TY - JOUR
T1 - Single-Frame Infrared Target Detection Based on Fast Content-Related Modeling
AU - Zhang, Zipeng
AU - Zhao, Xidong
AU - Wang, Wenzheng
AU - Han, Yuqi
AU - Deng, Chenwei
AU - Li, Zhuokai
AU - Tang, Linbo
N1 - Publisher Copyright:
© 2008-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Infrared small target detection has attracted great interest in applications related to public safety, area monitoring and various other fields. However, this task faces two challenges: 1) The diversity of background scenes leads to complexity of infrared content. 2) The small size of targets results in limited available information. Most of methods mainly concentrate on modeling global features, overlooking the variations in local features due to complex scenes. To solve these problems, a single-frame infrared target detection method based on fast content-related modeling is proposed to combine global and local features of infrared images, describing the common features of vary scenes robustly and enhancing the distinction between targets and backgrounds. Specifically, we analyzed and integrated multi-dimensional global statistical characteristics to construct a weighted spatial sum of nuclear norm, achieving a comprehensive background modeling and mitigating complex background clutters. On the other hand, we incorporated local distribution priors generated by target-constraint filter into the model to adaptively protect suspected target areas from suppression. Finally, we propose an efficient solving algorithm with stepwise reconstruction from seed-images sampled from infrared images, enabling linear-Time extraction of infrared small targets. Comparison experiments on SIRST, IRSTD-1k, NUDT-SIRST and NUST-SIRST datasets indicate that the proposed method enhances detection accuracy and reduces detection time compared to state-of-The-Art methods.
AB - Infrared small target detection has attracted great interest in applications related to public safety, area monitoring and various other fields. However, this task faces two challenges: 1) The diversity of background scenes leads to complexity of infrared content. 2) The small size of targets results in limited available information. Most of methods mainly concentrate on modeling global features, overlooking the variations in local features due to complex scenes. To solve these problems, a single-frame infrared target detection method based on fast content-related modeling is proposed to combine global and local features of infrared images, describing the common features of vary scenes robustly and enhancing the distinction between targets and backgrounds. Specifically, we analyzed and integrated multi-dimensional global statistical characteristics to construct a weighted spatial sum of nuclear norm, achieving a comprehensive background modeling and mitigating complex background clutters. On the other hand, we incorporated local distribution priors generated by target-constraint filter into the model to adaptively protect suspected target areas from suppression. Finally, we propose an efficient solving algorithm with stepwise reconstruction from seed-images sampled from infrared images, enabling linear-Time extraction of infrared small targets. Comparison experiments on SIRST, IRSTD-1k, NUDT-SIRST and NUST-SIRST datasets indicate that the proposed method enhances detection accuracy and reduces detection time compared to state-of-The-Art methods.
KW - content constraints
KW - Infrared small target detection
KW - Seed-image Step Reconstruction
UR - http://www.scopus.com/inward/record.url?scp=85214372445&partnerID=8YFLogxK
U2 - 10.1109/JSTARS.2024.3524551
DO - 10.1109/JSTARS.2024.3524551
M3 - Article
AN - SCOPUS:85214372445
SN - 1939-1404
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ER -