標題: INCORPORATING LUMINANCE, DEPTH AND COLOR INFORMATION BY A FUSION-BASED NETWORK FOR SEMANTIC SEGMENTATION
作者: Hung, Shang-Wei
Lo, Shao-Yuan
Hang, Hsueh-Ming
交大名義發表
電子工程學系及電子研究所
National Chiao Tung University
Department of Electronics Engineering and Institute of Electronics
關鍵字: RGB-D semantic segmentation;depth map;illuminance;fusion-based network
公開日期: 1-一月-2019
摘要: Semantic segmentation has made encouraging progress due to the success of deep convolutional networks in recent years. Meanwhile, depth sensors become prevalent nowadays; thus, depth maps can be acquired more easily. However, there are few studies that focus on the RGB-D semantic segmentation task. Exploiting the depth information effectiveness to improve performance is a challenge. In this paper, we propose a novel solution named LDFNet, which incorporates Luminance, Depth and Color information by a fusion-based network. It includes a sub-network to process depth maps and employs luminance images to assist the depth information in processes. LDFNet outperforms the other state-of-art systems on the Cityscapes dataset, and its inference speed is faster than most of the existing networks. The experimental results show the effectiveness of the proposed multi-modal fusion network and its potential for practical applications.
URI: http://hdl.handle.net/11536/154046
ISBN: 978-1-5386-6249-6
ISSN: 1522-4880
期刊: 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
起始頁: 2374
結束頁: 2378
顯示於類別:會議論文