Document type

Master thesis

Publication date

Publication license

cc-by-nc-nd (c) Juan Borrego Carazo, 2018
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/133458

Fully convolutional architectures for multi-part body segmentation

Journal Title

Journal ISSN

Volume Title

Related resource

Abstract

[en] Since the appearance of the baseline Fully Convolutinal Network (FCN), convolution architectures usage has spread widely among Deep Neural Networks: from classification tasks to object tracking, they are found ubiquitously in the Deep Learning field. In this study, three different convolutional architectures are studied with regard its application to the semantic segmentation of the human body: ICNet, a different resolution cascade network, SegNet, a encoder-decoder network, and Stacked Hourglass, a specially purposed network for the human body. For this purpose, the SURREAL (Synthetic hUmans foR REAL tasks) dataset, which consists of synthetically rendered but realistic images of people, is used. As a result, is shown that the best performing network for this task is the Stacked Hourglass. Due to its continuous refinement of the output and the use of the full network for inference a 55.3% mIoU is achieved on the 24 body part dataset.

Description

Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona, Any: 2018, Tutor: Meysam Madadi i Sergio Escalera Guerrero

Citation

Citation

BORREGO CARAZO, Juan. Fully convolutional architectures for multi-part body segmentation. [consulted: 15 of June of 2026]. Available at: https://hdl.handle.net/2445/133458

Export metadata

JSON - METS

Share record