Mahyoub, Mohamed and Natalia, Friska and Sudirman, Sud and Al-Jumaily, Abdulmajeed Hammadi Jasim and Liatsis, Panos
(2023)
Semantic Segmentation and Depth Estimation of Urban Road Scene Images Using Multi-Task Networks.
In: 2023 15th International Conference on Developments in eSystems Engineering (DeSE).
![[img]](https://kc.umn.ac.id/27046/1.hassmallThumbnailVersion/Semantic%20Segmentation%20and%20Depth%20Estimation%20of%20Urban%20Road%20Scene%20Images%20using%20Multi-Task%20Networks.pdf)  Preview |
|
Text
Semantic Segmentation and Depth Estimation of Urban Road Scene Images using Multi-Task Networks.pdf
Download (2MB)
| Preview
|
Abstract
In autonomous driving, environment perception
is an important step in understanding the driving scene. Objects
in images captured through a vehicle camera can be detected
and classified using semantic segmentation and depth
estimation methods. Both these tasks are closely related to each
other and this association helps in building a multi-task neural
network where a single network is used to generate both views
from a given monocular image. This approach gives the
flexibility to include multiple related tasks in a single network.
It helps reduce multiple independent networks and improve the
performance of all related tasks. The main aim of our research
presented in this paper is to build a multi-task deep learning
network for simultaneous semantic segmentation and depth
estimation from monocular images. Two decoder-focused U-
Net-based multi-task networks that use a pre-trained Resnet-50 and DenseNet-121 which shared encoder and task-specific
decoder networks with Attention Mechanisms are considered.
We also employed multi-task optimization strategies such as
equal weighting and dynamic weight averaging during the
training of the models. The corresponding models’ performance
is evaluated using mean IoU for semantic segmentation and
Root Mean Square Error for depth estimation. From our
experiments, we found that the performance of these multi-task
networks is on par with the corresponding single-task networks.
Item Type: |
Conference or Workshop Item
(Paper)
|
Keywords: |
Urban Road Scene Analysis; Deep Learning; Multi-Task Networks; Semantic Segmentation; Depth Estimation |
Creators: |
Creators | NIM |
---|
Mahyoub, Mohamed | UNSPECIFIED | Natalia, Friska | UNSPECIFIED | Sudirman, Sud | UNSPECIFIED | Al-Jumaily, Abdulmajeed Hammadi Jasim | UNSPECIFIED | Liatsis, Panos | UNSPECIFIED |
|
Subjects: |
000 Computer Science, Information and General Works > 000 Computer Science, Knowledge and Systems > 006 Special Computer Methods > Artificial Intelligence, Machine Learning, Pattern Recognition, Data Mining |
Divisions: |
Faculty of Engineering & Informatics > Information System |
Date Deposited: |
06 Nov 2023 23:48 |
URI: |
https://kc.umn.ac.id/id/eprint/27046 |
Actions (login required)
 |
View Item |