DocumentCode :
3612259
Title :
Seamline Determination Based on Semantic Segmentation for Aerial Image Mosaicking
Author :
Saito, Shunta ; Arai, Ryota ; Aoki, Yoshimitsu
Author_Institution :
Grad. Sch. of Integrated Design Eng., Keio Univ., Yokohama, Japan
Volume :
3
fYear :
2015
fDate :
7/7/1905 12:00:00 AM
Firstpage :
2847
Lastpage :
2856
Abstract :
We propose a novel method for seamline determination based on semantic segmentation for aerial image mosaicking. First, we train a convolutional neural network (CNN) for pixel labeling to extract building regions. Using the trained CNN, we create a building probability map from an input aerial image with no pre-processing. We then use Dijkstra´s algorithm to find the optimal seamline as a shortest path on the map. We evaluate the quality of the seamlines produced by our method on actual aerial images. Finally, we show that our seamlines never pass through any buildings and compare the effectiveness with the conventional mean-shift segmentation-based method.
Keywords :
geophysical image processing; image segmentation; learning (artificial intelligence); probability; remote sensing; CNN training; Dijkstra algorithm; aerial image mosaicking; building probability map; building region extraction; convolutional neural network training; pixel labeling; seamline determination; semantic segmentation; Buildings; Data mining; Image color analysis; Image segmentation; Semantics; Shortest path problem; Remote sensing; artificial neural networks; computer vision; image processing; neural networks;
fLanguage :
English
Journal_Title :
Access, IEEE
Publisher :
ieee
ISSN :
2169-3536
Type :
jour
DOI :
10.1109/ACCESS.2015.2508921
Filename :
7355281
Link To Document :
بازگشت