Affiliation:
1. Southwest Jiaotong University
Abstract
Compared with RGB semantic segmentation, RGB-D semantic segmentation can combine the geometric depth information to effectively improve the segmentation accuracy. Considering the application of RGB-D semantic segmentation in autonomous driving, we design a real-time semantic segmentation network, that is, MAFFNet, which can effectively extract depth features and combine the complementary information in RGB and depth. We also design a multi-level attention feature fusion module that can excavate the available context information of RGB and depth features. At the same time, its inference speed can also meet the demands of autonomous driving. Experiments show that our network achieves excellent performance of 74.4% mIoU and an inference speed of 15.9 Hz at a full resolution of
2048
×
1024
on the cityscapes dataset. Using multi-source learning, we mixed the cityscapes and lost and found as the multi-dataset. Our network is also superior to previous algorithms in using the multi-dataset to detect small obstacles outside the road.
Funder
Natural Foundation International Cooperation Project
Sichuan Province Science and Technology Support Program
Subject
Atomic and Molecular Physics, and Optics,Engineering (miscellaneous),Electrical and Electronic Engineering
Reference46 articles.
1. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
2. Fully convolutional networks for semantic segmentation;Long,2015
3. Encoder-decoder with atrous separable convolution for semantic image segmentation;Chen,2018
4. FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture;Hazirbas,2016
5. ACNet: attention based network to exploit complementary features for RGBD semantic segmentation;Hu,2019
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献