Robust video fingerprint method based on three-dimensional space-time characteristics

Abstract

The invention discloses a robust video fingerprint extraction method based on three-dimensional space-time characteristics, which mainly overcomes the deficiency in utilization of video characteristics in the time direction in the traditional method. The robust video fingerprint extraction method is characterized in that the three-dimensional space-time characteristics are introduced in fingerprint extraction, namely, three-dimensional space-time characteristic points in the successive frames of a video to be detected are extracted firstly, and the most stable characteristic area in each frame is obtained through selection of the characteristic strength and characteristic scale; then the characteristic area is obtained through down sampling; finally, a contrast histogram is used for representing the area and normalized into a vector-form fingerprint sequence of the video to be detected; and the fingerprint sequence of the video to be detected and a candidate fingerprint sequence in a database are subjected to distance matching so as to obtain a candidate video relevant to the video to be detected. The robust video fingerprint extraction method disclosed by the invention reflects the space characteristic and the time characteristic at the same time, has extremely good robustness and can be used for video content authentication and near video detection.

Description

technical field [0001] The invention belongs to the technical field of information security, and relates to a digital video fingerprint extraction and detection matching method. The method can resist conventional video attacks and processing, and is used in the fields of content authentication and near-video detection on the Internet. Background technique [0002] With the development of multimedia technology and network technology, the digitalization of video information provides great convenience for video information access, copying and modification, and at the same time makes the efficiency and accuracy of information transmission and expression significantly improved. However, because a large amount of video information can be easily downloaded and published from the Internet, and can be modified arbitrarily through processing software, coupled with some non-human attacks in the process of spreading and storing, this has caused a large number of video information on the ...

AI Technical Summary

Problems solved by technology

These methods can basically resist most of the common video attacks, but these methods do not pay attention to the space-time and redundancy of the video, that is, only a simple arrangement of the image sequence, ignoring the time information of the video, and fail to achieve Represents a video to the greatest extent, which affects the independence and robustness of digital video fingerprints, and ultimately limits the retrieval accuracy and retrieval efficiency in near-copy video detection

Images