Complementary Convolution Residual Networks for Semantic Segmentation in Street Scenes with Deep Gaussian CRF
-
- Li Yongbo
- School of Automation, China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems
-
- Ma Yuanyuan
- School of Automation, China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems
-
- Cai Wendi
- School of Automation, China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems
-
- Xie Zhongzhao
- School of Automation, China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems
-
- Zhao Tao
- School of Automation, China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems
この論文をさがす
抄録
<p>To understand surrounding scenes accurately, the semantic segmentation of images is vital in autonomous driving tasks, such as navigation, and route planning. Currently, convolutional neural networks (CNN) are widely employed in semantic segmentation to perform precise prediction in the dense pixel level. A recent trend in network design is the stacking of small convolution kernels. In this work, small convolution kernels (3 × 3) are decomposed into complementary convolution kernels (1 × 3 + 3 × 1, 3 × 1 + 1 × 3), the complementary small convolution kernels perform better in the classification and location tasks of semantic segmentation. Subsequently, a complementary convolution residual network (CCRN) is proposed to improve the speed and accuracy of semantic segmentation. To further locate the edge of objects precisely, A coupled Gaussian conditional random field (G-CRF) is utilized for CCRN post-processing. Proposal approach achieved 81.8% and 73.1% mean Intersection-over-Union (mIoU) on PASCAL VOC-2012 test set and Cityscapes test set, respectively.</p>
収録刊行物
-
- Journal of Advanced Computational Intelligence and Intelligent Informatics
-
Journal of Advanced Computational Intelligence and Intelligent Informatics 25 (1), 3-12, 2021-01-20
富士技術出版株式会社
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390005506400233728
-
- NII論文ID
- 130007971441
-
- NII書誌ID
- AA12042502
-
- ISSN
- 18838014
- 13430130
-
- NDL書誌ID
- 031224085
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可