Digital video source evidence forensics method

Abstract

The invention belongs to the technical field of digital video detection, and in particular relates to a digital video source evidence forensics method. The method comprises the following steps of: establishing a video sequence sample library used for training; calculating the activity of each of image groups by using an activity and complexity analysis module, and dividing the activity into high activity, medium activity and low activity; decoding the video sequence partially, acquiring various information in a compressed domain thereof, and respectively extracting three characteristics, namely a code rate characteristic, a texture characteristic and a motion vector characteristic; establishing three classifiers, and classifying the image groups with different activities by adopting different classifiers; reading the video sequence of a video source to be detected, acquiring a characteristic vector of each image group of the video sequence, selecting a corresponding classifier according to the activity thereof, and giving a classification result; and synthesizing the classification results of all image groups of the video sequence to perform final judgment. The method has high pertinence and high practicability, and is not easy to attack.

Description

technical field [0001] The invention belongs to the technical field of digital video resource information security, and in particular relates to a digital video source evidence collection method. Background technique [0002] At the beginning of this century, digital video has been widely used in people's daily life and work. At the same time, the rapid development of video editing and processing software has made it easier for video amateurs to use these video editing tools to modify video content and create Digital videos that confuse real ones subvert people's traditional concept of "seeing is believing". If digital video tampering and forgery are used in official media, scientific discovery, insurance and court evidence, etc., it will have an important impact on political and social stability. In 2007, a TV station in the Czech Republic broadcast a video that had not been strictly censored, causing tens of thousands of viewers to see a fake picture of a nuclear explosio...

AI Technical Summary

Problems solved by technology

The easiest way is to check the video file header information. Generally, digital cameras and other devices will write relevant system information, camera type, encoding mode, date and time and other information in the video file header, but these information are easy to be changed. , the credibility is low; another method is to use the intrinsic properties of the encoder and the statistical characteristics of the output video stream to identify its source. This method has high credibility and is not vulnerable to attacks.

Images