UNSUPERVISED AUTOMATIC TARGET DETECTION FOR MULTITEMPORAL SAR IMAGES BASED ON ADAPTIVE K-MEANS ALGORITHM

被引：0

作者：

Campos, Alexandre B. ^{[1
,2
]}

Molin, Ricardo D., Jr. ^{[1
,3
]}

Vu, Viet T. ^{[2
]}

Pettersson, Mats, I ^{[2
]}

Machado, Renato ^{[1
]}

机构：

[1] Aeronaut Inst Technol ITA, BR-12228900 Sao Jose Dos Campos, SP, Brazil

[2] Blekinge Inst Technol BTH, SE-37179 Karlskrona, Sweden

[3] German Aerosp Ctr DLR, D-82234 Wessling, Germany

来源：

IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2020年

关键词：

Automatic target detection; CARABAS-II; k-means; SAR images; unsupervised change detection;

D O I：

10.1109/IGARSS39084.2020.9324678

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present an unsupervised automatic target detection algorithm for multitemporal SAR images. The proposed two-fold method is expected to reduce processing time for large scene sizes with sparse targets while still improving detection performance. Firstly, pixel blocks are extracted from an initial change map to reduce the algorithm's search space and favor target detection. Secondly, an adaptive k-means algorithm selects the number of clusters that better separates targets from false alarms, which are discarded. Preliminary results show the advantages of the proposed method in processing time and detection performance over a recently proposed supervised method for the CARABAS-II dataset.

引用

页码：328 / 331

页数：4

共 50 条

[41] Background Subtraction Based on Threshold detection using Modified K-Means Algorithm
Kumar, A. Niranjil
Sureshkumar, C.
2013 INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, INFORMATICS AND MEDICAL ENGINEERING (PRIME), 2013,
[42] A K-means algorithm based on characteristics of density applied to network intrusion detection
Xu, Jing
Han, Dezhi
Li, Kuan-Ching
Jiang, Hai
COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2020, 17 (02) : 665 - 687
[43] Laplacian pyramid-based change detection in multitemporal SAR images
Geetha, R. Vijaya
Kalaivani, S.
EUROPEAN JOURNAL OF REMOTE SENSING, 2019, 52 (01) : 463 - 483
[44] Motion-based Moving Object Detection and Tracking using Automatic K-means
Keivani, Arghavan
Tapamo, Jules-Raymond
Ghayoor, Farzad
2017 IEEE AFRICON, 2017, : 32 - 37
[45] Vision-based corridor line detection using K-means algorithm
Lho, Hyung-Suk
Kwon, Ji-Wook
Chwa, Dongkyoung
Hong, Suk-Kyo
2007 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS, VOLS 1-6, 2007, : 2679 - 2683
[46] Image Object Extraction Based on Semantic Detection and Improved K-Means Algorithm
Rong, Hanxiao
Ramirez-Serrano, Alex
Guan, Lianwu
Gao, Yanbin
IEEE ACCESS, 2020, 8 : 171129 - 171139
[47] ADAPTIVE K-MEANS METHOD FOR SEGMENTING IMAGES UNDER NATURAL ENVIRONMENT
Abdullah, Sharifah Lailee Syed
Hambali, Hamirul'Aini
Jamil, Nursuriati
COMPUTING & INFORMATICS, 4TH INTERNATIONAL CONFERENCE, 2013, 2013, : 115 - +
[48] Automatic centroid initialization in k-means using artificial hummingbird algorithm
Kusum Preeti
undefined Deep
Neural Computing and Applications, 2025, 37 (5) : 3373 - 3398
[49] Development of a Corruption Detection Algorithm using K-means Clustering
Islam, Md. Tawheedul
Abu Yousuf, Mohammad
2018 INTERNATIONAL CONFERENCE ON ADVANCEMENT IN ELECTRICAL AND ELECTRONIC ENGINEERING (ICAEEE), 2018,
[50] Hybridization of K-Means and Firefly Algorithm for intrusion detection system
Kaur A.
Pal S.K.
Singh A.P.
International Journal of System Assurance Engineering and Management, 2018, 9 (04) : 901 - 910

← 1 2 3 4 5 →