Lightweight Design for Infrared Dim and Small Target Detection in Complex Environments

被引:0
|
作者
Chang, Yan [1 ]
Ma, Decao [1 ]
Ding, Yao [1 ]
Chen, Kefu [1 ]
Zhou, Daming [2 ]
机构
[1] PLA Rocket Force Univ Engn, Xian 710025, Peoples R China
[2] Northwestern Polytech Univ, Sch Astronaut, Xian 710072, Peoples R China
关键词
object detection; lightweight; small infrared targets; attention mechanism; NETWORK; MODEL;
D O I
10.3390/rs16203761
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In the intricate and dynamic infrared imaging environment, the detection of infrared dim and small targets becomes notably challenging due to their feeble radiation intensity, intricate background noise, and high interference characteristics. To tackle this issue, this paper introduces a lightweight detection and recognition algorithm, named YOLOv5-IR, and further presents an even more lightweight version, YOLOv5-IRL. Firstly, a lightweight network structure incorporating spatial and channel attention mechanisms is proposed. Secondly, a detection head equipped with an attention mechanism is designed to intensify focus on small target information. Lastly, an adaptive weighted loss function is devised to improve detection performance for low-quality samples. Building upon these advancements, the network size can be further compressed to create the more lightweight YOLOv5-IRL version, which is better suited for deployment on resource-constrained mobile platforms. Experimental results on infrared dim and small target detection datasets with complex backgrounds indicate that, compared to the baseline model YOLOv5, the proposed YOLOv5-IR and YOLOv5-IRL detection algorithms reduce model parameter counts by 42.9% and 45.6%, shorten detection time by 13.6% and 16.9%, and enhance mAP0.5 by 2.4% and 1.8%, respectively. These findings demonstrate that the proposed algorithms effectively elevate detection efficiency, meeting future demands for infrared dim and small target detection.
引用
收藏
页数:24
相关论文
共 50 条
  • [21] An infrared dim and small target detection method based on fractional differential
    Li, Peng
    Yan, Bin
    Ye, Run
    Sun, GuangHui
    PROCEEDINGS OF THE 30TH CHINESE CONTROL AND DECISION CONFERENCE (2018 CCDC), 2018, : 2381 - 2386
  • [22] Dim2Clear Network for Infrared Small Target Detection
    Zhang, Mingjin
    Zhang, Rui
    Zhang, Jing
    Guo, Jie
    Li, Yunsong
    Gao, Xinbo
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [23] Global induced local network for infrared: dim small target detection
    Li, Junying
    Hou, Xiaorong
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2025, 36 (01)
  • [24] Research of desert infrared polarization dim and small target detection method
    Xue, Mo-Gen
    Liu, Xiao-Cheng
    Liu, Xiao
    Yang, Fan
    Guangzi Xuebao/Acta Photonica Sinica, 2014, 43 (10):
  • [25] Infrared dim small target detection algorithm based on NSCT and SVD
    Zhao, Ying
    Liu, Gang
    Zhou, Huixin
    Qin, Hanlin
    Li, Xiao
    Wen, Zhigang
    Ni, Man
    Wang, Bingjian
    AOPC 2015: IMAGE PROCESSING AND ANALYSIS, 2015, 9675
  • [26] Dim and small infrared target fast detection guided by visual saliency
    Yi, Xiang
    Wang, Bingjian
    Zhou, Huixin
    Qin, Hanlin
    INFRARED PHYSICS & TECHNOLOGY, 2019, 97 : 6 - 14
  • [27] An Intelligent Particle Filter for Infrared Dim Small Target Detection and Tracking
    Tian, Mengchu
    Chen, Zhimin
    Wang, Huifen
    Liu, Linyan
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2022, 58 (06) : 5318 - 5333
  • [28] A Detection Algorithm of Infrared Dim and Small Target Based on Background Prediction
    Song, Yu
    Zhang, Chun-yan
    2013 INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ARTIFICIAL INTELLIGENCE (ICCSAI 2013), 2013, : 132 - 135
  • [29] Infrared Dim and Small Target Detection Based on Denoising Autoencoder Network
    Shi, Manshu
    Wang, Huan
    MOBILE NETWORKS & APPLICATIONS, 2020, 25 (04): : 1469 - 1483
  • [30] Infrared dim-small target detection via chessboard topology
    Dan, Bingbing
    Zhu, Zijian
    Wei, Yuxing
    Liu, Dongxu
    Li, Meihui
    Tang, Tao
    OPTICS AND LASER TECHNOLOGY, 2025, 181