Infrared Small Target Detection via Low-Rank Tensor Completion With Top-Hat Regularization

正规化(语言学) 杂乱 计算机科学 人工智能 结构张量 模式识别(心理学) 秩(图论) 张量(固有定义) 红外线的 算法 计算机视觉 数学 雷达 物理 图像(数学) 光学 组合数学 电信 纯数学
作者
Hu Zhu,Shiming Liu,Lizhen Deng,Yansheng Li,Fu Xiao
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:58 (2): 1004-1016 被引量:230
标识
DOI:10.1109/tgrs.2019.2942384
摘要

Infrared small target detection technology is one of the key technologies in the field of computer vision. In recent years, several methods have been proposed for detecting small infrared targets. However, the existing methods are highly sensitive to challenging heterogeneous backgrounds, which are mainly due to: 1) infrared images containing mostly heavy clouds and chaotic sea backgrounds and 2) the inefficiency of utilizing the structural prior knowledge of the target. In this article, we propose a novel approach for infrared small target detection in order to take both the structural prior knowledge of the target and the self-correlation of the background into account. First, we construct a tensor model for the high-dimensional structural characteristics of multiframe infrared images. Second, inspired by the low-rank background and morphological operator, a novel method based on low-rank tensor completion with top-hat regularization is proposed, which integrates low-rank tensor completion and a ring top-hat regularization into our model. Third, a closed solution to the optimization algorithm is given to solve the proposed tensor model. Furthermore, the experimental results from seven real infrared sequences demonstrate the superiority of the proposed small target detection method. Compared with traditional baseline methods, the proposed method can not only achieve an improvement in the signal-to-clutter ratio gain and background suppression factor but also provide a more robust detection model in situations with low false-positive rates.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
n11发布了新的文献求助10
刚刚
李李完成签到,获得积分10
刚刚
刚刚
yolo完成签到 ,获得积分10
刚刚
1秒前
所所的应助被songsheng采纳,获得10
1秒前
zzhou完成签到,获得积分10
1秒前
Yy发布了新的文献求助10
1秒前
情怀的应助被核桃采纳,获得10
1秒前
晴天发布了新的文献求助10
2秒前
顾矜的应助被核桃采纳,获得10
2秒前
清辉影发布了新的文献求助10
2秒前
清辉影发布了新的文献求助10
2秒前
田様的应助被核桃采纳,获得10
2秒前
清辉影发布了新的文献求助30
2秒前
共享精神的应助被核桃采纳,获得10
2秒前
清辉影发布了新的文献求助10
2秒前
可爱的函函的应助被核桃采纳,获得10
2秒前
汉堡包的应助被核桃采纳,获得10
2秒前
2秒前
852的应助被核桃采纳,获得10
2秒前
科目三的应助被核桃采纳,获得10
2秒前
Lucas的应助被核桃采纳,获得10
2秒前
英姑的应助被核桃采纳,获得10
3秒前
zzk发布了新的文献求助10
3秒前
04d的应助被luchong采纳,获得10
3秒前
坚定的珊珊完成签到 ,获得积分10
3秒前
曾宪煌发布了新的文献求助10
3秒前
4秒前
华仔的应助被dbyte采纳,获得10
4秒前
世外仙姝发布了新的文献求助10
5秒前
Lily发布了新的文献求助10
5秒前
xm完成签到,获得积分10
5秒前
5秒前
5秒前
5秒前
清辉影发布了新的文献求助10
5秒前
稳健发布了新的文献求助30
6秒前
lllliiii发布了新的文献求助10
7秒前
田様的应助被corleeang采纳,获得10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183142
求助须知:如何正确求助?哪些是违规求助? 9572420
关于积分的说明 21825253
捐赠科研通 7779922
什么是DOI,文献DOI怎么找? 3433850
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480124