DocumentCode :
3605078
Title :
A Hierarchical Oil Tank Detector With Deep Surrounding Features for High-Resolution Optical Satellite Imagery
Author :
Lu Zhang ; Zhenwei Shi ; Jun Wu
Author_Institution :
Sch. of Astronaut., Beihang Univ., Beijing, China
Volume :
8
Issue :
10
fYear :
2015
Firstpage :
4895
Lastpage :
4909
Abstract :
Automatic oil tank detection plays a very important role for remote sensing image processing. To accomplish the task, a hierarchical oil tank detector with deep surrounding features is proposed in this paper. The surrounding features extracted by the deep learning model aim at making the oil tanks more easily to recognize, since the appearance of oil tanks is a circle and this information is not enough to separate targets from the complex background. The proposed method is divided into three modules: 1) candidate selection; 2) feature extraction; and 3) classification. First, a modified ellipse and line segment detector (ELSD) based on gradient orientation is used to select candidates in the image. Afterward, the feature combing local and surrounding information together is extracted to represent the target. Histogram of oriented gradients (HOG) which can reliably capture the shape information is extracted to characterize the local patch. For the surrounding area, the convolutional neural network (CNN) trained in ImageNet Large Scale Visual Recognition Challenge 2012 (ILSVRC2012) contest is applied as a blackbox feature extractor to extract rich surrounding feature. Then, the linear support vector machine (SVM) is utilized as the classifier to give the final output. Experimental results indicate that the proposed method is robust under different complex backgrounds and has high detection rate with low false alarm.
Keywords :
feature extraction; fuel storage; geophysical image processing; image classification; learning (artificial intelligence); neural nets; remote sensing by laser beam; support vector machines; tanks (containers); AD 2012; Ellipse and Line Segment Detector; ImageNet Large Scale Visual Recognition Challenge; automatic oil tank detection; blackbox feature extractor; convolutional neural network; deep learning model; deep surrounding feature; feature extraction; gradient orientation; hierarchical oil tank detector; high-resolution optical satellite imagery; histogram-of-oriented gradient; linear support vector machine; modified ELSD; remote sensing image processing; shape information; Data mining; Detectors; Feature extraction; Fuel storage; Machine learning; Neural networks; Remote sensing; Support vector machines; Convolutional neural network (CNN); deep learning; ellipse and line segment detector (ELSD); oil tank detection; surrounding information;
fLanguage :
English
Journal_Title :
Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of
Publisher :
ieee
ISSN :
1939-1404
Type :
jour
DOI :
10.1109/JSTARS.2015.2467377
Filename :
7229258
Link To Document :
بازگشت