the upsampled key frame using temporal information obtained from the motion vector and spatial information in the key frame.

Abstract: A method for synchronization of a digital watermark generates a digital watermark based on feature extraction and a key generator. The synchronization method is adapted for both temporal and spatial synchronization. Statistical features of the watermarked signal along with key generators are used to compute keys used to detect embedded digital watermarks that vary over time or space. For spatial synchronization, spatial redundancy is used to detect geometric distortion of a signal in which the watermark is embedded using an autocorrelation method to detect peaks caused by the redundancy of the watermark structure. These peaks are then analyzed with a histogram method to detect rotation and scaling of the host media signal. The spatial synchronization process is applied to watermarks for both intra-coded frames of video (I-frames) as well as still images.

Abstract: A protocol for temporal synchronization of media signals with temporal components is used for digital watermarking and other applications. The synchronization protocol achieves initial synchronization by finding an initial synchronization key through analysis of a temporal media signal stream. It then uses features of the stream and a queue of one or more keys from previous frames to derive subsequent keys to maintain synchronization. If synchronization is lost due to channel errors or attacks, for example, the protocol uses the initial synchronization key to re-establish synchronization. In digital watermarking applications, the synchronization protocol is agnostic to the watermark embedding and reading functions.

Abstract: A method for synchronization of a media signal computes features of the media signal and determines redundancy of the features to establish synchronization. The synchronization method is adapted for both temporal and spatial synchronization. For spatial synchronization, spatial redundancy is used to detect geometric distortion of a signal using an autocorrelation method to detect peaks caused by the redundancy of features of the signal. These peaks are then analyzed with a histogram method to detect rotation and scaling of the host media signal. The spatial synchronization process is applied for both intra-coded frames of video (I-frames) as well as still images.

Abstract: Provided is a technology which can prevent deterioration of image quality when enhancing resolution of a predetermined key frame in a video sequence. Specifically, an apparatus to enhance resolution of a video frame is provided. The apparatus includes a frame extraction unit which extracts a key frame and one or more neighboring frames of the key frame from a video sequence; an upsampling unit which upsamples the key frame and the neighboring frames; a motion-vector search unit which calculates a motion vector of the upsampled key frame using the upsampled neighboring frames as reference frames; and a key-frame estimation unit which enhances quality of the upsampled key frame using temporal information obtained from the motion vector and spatial information in the key frame.

Abstract: A method of data hiding includes providing a message (68), providing an encrypting sequence (86), and generating an encrypted message (72) based on the message and the encrypting sequence. A carrier signal (66) that conveys information unrelated to the encrypted message is provided, and the encrypted message is embedded (78) into the carrier signal by performing an exclusive-OR of the encrypted message with a first portion of the carrier signal.

Abstract: This disclosure provides a protocol for temporal synchronization of media signals with temporal components. While the disclosure focuses on temporal synchronization of video in a digital watermark application, the protocol is applicable to other applications and media types.

Abstract: A method of determining if at least a portion of a suspect signal (58) is derived from a watermarked original signal (56) includes the steps of providing a watermark (50) and creating the watermarked original signal (56) by incorporating the watermark (50) onto an original signal (52). At least one first watermark indicator is generated (64) based on the the watermarked original signal (56) and the watermark (50) and at least one second watermark indicator is generated (62) based on the suspect signal (58) and the watermark (50). A determination is made (66, 68, 70) whether at least a portion of the suspect signal (58) is derived from the watermarked original signal (56) is made based on the at least one first watermark indicator (64) and the at least one second watermark indicator (62).