Semantic Segmentation of Indoor-Scene RGB-D Images Based on Iterative Contraction and Merging
檔案
本條目沒有附加檔案。
日期
2018-01-01
類型
期刊名稱
IMAGE AND SIGNAL PROCESSING (ICISP 2018)
卷期與頁次
第 10884 卷,頁 252–261
ISSN
0302-9743
ISBN
978-3-319-94211-7; 978-3-319-94210-0
語言
英文
摘要
In this paper, we propose an iterative contraction and merging framework (ICM) for semantic segmentation in indoor scenes. Given an input image and a raw depth image, we first derive the dense prediction map from a convolutional neural network (CNN) and a normal vector map from the depth image. By combining the RGB-D image with these two maps, we can guide the ICM process to produce a more accurate hierarchical segmentation tree in a bottom-up manner. After that, based on the hierarchical segmentation tree, we design a decision process which uses the dense prediction map as a reference to make the final decision of semantic segmentation. Experimental results show that the proposed method can generate much more accurate object boundaries if compared to the state-of-the-art methods.
所屬典藏
會議論文引用此條目
Syu, J.-H., Cho, S.-H., Wang, S.-J., & Wang, L.-C. (2018). Semantic Segmentation of Indoor-Scene RGB-D Images Based on Iterative Contraction and Merging. IMAGE AND SIGNAL PROCESSING (ICISP 2018), 10884, 252–261. https://doi.org/10.1007/978-3-319-94211-7_28
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/152463