Civolution is a provider of technology and services for identifying, managing and monetizing audio and video media content. The company offers a portfolio of proprietary and patented digital watermarking and digital audio and video fingerprinting technology solutions for media protection: forensic tracking of media assets in pre-release, digital cinema, Pay Television and online; media intelligence: , broadcast monitoring, internet and radio tracking; media interaction: Automatic Content Recognition and triggering for second screen and . Wikipedia.
Skoric B.,TU Eindhoven |
Katzenbeisser S.,TU Darmstadt |
Schaathun H.G.,Alesund University College |
IEEE Transactions on Information Forensics and Security | Year: 2011
We formalize a new attack model for collusion secure codes, incorporating attacks on the underlying watermarking scheme as well as cut-and-paste attacks traditionally considered for collusion secure codes. We use this model to analyze the collusion resistance of two versions of the Tardos code, both for binary and nonbinary alphabets. The model allows us to consider different signal processing attacks on the content, namely the addition of noise and averaging attacks. The latter may result in content segments that have multiple watermarks embedded. We study two versions of the q-ary Tardos code in which the accusation method has been modified so as to allow for the detection of multiple symbols in the same content segment. We show that both variants yield efficient codes in the new model, parametrized for realistic attacker strengths. © 2011 IEEE. Source
Han J.,Civolution |
Shao L.,Nanjing University of Information Science and Technology |
Shao L.,University of Sheffield |
Xu D.,Nanyang Technological University |
IEEE Transactions on Cybernetics | Year: 2013
With the invention of the low-cost Microsoft Kinect sensor, high-resolution depth and visual (RGB) sensing has become available for widespread use. The complementary nature of the depth and visual information provided by the Kinect sensor opens up new opportunities to solve fundamental problems in computer vision. This paper presents a comprehensive review of recent Kinect-based computer vision algorithms and applications. The reviewed approaches are classified according to the type of vision problems that can be addressed or enhanced by means of the Kinect sensor. The covered topics include preprocessing, object tracking and recognition, human activity analysis, hand gesture analysis, and indoor 3-D mapping. For each category of methods, we outline their main algorithmic contributions and summarize their advantages/differences compared to their RGB counterparts. Finally, we give an overview of the challenges in this field and future research trends. This paper is expected to serve as a tutorial and source of references for Kinect-based computer vision researchers. © 2013 IEEE. Source
Civolution | Date: 2013-03-18
A method of embedding a pattern as a watermark into a content segment. Prior to modifying the content segment, an impulse response of a filter to be used for detecting the pattern is determined; the time-reversed impulse response of the filter is inserted into the segment as the set of imperceptible features; wherein the filter is an infinite impulse response filter having a semi-white frequency spectrum and provides a pseudo-random time-domain response.
Civolution | Date: 2012-06-20
A device for rendering content from a first source comprising a first input for receiving the content from the first source, a second input for receiving a substitution content item from a second source, a substitution module for substituting a segment of the content with the substitution content item, and rendering means for rendering the content wherein the segment is substituted with the substitution content item. The rendering device has monitoring module for monitoring the reception of the segment, and controlling the substitution module dependent on whether the segment is being received, such that the substitution module ceases the substitution upon failure to receive the segment.
Civolution | Date: 2012-10-09
A method for detecting a payload embedded using watermarking in a content stream, the payload being different in a first and a second segment of the content stream, a payload in the second segment having a predetermined relationship with a payload in the first segment, is described. The method selects a point in the content stream where the first segment is likely to end and the second segment to being, samples the stream to obtain a first set of samples that is before the chosen point and a second set of samples that is after the chosen point, and detects the payload on a combination of the first set and a transformation of the second set, where the transformation is based on the assumption that the second set is from the second segment and exploits the relationship that exists between the payloads in the first and second segments.