A review of small target detection based on deep learning

Tao Zhang; YaLi Qi; LiKun Lu; QingTao Zeng; Wu Dong; LiQin Yu

doi:10.1117/12.3015005

4 March 2024 A review of small target detection based on deep learning

Tao Zhang, YaLi Qi, LiKun Lu, QingTao Zeng, Wu Dong, LiQin Yu

Proceedings Volume 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023); 1298122 (2024) https://doi.org/10.1117/12.3015005
Event: 9th International Symposium on Sensors, Mechatronics, and Automation (ISSMAS 2023), 2023, Nanjing, China

Abstract

Small target detection is a difficult point in target detection. Small target detection needs to identify the location and type of targets with few pixels in the picture and little resolution and feature information, and the algorithms used in the current application of mature medium and large target detection do not work well in detecting small targets. Therefore, improving the capability of small target detection is a current challenge in the field of target detection and an important research direction. In this paper, we will focus on deep learning small target detection technology, first introduce the definition of small targets and the reasons for the difficulty of small target detection, then comprehensively discuss the methods to improve the effectiveness of small target detection, and finally introduce the common small target datasets and the evaluation index of detection algorithms.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Tao Zhang, YaLi Qi, LiKun Lu, QingTao Zeng, Wu Dong, and LiQin Yu "A review of small target detection based on deep learning", Proc. SPIE 12981, Ninth International Symposium on Sensors, Mechatronics, and Automation System (ISSMAS 2023), 1298122 (4 March 2024); https://doi.org/10.1117/12.3015005

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available