Egocentric Human Segmentation for Mixed Reality
The objective of this work is to segment human body parts from egocentric video using semantic segmentation networks. Our contribution is two-fold: i) we create a semi-synthetic dataset composed of more than 15, 000 realistic images and associated pixel-wise labels of egocentric human body parts, such as arms or legs including different demographic factors; ii) building upon the ThunderNet architecture, we implement a deep learning semantic segmentation algorithm that is able to perform beyond real-time requirements (16 ms for 720 x 720 images). It is believed that this method will enhance sense of presence of Virtual Environments and will constitute a more realistic solution to the standard virtual avatars.
PDF Abstract
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
1x1 Convolution •
Average Pooling •
Batch Normalization •
Channel Shuffle •
Context Enhancement Module •
Dense Connections •
Depthwise Convolution •
Global Average Pooling •
Max Pooling •
Position-Sensitive RoIAlign •
ReLU •
RPN •
ShuffleNet V2 Block •
Sigmoid Activation •
SNet •
Softmax •
Spatial Attention Module (ThunderNet) •
ThunderNet
