Abstract
Google earth with high-resolution imagery basically takes months to process new images before online updates. It is a time consuming and slow process especially for post-disaster application. The objective of this research is to develop a fast and effective method of updating maps by detecting local differences occurred over different time series; where only region with differences will be updated. In our system, aerial images from Massachusetts's road and building open datasets, Saitama district datasets are used as input images. Semantic segmentation is then applied to input images. Semantic segmentation is a pixel-wise classification of images by implementing deep neural network technique. Deep neural network technique is implemented due to being not only efficient in learning highly discriminative image features such as road, buildings etc., but also partially robust to incomplete and poorly registered target maps. Then, aerial images which contain semantic information are stored as database in 5D world map is set as ground truth images. This system is developed to visualise multimedia data in 5 dimensions; 3 dimensions as spatial dimensions, 1 dimension as temporal dimension, and 1 dimension as degenerated dimensions of semantic and colour combination dimension. Next, ground truth images chosen from database in 5D world map and a new aerial image with same spatial information but different time series are compared via difference extraction method. The map will only update where local changes had occurred. Hence, map updating will be cheaper, faster and more effective especially post-disaster application, by leaving unchanged region and only update changed region.
Original language | English |
---|---|
Title of host publication | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
Publisher | International Society for Photogrammetry and Remote Sensing |
Pages | 1119-1122 |
Number of pages | 4 |
Volume | 40 |
Edition | 7W3 |
DOIs | |
Publication status | Published - 2015 Apr 28 |
Event | 2015 36th International Symposium on Remote Sensing of Environment - Berlin, Germany Duration: 2015 May 11 → 2015 May 15 |
Other
Other | 2015 36th International Symposium on Remote Sensing of Environment |
---|---|
Country | Germany |
City | Berlin |
Period | 15/5/11 → 15/5/15 |
Fingerprint
Keywords
- Aerial images
- Convolution neural networks
- Difference extraction
- Semantic segmentation
ASJC Scopus subject areas
- Information Systems
- Geography, Planning and Development
Cite this
Semantic segmentation and difference extraction via time series aerial video camera and its application. / Amit, S. N K; Saito, S.; Sasaki, S.; Kiyoki, Yasushi; Aoki, Yoshimitsu.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. Vol. 40 7W3. ed. International Society for Photogrammetry and Remote Sensing, 2015. p. 1119-1122.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Semantic segmentation and difference extraction via time series aerial video camera and its application
AU - Amit, S. N K
AU - Saito, S.
AU - Sasaki, S.
AU - Kiyoki, Yasushi
AU - Aoki, Yoshimitsu
PY - 2015/4/28
Y1 - 2015/4/28
N2 - Google earth with high-resolution imagery basically takes months to process new images before online updates. It is a time consuming and slow process especially for post-disaster application. The objective of this research is to develop a fast and effective method of updating maps by detecting local differences occurred over different time series; where only region with differences will be updated. In our system, aerial images from Massachusetts's road and building open datasets, Saitama district datasets are used as input images. Semantic segmentation is then applied to input images. Semantic segmentation is a pixel-wise classification of images by implementing deep neural network technique. Deep neural network technique is implemented due to being not only efficient in learning highly discriminative image features such as road, buildings etc., but also partially robust to incomplete and poorly registered target maps. Then, aerial images which contain semantic information are stored as database in 5D world map is set as ground truth images. This system is developed to visualise multimedia data in 5 dimensions; 3 dimensions as spatial dimensions, 1 dimension as temporal dimension, and 1 dimension as degenerated dimensions of semantic and colour combination dimension. Next, ground truth images chosen from database in 5D world map and a new aerial image with same spatial information but different time series are compared via difference extraction method. The map will only update where local changes had occurred. Hence, map updating will be cheaper, faster and more effective especially post-disaster application, by leaving unchanged region and only update changed region.
AB - Google earth with high-resolution imagery basically takes months to process new images before online updates. It is a time consuming and slow process especially for post-disaster application. The objective of this research is to develop a fast and effective method of updating maps by detecting local differences occurred over different time series; where only region with differences will be updated. In our system, aerial images from Massachusetts's road and building open datasets, Saitama district datasets are used as input images. Semantic segmentation is then applied to input images. Semantic segmentation is a pixel-wise classification of images by implementing deep neural network technique. Deep neural network technique is implemented due to being not only efficient in learning highly discriminative image features such as road, buildings etc., but also partially robust to incomplete and poorly registered target maps. Then, aerial images which contain semantic information are stored as database in 5D world map is set as ground truth images. This system is developed to visualise multimedia data in 5 dimensions; 3 dimensions as spatial dimensions, 1 dimension as temporal dimension, and 1 dimension as degenerated dimensions of semantic and colour combination dimension. Next, ground truth images chosen from database in 5D world map and a new aerial image with same spatial information but different time series are compared via difference extraction method. The map will only update where local changes had occurred. Hence, map updating will be cheaper, faster and more effective especially post-disaster application, by leaving unchanged region and only update changed region.
KW - Aerial images
KW - Convolution neural networks
KW - Difference extraction
KW - Semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=84930405236&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84930405236&partnerID=8YFLogxK
U2 - 10.5194/isprsarchives-XL-7-W3-1119-2015
DO - 10.5194/isprsarchives-XL-7-W3-1119-2015
M3 - Conference contribution
AN - SCOPUS:84930405236
VL - 40
SP - 1119
EP - 1122
BT - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
PB - International Society for Photogrammetry and Remote Sensing
ER -