Content-based video copy detection is an active research field due to the need for copyright pro- tection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach ...Content-based video copy detection is an active research field due to the need for copyright pro- tection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach for video copy detection. This approach directly estimates the location of the copy segment with a probabilistic graphical model. The spatial and temporal consistency of the video copy is embedded in the local probability function. An effective local descriptor and a two-level descriptor pairing method are used to build a video copy detection system to evaluate the approach. Tests show that it outperforms the popular voting algorithm and the probabilistic fusion framework based on the Hidden Markov Model, improving F-score （F1） by 8%.展开更多
针对目前数字视频版权保护问题,提出一种基于ORB(oriented FAST and rotated BRIEF)二值特征描述符局部特征和灰度序全局特征的视频拷贝检测方法。通过比较相邻视频帧灰度直方图的巴氏距离对视频进行镜头分割,将镜头的第一帧作为视频关...针对目前数字视频版权保护问题,提出一种基于ORB(oriented FAST and rotated BRIEF)二值特征描述符局部特征和灰度序全局特征的视频拷贝检测方法。通过比较相邻视频帧灰度直方图的巴氏距离对视频进行镜头分割,将镜头的第一帧作为视频关键帧,提取其灰度序特征和ORB特征,利用灰度序特征对查询视频进行初次匹配,去除部分干扰视频,使用ORB特征对灰度序检测结果再次匹配,得到视频拷贝检测结果。实验结果表明,该方法在视频拷贝检测方面具有可行性和有效性,并且准确率和召回率均可达80%以上。展开更多
Content-based video copy detection becomes an active research field due to requirement of copyright protection, business intelligence, video retrieval, etc. Although it is assumed in the existing methods that referenc...Content-based video copy detection becomes an active research field due to requirement of copyright protection, business intelligence, video retrieval, etc. Although it is assumed in the existing methods that reference database consists of original videos, these videos are difficult to be obtained in many practical cases. In this paper, a copy detection method based on sparse repre- sentation is proposed to make use of some imperfect prototypes of original videos maintained in the reference database. A query video is represented as a linear combination of all the videos in the database. Then we can determine that whether the query has sibling videos in the database based on distribution of coefficients and find them out based on reconstruction error. The experiments show that even with very limited dimensional feature, this method can achieve high performance.展开更多
基金Supported by the National Key Basic Research and Development (863) Program of China (No. 2007CB311003)
文摘Content-based video copy detection is an active research field due to the need for copyright pro- tection and business intellectual property protection. This paper gives a probabilistic spatiotemporal fusion approach for video copy detection. This approach directly estimates the location of the copy segment with a probabilistic graphical model. The spatial and temporal consistency of the video copy is embedded in the local probability function. An effective local descriptor and a two-level descriptor pairing method are used to build a video copy detection system to evaluate the approach. Tests show that it outperforms the popular voting algorithm and the probabilistic fusion framework based on the Hidden Markov Model, improving F-score （F1） by 8%.
文摘针对目前数字视频版权保护问题,提出一种基于ORB(oriented FAST and rotated BRIEF)二值特征描述符局部特征和灰度序全局特征的视频拷贝检测方法。通过比较相邻视频帧灰度直方图的巴氏距离对视频进行镜头分割,将镜头的第一帧作为视频关键帧,提取其灰度序特征和ORB特征,利用灰度序特征对查询视频进行初次匹配,去除部分干扰视频,使用ORB特征对灰度序检测结果再次匹配,得到视频拷贝检测结果。实验结果表明,该方法在视频拷贝检测方面具有可行性和有效性,并且准确率和召回率均可达80%以上。
文摘Content-based video copy detection becomes an active research field due to requirement of copyright protection, business intelligence, video retrieval, etc. Although it is assumed in the existing methods that reference database consists of original videos, these videos are difficult to be obtained in many practical cases. In this paper, a copy detection method based on sparse repre- sentation is proposed to make use of some imperfect prototypes of original videos maintained in the reference database. A query video is represented as a linear combination of all the videos in the database. Then we can determine that whether the query has sibling videos in the database based on distribution of coefficients and find them out based on reconstruction error. The experiments show that even with very limited dimensional feature, this method can achieve high performance.
