Human Body Segmentation Using Deep Convolutional Neural Networks

Student: Karamnova Yulia

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2018

This paper deals with the task of human body segmentation, which has many applications in computer vision, such as motion capture, intelligent video surveillance, human-robot interaction and online version of clothes fitting. The proposed method is based on Deep Convolutional Neural Networks. Two main challenges of body segmentation are nearby objects that could cover parts of a body and big variations of human poses. We propose the architecture of neural network that attempts to tackle both of them. We train and test our model on “MPII Human Pose“ dataset. We present a detailed analysis and show how our architecture performs compared to the current state-of-art models.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses