Online Active Learning for Automatic Target Recognition

被引:18
|
作者
Kriminger, Evan [1 ]
Cobb, J. Tory [2 ]
Principe, Jose C. [1 ]
机构
[1] Univ Florida, Dept Elect & Comp Engn, Gainesville, FL 32611 USA
[2] Naval Surface Warfare Ctr Panama City Div, Panama City, FL 32407 USA
关键词
Active learning; automatic target recognition; sonar imaging; SIDESCAN SONAR; IMAGERY;
D O I
10.1109/JOE.2014.2340353
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Automatic target recognition in sidescan sonar imagery is vital to many applications, particularly sea mine detection and classification. We expand upon the traditional offline supervised classification approach with an active learning method to automatically label new objects that are not present in the training set. This is facilitated by the option of sending difficult samples to an outlier bin, from which models can be built for new objects. The decisions of the classifier are improved by a novel active learning approach, called model trees (MT), which builds an ensemble of hypotheses about the classification decisions that grows proportionally to the amount of uncertainty the system has about the samples. Our system outperforms standard active learning methods, and is shown to correctly identify new objects much more accurately than a pure clustering approach, on a simulated sidescan sonar data set.
引用
收藏
页码:583 / 591
页数:9
相关论文
共 50 条
  • [21] XCS for robust automatic target recognition
    Ravichandran, B.
    Gandhe, Avinash
    Smith, R. E.
    GECCO 2005: Genetic and Evolutionary Computation Conference, Vols 1 and 2, 2005, : 1803 - 1810
  • [22] Active and adaptive ensemble learning for online activity recognition from data streams
    Krawczyk, Bartosz
    KNOWLEDGE-BASED SYSTEMS, 2017, 138 : 69 - 78
  • [23] Online active learning for human activity recognition from sensory data streams
    Mohamad, Saad
    Sayed-Mouchaweh, Moamar
    Bouchachia, Abdelhamid
    NEUROCOMPUTING, 2020, 390 (390) : 341 - 358
  • [24] Active Learning for Recognition of Shipwreck Target in Side-Scan Sonar Image
    Zhu, Bangyan
    Wang, Xiao
    Chu, Zhengwei
    Yang, Yi
    Shi, Juan
    REMOTE SENSING, 2019, 11 (03)
  • [25] Deep Learning for on-board AUV Automatic Target Recognition for Optical and Acoustic imagery
    Zacchini, Leonardo
    Ridolfi, Alessandro
    Topini, Alberto
    Secciani, Nicola
    Bucci, Alessandro
    Topini, Edoardo
    Allotta, Benedetto
    IFAC PAPERSONLINE, 2020, 53 (02): : 14589 - 14594
  • [26] Multistage approach for automatic target detection and recognition in infrared imagery using deep learning
    Baili, Nada
    Moalla, Mahdi
    Frigui, Hichem
    Karem, Andrew D.
    JOURNAL OF APPLIED REMOTE SENSING, 2022, 16 (04)
  • [27] ISAR target parameter estimation with application for automatic target recognition
    Melendez, KA
    Bennett, JR
    RADAR PROCESSING, TECHNOLOGY, AND APPLICATIONS III, 1998, 3462 : 2 - 13
  • [28] ARTIFICIAL NEURAL NETWORKS FOR AUTOMATIC TARGET RECOGNITION
    DANIELL, CE
    KEMSLEY, DH
    LINCOLN, WP
    TACKETT, WA
    BARAGHIMIAN, GA
    OPTICAL ENGINEERING, 1992, 31 (12) : 2521 - 2531
  • [29] Automatic Target Recognition Using Multiple-Aspect Sonar Images
    Wang, Xiaoguang
    Liu, Xuan
    Japkowicz, Nathalie
    Matwin, Stan
    Bao Nguyen
    2014 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2014, : 2330 - 2337
  • [30] Performance modeling for automatic target recognition systems
    Catlin, A
    Myers, L
    Bauer, K
    Rogers, S
    Broussard, R
    ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY IV, 1997, 3070 : 185 - 193