Abstract
In order to align the remote sensing images, we propose a novel hybrid method that combines image segmentation and salient region detection, which is inspired by human vision system. First of all, we present a novel superpixel-based method for dividing the image into sub-areas. Second, we propose a novel method based on color and image textures for detecting salient regions composed by superpixels. Then, we extract a new feature based on difference of Gaussian and local binary pattern from the salient regions. Finally, the sensed image is transformed by thin-plate spline. The proposed algorithm was tested on 30 pairs of remote sensing images and compared to other three state of the art methods. Experimental results show our approach is fast and robust, while still being efficient, which is better than other three methods.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 2293-2317 |
| Number of pages | 25 |
| Journal | Circuits, Systems, and Signal Processing |
| Volume | 33 |
| Issue number | 7 |
| DOIs | |
| State | Published - 2014 |
Fingerprint
Keywords
- Human vision system
- Image registration
- Image segmentation
- Local binary pattern
- Remote sensing images
- Salient region detection
ASJC Scopus subject areas
- Signal Processing
- Applied Mathematics
Cite this
A hybrid method for multi-sensor remote sensing image registration based on salience region. / Jiao, Jichao; Deng, Zhongliang; Zhao, Baojun; Femiani, John; Wang, Xin.
In: Circuits, Systems, and Signal Processing, Vol. 33, No. 7, 2014, p. 2293-2317.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A hybrid method for multi-sensor remote sensing image registration based on salience region
AU - Jiao, Jichao
AU - Deng, Zhongliang
AU - Zhao, Baojun
AU - Femiani, John
AU - Wang, Xin
PY - 2014
Y1 - 2014
N2 - In order to align the remote sensing images, we propose a novel hybrid method that combines image segmentation and salient region detection, which is inspired by human vision system. First of all, we present a novel superpixel-based method for dividing the image into sub-areas. Second, we propose a novel method based on color and image textures for detecting salient regions composed by superpixels. Then, we extract a new feature based on difference of Gaussian and local binary pattern from the salient regions. Finally, the sensed image is transformed by thin-plate spline. The proposed algorithm was tested on 30 pairs of remote sensing images and compared to other three state of the art methods. Experimental results show our approach is fast and robust, while still being efficient, which is better than other three methods.
AB - In order to align the remote sensing images, we propose a novel hybrid method that combines image segmentation and salient region detection, which is inspired by human vision system. First of all, we present a novel superpixel-based method for dividing the image into sub-areas. Second, we propose a novel method based on color and image textures for detecting salient regions composed by superpixels. Then, we extract a new feature based on difference of Gaussian and local binary pattern from the salient regions. Finally, the sensed image is transformed by thin-plate spline. The proposed algorithm was tested on 30 pairs of remote sensing images and compared to other three state of the art methods. Experimental results show our approach is fast and robust, while still being efficient, which is better than other three methods.
KW - Human vision system
KW - Image registration
KW - Image segmentation
KW - Local binary pattern
KW - Remote sensing images
KW - Salient region detection
UR - http://www.scopus.com/inward/record.url?scp=84902817781&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84902817781&partnerID=8YFLogxK
U2 - 10.1007/s00034-014-9763-z
DO - 10.1007/s00034-014-9763-z
M3 - Article
AN - SCOPUS:84902817781
VL - 33
SP - 2293
EP - 2317
JO - Circuits, Systems, and Signal Processing
JF - Circuits, Systems, and Signal Processing
SN - 0278-081X
IS - 7
ER -