Construction method of image tracking classifier and face tracking method applying same

Abstract

The present invention discloses a construction method of an image tracking classifier and a face tracking method applying the same. The construction method of the image tracking classifier comprises the following steps: obtaining a first sample set for training; constructing a convolution neural network model; after performing target frame marking of each image in the first sample set, performing preprocessing to obtain a first target area image and a second target area image, wherein the first target area image is obtained through image expansion according to a target frame, and the second target area image is obtained through transformation of the first target area image and a corresponding target frame marking image; and employing all the first image areas and all the second image areas to perform training of the convolution neural network model to obtain a target regression model. Through adoption of features extracted by the convolution neural network method based on deep learning, the construction method of the image tracking classifier and the face tracking method applying the same effectively solve the problem of balance of robustness and accuracy, have higher robustness in the rapid movement and illumination fuzzy changing, are small in calculation and improve the tracking speed.

Description

technical field [0001] The invention relates to the technical field of face tracking, in particular to a construction method of an image tracking classifier and a face tracking method using the same. Background technique [0002] Today's tracking algorithms mainly include machine learning and filter learning algorithms based on traditional features. However, due to the extraction of traditional features such as HOG, they are less robust and have poor tracking effects on complex scenes such as blurred lighting and size changes. [0003] The existing face tracking methods have the following technical defects: 1) For the face, when deep learning is used for tracking, online fine-tuning requires a large amount of calculation, and it is difficult to achieve real-time performance; 2) For illumination changes and fast movement, The problem that traditional algorithms do not work well. Contents of the invention [0004] The object of the present invention is to provide a method t...

AI Technical Summary

Problems solved by technology

[0002] Today's tracking algorithms mainly include machine learning and filter learning algorithms based on traditional features. However, due to the extraction of traditional features such as HOG, the robustness is poor, and the tracking effect on complex scenes such as blurred lighting and size changes is not good.

[0003] The existing face tracking methods have the following technical defects: 1) For the face, when deep learning is used for tracking, online fine-tuning requires a large amount of calculation, and it is difficult to achieve real-time performance; 2) For illumination changes and fast movement, The problem that traditional algorithms do not work well

Images