Details
| Original language | English |
|---|---|
| Pages (from-to) | 46320 - 46329 |
| Number of pages | 10 |
| Journal | IEEE ACCESS |
| Volume | 11 |
| Publication status | Published - 10 Mar 2023 |
Abstract
A recently developed application of computer vision is pathfinding in self-driving cars. Semantic scene understanding and semantic segmentation, as subfields of computer vision, are widely used in autonomous driving. Semantic segmentation for pathfinding uses deep learning methods and various large sample datasets to train a proper model. Due to the importance of this task, accurate and robust models should be trained to perform properly in different lighting and weather conditions and in the presence of noisy input data. In this paper, we propose a novel learning method for semantic segmentation called layer-wise training and evaluate it on a light efficient structure called an efficient neural network (ENet). The results of the proposed learning method are compared with the classic learning approaches, including mIoU performance, network robustness to noise, and the possibility of reducing the size of the structure on two RGB image datasets on the road (CamVid) and off-road (Freiburg Forest) paths. Using this method partially eliminates the need for Transfer Learning. It also improves network performance when input is noisy.
Keywords
- Autonomous cars, Computer Vision, Convolution Neural Networks, Layer-wise trains, Semantic Segmentation, layer-wise trains, computer vision, convolution neural networks, semantic segmentation
ASJC Scopus subject areas
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: IEEE ACCESS, Vol. 11, 10.03.2023, p. 46320 - 46329.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Using layer-wise training for Road Semantic Segmentation in Autonomous Cars
AU - Shashaani, Shahrzad
AU - Teshnehlab, Mohammad
AU - Khodadadian, Amirreza
AU - Parvizi, Maryam
AU - Wick, Thomas
AU - Noii, Nima
N1 - Funding Information: The work of Maryam Parvizi was supported by the Alexander von Humboldt Foundation Project.
PY - 2023/3/10
Y1 - 2023/3/10
N2 - A recently developed application of computer vision is pathfinding in self-driving cars. Semantic scene understanding and semantic segmentation, as subfields of computer vision, are widely used in autonomous driving. Semantic segmentation for pathfinding uses deep learning methods and various large sample datasets to train a proper model. Due to the importance of this task, accurate and robust models should be trained to perform properly in different lighting and weather conditions and in the presence of noisy input data. In this paper, we propose a novel learning method for semantic segmentation called layer-wise training and evaluate it on a light efficient structure called an efficient neural network (ENet). The results of the proposed learning method are compared with the classic learning approaches, including mIoU performance, network robustness to noise, and the possibility of reducing the size of the structure on two RGB image datasets on the road (CamVid) and off-road (Freiburg Forest) paths. Using this method partially eliminates the need for Transfer Learning. It also improves network performance when input is noisy.
AB - A recently developed application of computer vision is pathfinding in self-driving cars. Semantic scene understanding and semantic segmentation, as subfields of computer vision, are widely used in autonomous driving. Semantic segmentation for pathfinding uses deep learning methods and various large sample datasets to train a proper model. Due to the importance of this task, accurate and robust models should be trained to perform properly in different lighting and weather conditions and in the presence of noisy input data. In this paper, we propose a novel learning method for semantic segmentation called layer-wise training and evaluate it on a light efficient structure called an efficient neural network (ENet). The results of the proposed learning method are compared with the classic learning approaches, including mIoU performance, network robustness to noise, and the possibility of reducing the size of the structure on two RGB image datasets on the road (CamVid) and off-road (Freiburg Forest) paths. Using this method partially eliminates the need for Transfer Learning. It also improves network performance when input is noisy.
KW - Autonomous cars
KW - Computer Vision
KW - Convolution Neural Networks
KW - Layer-wise trains
KW - Semantic Segmentation
KW - layer-wise trains
KW - computer vision
KW - convolution neural networks
KW - semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85149825727&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2023.3255988
DO - 10.1109/ACCESS.2023.3255988
M3 - Article
AN - SCOPUS:85149825727
VL - 11
SP - 46320
EP - 46329
JO - IEEE ACCESS
JF - IEEE ACCESS
SN - 2169-3536
ER -