Target Detection of High-Resolution Remote Sensing Images Based on Convolutional Neural Network with Salient Features

被引：0

作者：

Yang, Chen ^{[1
]}

Zhang, Xiuying ^{[2
]}

Zhao, Qiulan ^{[3
]}

Bao, Bowen ^{[4
]}

Jing, Yang ^{[5
]}

Bin, Li ^{[5
]}

Zhou, Ruiyi ^{[6
]}

机构：

[1] Changchun Univ Technol, Sch Comp Sci & Engn, Changchun, Peoples R China

[2] PetroChina Qinghai Oilfield Branch Qinghai Prov, Oil Prod Plant 3, Mangya, Haixi, Peoples R China

[3] PetroChina Qinghai Oilfield Branch Qinghai Prov, Oil Prod Plant 1, Mangya, Haixi, Peoples R China

[4] China Natl Petr Corp, Gas Prod Plant 3, Changqing Oilfield Branch, Ordos, Inner Mongolia, Peoples R China

[5] PetroChina Qinghai Oilfield Gas Prod Plant, Infrastruct Project Ctr, Golmud, Qinghai, Peoples R China

[6] Daqing Oilfield Co Ltd, Oil Prod Plant 8, Daqing, Heilongjiang, Peoples R China

来源：

CHEMISTRY AND TECHNOLOGY OF FUELS AND OILS | 2025年

关键词：

remote sensing images; convolutional neural networks; deep features; convolutional feature fusion; object detection; leakage monitoring; pipeline corrosion; remote pressure and flow monitoring; geological disaster warning;

D O I：

暂无

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

The processing technology of remote sensing images has attracted more and more attention. Since remote sensing image target detection technology has a wide range of applications in, terrain exploration and post-disaster reconstruction, etc. Remote sensing image target detection refers to finding the target of interest in the remote sensing image and giving the specific location, while remote sensing image target recognition is the further classification of a certain target, which is a long-term concern in the field of remote sensing image processing. Convolutional Neural Network CNN (Convolutional Neural Network) has achieved great success in the field of computer vision with its deep semantic features, and in recent years, it has been increasingly applied to remote sensing image target detection and recognition tasks. Aiming at the task of remote sensing image target detection, this paper proposes a new deep feature-based remote sensing image target detection method. The depth feature extracted by CNN is used to extract the region of interest, and the target confirmation of the region of interest is carried out through multiple scales of CNN. This method does not require bounding box data for training, and improves the detection accuracy and reduces the false alarm rate.

引用

页数：12