摘要：

We present a novel system to detect copies of 3D videos. The system creates signatures from the depth signals of 3D videos. It also extracts visual features from video frames and creates compact spatial signatures for videos. The system then uses the depth and spatial signatures to compare a given query video versus a reference video database. The system returns a score indicating whether the query video matches any video in the reference video database, and in case of matching, which portion of the reference video matches the query video. The system is computationally efficient and can be implemented in distributed manner. The system can be used, for example, by video content owners, video hosting sites, and third-party companies to find illegally copied 3D videos. To the best of our knowledge, this is the first complete D video copy detection system in the literature. We implemented the proposed system and conducted a rigorous evaluation study using 3D videos with diverse properties. Our experimental results show that the proposed system can achieve high accuracy in terms of precision and recall even if the 3D videos are subjected to several transformations at the same time. For example, the proposed system yields 100% precision and recall when copied videos are parts of original videos, and more than 90% precision and recall when copied videos are subjected to different individual transformations.

展开