Next Article in Journal
A CNN-Based Length-Aware Cascade Road Damage Detection Approach
Previous Article in Journal
An Adaptive Measurement System for the Simultaneous Evaluation of Frequency Shift and Series Resistance of QCM in Liquid
Open AccessArticle

Semantic Segmentation Leveraging Simultaneous Depth Estimation

1
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
2
Peng Cheng Laboratory, Shenzhen 518055, China
3
The N.1 Institute for Health, National University of Singapore, Singapore 117411, Singapore
*
Authors to whom correspondence should be addressed.
Sensors 2021, 21(3), 690; https://doi.org/10.3390/s21030690
Received: 14 December 2020 / Revised: 14 January 2021 / Accepted: 15 January 2021 / Published: 20 January 2021
(This article belongs to the Section Sensing and Imaging)
Semantic segmentation is one of the most widely studied problems in computer vision communities, which makes a great contribution to a variety of applications. A lot of learning-based approaches, such as Convolutional Neural Network (CNN), have made a vast contribution to this problem. While rich context information of the input images can be learned from multi-scale receptive fields by convolutions with deep layers, traditional CNNs have great difficulty in learning the geometrical relationship and distribution of objects in the RGB image due to the lack of depth information, which may lead to an inferior segmentation quality. To solve this problem, we propose a method that improves segmentation quality with depth estimation on RGB images. Specifically, we estimate depth information on RGB images via a depth estimation network, and then feed the depth map into the CNN which is able to guide the semantic segmentation. Furthermore, in order to parse the depth map and RGB images simultaneously, we construct a multi-branch encoder–decoder network and fuse the RGB and depth features step by step. Extensive experimental evaluation on four baseline networks demonstrates that our proposed method can enhance the segmentation quality considerably and obtain better performance compared to other segmentation networks. View Full-Text
Keywords: CNN; semantic segmentation; depth estimation; multi-source feature fusion CNN; semantic segmentation; depth estimation; multi-source feature fusion
Show Figures

Figure 1

MDPI and ACS Style

Sun, W.; Gao, Z.; Cui, J.; Ramesh, B.; Zhang, B.; Li, Z. Semantic Segmentation Leveraging Simultaneous Depth Estimation. Sensors 2021, 21, 690. https://doi.org/10.3390/s21030690

AMA Style

Sun W, Gao Z, Cui J, Ramesh B, Zhang B, Li Z. Semantic Segmentation Leveraging Simultaneous Depth Estimation. Sensors. 2021; 21(3):690. https://doi.org/10.3390/s21030690

Chicago/Turabian Style

Sun, Wenbo; Gao, Zhi; Cui, Jinqiang; Ramesh, Bharath; Zhang, Bin; Li, Ziyao. 2021. "Semantic Segmentation Leveraging Simultaneous Depth Estimation" Sensors 21, no. 3: 690. https://doi.org/10.3390/s21030690

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop