Citation: Li, Z.; Wang, Y.; Zhang, N.;
Zhang, Y.; Zhao, Z.; Xu, D.; Ben, G.;
Gao, Y. Deep Learning-Based Object
Detection Techniques for Remote
Sensing Images: A Survey. Remote
Sens. 2022, 14, 2385. https://doi.org/
10.3390/rs14102385
Academic Editors: M. Jamal Deen,
Subhas Mukhopadhyay,
Yangquan Chen, Simone Morais,
Nunzio Cennamo and Junseop Lee
Received: 7 April 2022
Accepted: 11 May 2022
Published: 16 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Review
Deep Learning-Based Object Detection Techniques for Remote
Sensing Images: A Survey
Zheng Li
1,2
, Yongcheng Wang
1,
* , Ning Zhang
1,2
, Yuxi Zhang
1,2
, Zhikang Zhao
1,2
, Dongdong Xu
1
,
Guangli Ben
1,2
and Yunxiao Gao
1,2
1
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences,
Changchun 130033, China; lizheng20@mails.ucas.ac.cn (Z.L.); zhangning171@mails.ucas.ac.cn (N.Z.);
zhangyuxi18@mails.ucas.ac.cn (Y.Z.); zhaozhikang20@mails.ucas.ac.cn (Z.Z.);
xudongdong@ciomp.ac.cn (D.X.); benguangli@ciomp.ac.cn (G.B.); gaoyunxiao19@mails.ucas.ac.cn (Y.G.)
2
University of Chinese Academy of Sciences, Beijing 100049, China
* Correspondence: wangyc@ciomp.ac.cn
Abstract:
Object detection in remote sensing images (RSIs) requires the locating and classifying
of objects of interest, which is a hot topic in RSI analysis research. With the development of deep
learning (DL) technology, which has accelerated in recent years, numerous intelligent and efficient
detection algorithms have been proposed. Meanwhile, the performance of remote sensing imaging
hardware has also evolved significantly. The detection technology used with high-resolution RSIs
has been pushed to unprecedented heights, making important contributions in practical applications
such as urban detection, building planning, and disaster prediction. However, although some
scholars have authored reviews on DL-based object detection systems, the leading DL-based object
detection improvement strategies have never been summarized in detail. In this paper, we first
briefly review the recent history of remote sensing object detection (RSOD) techniques, including
traditional methods as well as DL-based methods. Then, we systematically summarize the procedures
used in DL-based detection algorithms. Most importantly, starting from the problems of complex
object features, complex background information, tedious sample annotation that will be faced by
high-resolution RSI object detection, we introduce a taxonomy based on various detection methods,
which focuses on summarizing and classifying the existing attention mechanisms, multi-scale feature
fusion, super-resolution and other major improvement strategies. We also introduce recognized
open-source remote sensing detection benchmarks and evaluation metrics. Finally, based on the
current state of the technology, we conclude by discussing the challenges and potential trends in the
field of RSOD in order to provide a reference for researchers who have just entered the field.
Keywords:
object detection; deep learning; remote sensing; neural network; weakly supervised learning
1. Introduction
In recent years, considerable effort has been devoted to overcoming the challenge
of object detection in computer vision. Unlike image classification, object detection [
1
]
inherited from classification tasks not only needs to identify the category to which an object
of interest belongs, but also to locate the position of the object using a bounding box (BBox),
which makes the task more difficult and increases the requirements of the algorithm [2].
Large quantities of remote sensing data have been obtained from imaging optical
sensors on artificial Earth satellites and aerial platforms; such approaches have the ad-
vantages of being realistic and obtainable in real time. According to different imaging
spectral ranges, the data can be classified as visible, infrared, ultraviolet, multispectral,
hyperspectral, or SAR images [
3
,
4
]. These images make different contributions to the Earth
Observation System, promoting our understanding of the environment and facilitating
people’s activities. Recently, thanks to the rapid development of remote sensing platforms
and sensors, the fact that the quantity and quality of remote sensing data are improving
Remote Sens. 2022, 14, 2385. https://doi.org/10.3390/rs14102385 https://www.mdpi.com/journal/remotesensing
