Similar video searching method and system based on a double-flow neural network

Abstract

The invention provides a similar video searching method and system based on a double-flow neural network. According to the invention, a key frame extraction technology is adopted for video frame extraction, so that the storage space is greatly saved, the neural network training is more stable, and the convergence speed of the neural network training is accelerated; the video features are extractedby adopting the double-flow convolutional neural network, so that the extracted video features keep the spatial information and the time information in the video at the same time, and the robustnessis better. The Hamming distance is used for measuring the similarity of videos, the distance operation in the Hamming space is a bit operation, so that the calculation cost of the Hamming space is farlower than that of the original space even if the Hamming space is a complex retrieval algorithm, and the retrieval algorithm is an efficient retrieval mode.

Description

technical field [0001] The invention relates to a search algorithm for similar videos, in particular to a feature extraction and video hash search algorithm based on a dual-stream neural network algorithm. Background technique [0002] With the popularity of short videos, the scale of users and the duration of watching videos are also increasing. In large cities, the amount of data generated per second is as high as 4T or more. A large number of near-duplicate videos have emerged on the Internet, showing an explosive growth trend. In the face of a large number of videos, how to search through the search algorithm in the video library to find out similar or duplicate videos to the sample video is of great significance for copyright protection, video monitoring, and video recommendation. [0003] At present, the locality-sensitive hashing algorithm is mainly used in the video search field. The core idea is that similar data in the original data space, the hash code after the...

AI Technical Summary

Problems solved by technology

First of all, in order to achieve higher retrieval requirements, longer hash codes are often required, which will undoubtedly sacrifice the recall rate, and the multi-hashing algorithm used to solve this problem will increase storage costs and retrieval time costs

Secondly, local sensitivity is only applicable to some specific indicators, such as p coefficient, jaccard coefficient, etc. When the retrieval requirements become complex, such as semantics, rather than simple distance or similarity, this measurement method is no longer satisfactory Requirements for Approximate Nearest Neighbor Search

Images