A measuring algorithm for the difference of time information

Abstract

The invention relates to measuring algorithm for the difference of time information, and belongs to the video understanding field in the computer vision application. In order to solve the problem of increasing the kinds of information available to convolution neural networks, The maximum mean difference in time information is: the original video image and convolution feature map are divided into two sets, within each set, two adjacent images are used as a set of time information elements to be calculated in the set, The resulting set is the first set of original video images and the first setof convolution feature maps. The effect is that the temporal information of the two sets of data can also be regarded as having a direct relationship. The rational use of the relationship between thetwo sets of data has certain value for the field of video understanding and its related applications.

Description

technical field [0001] The invention belongs to the field of video understanding in computer vision applications, in particular to a method for measuring the difference between continuous video frames and their convolution feature maps. Background technique [0002] Deep learning uses the model constructed by the neural network structure to realize the end-to-end application mode. At the same time, the storage capacity of the model itself for key information in huge data ensures the reliability of the model, which makes the deep learning model unique compared with traditional algorithms. The advantage of comparison has been studied by many scholars in the fields of image, speech and text in a short period of several years and has made great progress. [0003] In computer vision technology such as target detection, target classification, target recognition, target segmentation and other single-frame image applications, deep learning can obtain corresponding models that meet t...

AI Technical Summary

Problems solved by technology

However, since the development time of the direction of video understanding is not long, the accuracy in practical application scenarios is not satisfactory.

More and more scholars believe that the existing methods cannot accurately extract the time information of continuous frames of video, which leads to the accuracy of the model is not enough to meet the application requirements, and further improvement of the original method is needed

Images