Accurate Localization of Oil Tanks in Remote Sensing Images via FGMRST-Based CNN

Han Jiang,Fangfang Li,Bin Lei,Yueting Zhang,Jiayi Guo,Yuxin Hu,Chibiao Ding

doi:10.3390/rs13224646

Abstract

Object localization is an important application of remote sensing images and the basis of information extraction. The acquired accuracy is the key factor to improve the accuracy of object structure information inversion. The floating roof oil tank is a typical cylindrical artificial object, and its top cover fluctuates up and down with the change in oil storage. Taking the oil tank as an example, this study explores the localization by combining the traditional feature parameter method and convolutional neural networks (CNNs). In this study, an improved fast radial symmetry transform (FRST) algorithm called fast gradient modulus radial symmetry transform (FGMRST) is proposed and an approach based on FGMRST combined with CNN is proposed. It effectively adds the priori of circle features to the calculation process. Compared with only using CNN, it achieves higher precision localization with fewer network layers. The experimental results based on SkySat data show that the method can effectively improve the calculation accuracy and efficiency of the same order of magnitude network, and by increasing the network depth, the accuracy still has a significant improvement.

Highlights

In computer vision, object localization is to determine the position of the object in a single object image, and object detection is to identify all the objects and determine their positions in an image in which the type and number of objects are not fixed
The localization of the oil tank in this study refers to the determination of the center position of the tank roof, the center position of the circular-arc-shaped shadow cast by the sun on the floating roof, and the radius of the oil tank in the image, which is of great significance for the inversion of the oil tank structure [4]
The results show that, compared with ordinary convolutional neural networks (CNNs), the method can effectively improve the accuracy of the localization of the oil tank, and has good stability

Summary

Introduction

Object localization is to determine the position of the object in a single object image, and object detection is to identify all the objects and determine their positions in an image in which the type and number of objects are not fixed. The floating roof oil tank in remote a sensing image, as a representative of a man-fabricated object with the circular feature, plays an important role in both military and civil fields [3]. The localization of the oil tank in this study refers to the determination of the center position of the tank roof, the center position of the circular-arc-shaped shadow cast by the sun on the floating roof, and the radius of the oil tank in the image, which is of great significance for the inversion of the oil tank structure [4]. (a) Comparison of the number of pixels traversed by CNN in processing circular objects;. (b) comparison of the number of pixels traversed by FRST in processing circular objects. The value of the transform at the radius n indicates the contribution to radial symmetry of the gradients a distance n away from each point

Objectives

Methods

Results

Conclusion