Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks

02/02/2021
by   Alessandro Saviolo, et al.
8

This paper presents a new framework for human body part segmentation based on Deep Convolutional Neural Networks trained using only synthetic data. The proposed approach achieves cutting-edge results without the need of training the models with real annotated data of human body parts. Our contributions include a data generation pipeline, that exploits a game engine for the creation of the synthetic data used for training the network, and a novel pre-processing module, that combines edge response map and adaptive histogram equalization to guide the network to learn the shape of the human body parts ensuring robustness to changes in the illumination conditions. For selecting the best candidate architecture, we performed exhaustive tests on manually-annotated images of real human body limbs. We further present an ablation study to validate our pre-processing module. The results show that our method outperforms several state-of-the-art semantic segmentation networks by a large margin. We release an implementation of the proposed approach along with the acquired datasets with this paper.

READ FULL TEXT

page 4

page 8

page 12

page 13

research
05/25/2020

Egocentric Human Segmentation for Mixed Reality

The objective of this work is to segment human body parts from egocentri...
research
07/28/2018

Deep Leaf Segmentation Using Synthetic Data

Automated segmentation of individual leaves of a plant in an image is a ...
research
07/20/2020

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

Existing semantic segmentation approaches either aim to improve the obje...
research
06/21/2023

Exploiting Multimodal Synthetic Data for Egocentric Human-Object Interaction Detection in an Industrial Scenario

In this paper, we tackle the problem of Egocentric Human-Object Interact...
research
01/11/2017

Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification

Re-identification is generally carried out by encoding the appearance of...
research
08/21/2019

In-bed Pressure-based Pose Estimation using Image Space Representation Learning

In-bed pose estimation has shown value in fields such as hospital patien...

Please sign up or login with your details

Forgot password? Click here to reset