A micro video copyright automatic detection method based on a block chain technology

Abstract

The invention relates to a micro video copyright automatic detection method based on a block chain technology. The micro video copyright automatic detection method based on the block chain technologycomprises the steps that feature information of a to-be-submitted micro video file is extracted, and the feature information comprises a Hash value of each frame of a P frame sequence group composed of a first P frame value behind each IDR frame; Extracting the Hash value of each frame of the P-frame sequence group with the existing data record on the video collection platform block chain; Comparing the hash value of each frame of the to-be-submitted micro video file with the hash value of each frame of the existing data record; And if the Hash value coincidence rate X of each frame is greaterthan or equal to 2, determining that the to-be-submitted micro video file is a pirated micro video. The method is high in pirate micro video discrimination efficiency and short in discrimination time; The edited to-be-submitted micro video file can also be quickly audited and checked; Existing data record data are stored in the block chain, tamper-proofing is achieved, and traceability and reliability are guaranteed.

Description

technical field [0001] The invention relates to an automatic detection method of micro-video copyright based on block chain technology. Background technique [0002] Video data generally includes three types of frames, namely I frame, B frame, and P frame. I frame is an independent frame with all information, which can be decoded independently without referring to other images. The first frame in the video sequence Frames are always I-frames. [0003] IDR: In H.264, images are organized in units of sequences. The first image of a sequence is called an IDR image (refresh image immediately), and IDR images are all I-frame images. H.264 introduces IDR images for resynchronization of decoding. When the decoder decodes an IDR image, it immediately clears the reference frame queue, outputs or discards all the decoded data, searches for the parameter set again, and starts a new sequence. This way, if a major error occurred in the previous sequence, there is an opportunity to res...

AI Technical Summary

Problems solved by technology

B frame has high compression rate, but requires high decoding performance

[0005] At present, the copyright infringement of online micro-videos on the short video platform is serious, and the inspection is relatively cumbersome and lagging behind. The characteristics of micro-videos are that the video capacity is small and the number of videos is large. The process is short and there is not enough time for manual review. If there is no automatic detection function, there will be a large number of pirated micro-videos on the platform.