Карамнова Юлия Андреевна
Human Body Segmentation Using Deep Convolutional Neural Networks
Прикладная математика и информатика
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.