Method for video labeling and device for video labeling

Abstract

The invention discloses a method for video labeling and a device for video labeling and belongs to the field of video processing. The method for the video labeling comprises carrying out a shot segmentation to a video; extracting a key frame assembly in each segmented shot; extracting relevant low layer eigenvectors of each key frame assembly; using semi-supervised kernel density estimation arithmetic to label each unlabeled sample with a category label and labeling key frames corresponding to the unlabeled samples with category. Due to the fact that the eigenvectors combined by various low layer characteristics of an image are adopted to represent the key frames, and loss of pattern information is reduced. The semi-supervised kernel density estimation arithmetic is used for labeling each unlabeled sample with a category, unlabeled data is leaded to a kernel density estimation, feature information of the labeled samples and unlabeled samples are comprehensively applied, and efficiency of video labeling and accuracy of kernel density estimation are improved.

Description

technical field [0001] The invention relates to the fields of video processing and machine learning, in particular to a video tagging method and device. Background technique [0002] With the development of computer and network technology, ordinary users can access more and more video data. Video data provides a lot of useful information, and its content is more abundant, intuitive and vivid than other forms of data. On the one hand, the massive amount of information contained in rich video data is unmatched by other media; on the other hand, its increasingly huge data volume, unstructured data forms and ambiguity in content make it more convenient for user interaction. Operations set up obstacles that prevent it from functioning more effectively. [0003] In order to mine the potential value of large video collections, users need to be able to efficiently retrieve the desired video clips. Video annotation is a technology that links text and video semantic content. It is ...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the disadvantages of the prior art that there is a small amount of labeled data and a large number of unlabeled quantities, as well as the lack of single feature expression information, the present invention provides a video labeling method and device, which introduces unlabeled data into kernel density estimation, and comprehensively The feature information of labeled samples and unlabeled samples is used to improve the efficiency of video labeling and the accuracy of kernel density estimation

Images