TY - JOUR
T1 - Power Transmission Tower Detection Based on Polar Coordinate Semivariogram in High-Resolution SAR Image
AU - Zeng, Tao
AU - Gao, Qiang
AU - Ding, Zegang
AU - Tian, Weiming
AU - Yang, Yanjiao
AU - Zhang, Ziqing
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2017/12
Y1 - 2017/12
N2 - The detection of a power transmission tower in a synthetic aperture radar (SAR) image has been widely studied. However, few works consider the geometric features of the power transmission tower. In a high-resolution SAR image, the geometric features of the power transmission tower are more obvious and can be used to further reduce the false-alarm probability. In this letter, a new power transmission tower detection method is proposed, which takes into account the geometric features of the target and obtains lower false-alarm probability than the traditional methods. First, the polar coordinate semivariogram is proposed, which has the advantages of low computational complexity and high sensitivity to the shape of the targets. Then, a three-layer neural network is employed to detect the power transmission tower, taking the geometric features as the input vector. Finally, the validity of the proposed method is illuminated by the experimental measurement results of the airborne data with 0.5-m resolution.
AB - The detection of a power transmission tower in a synthetic aperture radar (SAR) image has been widely studied. However, few works consider the geometric features of the power transmission tower. In a high-resolution SAR image, the geometric features of the power transmission tower are more obvious and can be used to further reduce the false-alarm probability. In this letter, a new power transmission tower detection method is proposed, which takes into account the geometric features of the target and obtains lower false-alarm probability than the traditional methods. First, the polar coordinate semivariogram is proposed, which has the advantages of low computational complexity and high sensitivity to the shape of the targets. Then, a three-layer neural network is employed to detect the power transmission tower, taking the geometric features as the input vector. Finally, the validity of the proposed method is illuminated by the experimental measurement results of the airborne data with 0.5-m resolution.
KW - Polar coordinate semivariogram (PCSV)
KW - power transmission tower detection
KW - synthetic aperture radar (SAR)
UR - http://www.scopus.com/inward/record.url?scp=85034219922&partnerID=8YFLogxK
U2 - 10.1109/LGRS.2017.2748819
DO - 10.1109/LGRS.2017.2748819
M3 - Article
AN - SCOPUS:85034219922
SN - 1545-598X
VL - 14
SP - 2200
EP - 2204
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
IS - 12
M1 - 8103926
ER -