An Improved Feature Mapping Method for Video Data

Abstract

The invention relates to an improved video data feature mapping method. The method includes after first features of test video data are mapped to second features for the first time, selecting features most relevant to first features in a training set from the first features of the test video data to be added into the training set, selecting features most relevant to second features in the training set from second features of the test video data to be added into the training set at the same time, then utilizing the features in the training set to recompute a mapping relation, and utilizing the mapping relation to remap the first features of the test video data onto the second features to obtain the second features of the test video data. The method has the advantages that a more complete mapping relation between the two kinds of features can be created by the aid of feature information of the test video data, the first features of the test video data are more accurately mapped onto the second features, and classification accuracy of the second features of the test video data can be improved as compared with that of a traditional improved video data feature mapping method.

Description

technical field [0001] The invention relates to an improved video data feature mapping method, which can be applied to solving the problem of video data feature mapping. Background technique [0002] In real life, all certain features of video data can be obtained, but only a part of another feature can be obtained. We call all available features the first feature of video data, and only part of the features can be obtained. It is called the second characteristic of video data. We expect to obtain the second type of features missing from video data through feature maps. Feature mapping refers to using two features in the video data training set to establish a mapping relationship between the two features, and to map the first feature of the video data used for testing to the second feature, so as to obtain the lack of test video data. The second characteristic. The traditional video data feature mapping method only uses two kinds of features in the training set when estab...

AI Technical Summary

Problems solved by technology

The traditional video data feature mapping method only uses two kinds of features in the training set when establishing the mapping relationship, ignoring the first feature contained in the test video data, and it is difficult to achieve satisfactory results when the number of features contained in the training set is small. The mapping effect, so we propose an improved feature mapping method for video data, this method selects from the first feature of the test video data after first mapping the first feature of the test video data to the second feature The features most related to the first feature in the training set are added to the training set, and at the same time, the features most related to the second feature in the training set are selected from the second feature of the test video data and added to the training set, and then the training set is used The feature recalculates the mapping relationship, and uses the mapping relationship to remap the first feature of the test video data to the second feature

Images