Three-dimensional convolutional neural network based video classifying method

Abstract

The invention discloses a three-dimensional convolutional neural network (3D CNN) based video classifying method and belongs to the technical field of video processing. According to the method, a video is sampled at equal intervals to obtain a plurality of video segments, a video database is amplified, three-dimensional video segments are directly input into a 3D CNN, and time domain and space domain characteristics of the video are extracted, so that the limitation of a conventional video classifying method in manually selecting video characteristics and video modeling modes is improved. A parallel distributed 3D CNN multi-classification model lowers the complexity in learning the 3D CNN and enables a classification system to realize distributed parallel computation more conveniently. Relatively high identification rate can be achieved with only fewer video segments based on a 3D CNN multi-classification system, and videos not belonging to any type can be classified into new type, so that the classification error of the new type is avoided.

Description

technical field [0001] The invention relates to a video classification method and belongs to the technical field of video processing. Background technique [0002] With the development of multimedia technology and Internet technology, people can now easily obtain a lot of video data from various channels, but because these massive video data are too large, how to classify these video data, so that people can more conveniently Obtaining the data you are interested in has become one of the very important and challenging research hotspots in the field of computer vision. [0003] The classification technology of video mainly includes three methods of video-based visual information, text information and audio information. As the most important information in video, visual information also contains the most video information and can best represent the video category, so it is also the most worthy. Research. The traditional video classification technology based on visual informa...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a video classification method based on a small-scale video data set and a relatively low-configuration hardware condition. The method uses data set amplification and a distributed parallel computing method of a three-dimensional convolutional neural network to classify videos in multiple ways. The problem is transformed into a binary classification problem, which not only solves the problem of insufficient video data resources, but also greatly reduces the complexity of 3D convolutional neural network learning

Images