Open AccessResearch on YOLOv3 target detection model in the field of remote sensing
Author(s) -
Yaguang Yang,
Cong Huang,
Huajun Wang,
Jun Wan,
ZhenHeng Wang,
Yuxian Ma
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2029/1/012093
Subject(s) - bottleneck , computer science , remote sensing , field (mathematics) , artificial intelligence , search and rescue , high resolution , real time computing , robot , computer vision , embedded system , mathematics , pure mathematics , geology
The target recognition problem of high-resolution remote sensing images is marine traffic monitoring, disaster reduction emergency search and rescue, unmanned autonomous systems (UAS) (such as unmanned aerial vehicles, unmanned vehicles, unmanned submersibles, unmanned surface craft and other autonomous robots) and other civilian applications. The core technology of the system is also the key technology of military automatic target recognition (ATR) systems such as military reconnaissance, precision guidance, and maritime monitoring. With the development of high-resolution earth observation systems, more and more industrial applications require the extraction of more valuable target details from high-resolution remote sensing images. Then, due to the complex background of high-resolution remote sensing images and the difference in image quality (factors such as size, resolution, noise, etc.), low target detection accuracy and slow speed are the main bottlenecks that affect the combination of artificial intelligence and remote sensing. In order to solve the technical bottleneck of target detection, this paper focuses on exploring the detection performance of the channel attention module SElayer and YOLOv3 model in the field of high-resolution remote sensing images, providing basic technical support for related research.