A De-raining semantic segmentation network for real-time foreground segmentation

9Citations
Citations of this article
15Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Few researches have been proposed specifically for real-time semantic segmentation in rainy environments. However, the demand in this area is huge and it is challenging for lightweight networks. Therefore, this paper proposes a lightweight network which is specially designed for the foreground segmentation in rainy environments, named De-raining Semantic Segmentation Network (DRSNet). By analyzing the characteristics of raindrops, the MultiScaleSE Block is targetedly designed to encode the input image, it uses multi-scale dilated convolutions to increase the receptive field, and SE attention mechanism to learn the weights of each channels. To combine semantic information between different encoder and decoder layers, it is proposed to use Asymmetric Skip, that is, the higher semantic layer of encoder employs bilinear interpolation and the output passes through pointwise convolution, then added element-wise to the lower semantic layer of the decoder. According to the control experiments, the performances of MultiScaleSE Block and Asymmetric Skip compared with SEResNet18 and Symmetric Skip respectively are improved to a certain degree on the Foreground Accuracy index. The parameters and the floating point of operations (FLOPs) of DRSNet are only 0.54M and 0.20GFLOPs separately. The state-of-the-art results and real-time performances are achieved on both the UESTC all-day Scenery add rain (UAS-add-rain) and the Baidu People Segmentation add rain (BPS-add-rain) benchmarks with the input sizes of 192*128, 384*256 and 768*512. The speed of DRSNet exceeds all the networks within 1GFLOPs, and Foreground Accuracy index is also the best among the similar magnitude networks on both benchmarks.

References Powered by Scopus

U-net: Convolutional networks for biomedical image segmentation

65047Citations
N/AReaders
Get full text

Rethinking the Inception Architecture for Computer Vision

24049Citations
N/AReaders
Get full text

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

16024Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Close the Loop: A Unified Bottom-Up and Top-Down Paradigm for Joint Image Deraining and Segmentation

16Citations
N/AReaders
Get full text

Real-time efficient semantic segmentation network based on improved ASPP and parallel fusion module in complex scenes

7Citations
N/AReaders
Get full text

A Survey of Efficient Deep Learning Models for Moving Object Segmentation

7Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Wang, F., & Zhang, Y. (2021). A De-raining semantic segmentation network for real-time foreground segmentation. Journal of Real-Time Image Processing, 18(3), 873–887. https://doi.org/10.1007/s11554-020-01042-2

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 4

80%

Researcher 1

20%

Readers' Discipline

Tooltip

Computer Science 6

86%

Agricultural and Biological Sciences 1

14%

Save time finding and organizing research with Mendeley

Sign up for free