Deep ensemble model-based moving object detection and classification using SAR images

被引:1
|
作者
Paramasivam, Ramya [1 ]
Kumar, Prashanth [2 ]
Lai, Wen-Cheng [3 ]
Bidare Divakarachari, Parameshachari [4 ]
机构
[1] Mahendra Engn Coll, Dept Comp Sci Engn, Mallasamudram, India
[2] Univ Newcastle, Coll Engn Sci & Environm, Sch Informat & Phys Sci, Callaghan, NSW, Australia
[3] Ming Chi Univ Technol, Dept Elect Engn, New Taipei City, Taiwan
[4] Nitte Meenakshi Inst Technol, Dept Elect & Commun Engn, Bengaluru, India
关键词
bidirectional long short-term memory; improved deep belief network; moving object detection; recurrent neural network; synthetic aperture radar images; SHIP DETECTION; NETWORK; TARGETS;
D O I
10.3389/feart.2023.1288003
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
In recent decades, image processing and computer vision models have played a vital role in moving object detection on the synthetic aperture radar (SAR) images. Capturing of moving objects in the SAR images is a difficult task. In this study, a new automated model for detecting moving objects is proposed using SAR images. The proposed model has four main steps, namely, preprocessing, segmentation, feature extraction, and classification. Initially, the input SAR image is pre-processed using a histogram equalization technique. Then, the weighted Otsu-based segmentation algorithm is applied for segmenting the object regions from the pre-processed images. When using the weighted Otsu, the segmented grayscale images are not only clear but also retain the detailed features of grayscale images. Next, feature extraction is carried out by gray-level co-occurrence matrix (GLCM), median binary patterns (MBPs), and additive harmonic mean estimated local Gabor binary pattern (AHME-LGBP). The final step is classification using deep ensemble models, where the objects are classified by employing the ensemble deep learning technique, combining the models like the bidirectional long short-term memory (Bi-LSTM), recurrent neural network (RNN), and improved deep belief network (IDBN), which is trained with the features extracted previously. The combined models increase the accuracy of the results significantly. Furthermore, ensemble modeling reduces the variance and modeling method bias, which decreases the chances of overfitting. Compared to a single contributing model, ensemble models perform better and make better predictions. Additionally, an ensemble lessens the spread or dispersion of the model performance and prediction accuracy. Finally, the performance of the proposed model is related to the conventional models with respect to different measures. In the mean-case scenario, the proposed ensemble model has a minimum error value of 0.032, which is better related to other models. In both median- and best-case scenario studies, the ensemble model has a lower error value of 0.029 and 0.015.
引用
收藏
页数:18
相关论文
共 50 条
  • [11] Object Classification using Ensemble of Local and Deep Features
    Srivastava, Siddharth
    Mukherjee, Prerana
    Lall, Brejesh
    Jaiswal, Kamlesh
    2017 NINTH INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION (ICAPR), 2017, : 139 - 144
  • [12] Model-based coding of SAR and ultrasound images
    do Rosiles, JEG
    Smith, MJT
    ICECS 2000: 7TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS & SYSTEMS, VOLS I AND II, 2000, : 62 - 65
  • [13] MODEL-BASED SUPERPIXEL SEGMENTATION OF SAR IMAGES
    Kayabol, Koray
    2015 23RD EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2015, : 1800 - 1804
  • [14] Ensemble Learning Based Classification of High Resolution SAR Images
    Turkmenli, Ilter
    Kayabol, Koray
    2019 27TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2019,
  • [15] Fishing Vessel Classification in SAR Images Using a Novel Deep Learning Model
    Guan, Yanan
    Zhang, Xi
    Chen, Siwei
    Liu, Genwang
    Jia, Yongjun
    Zhang, Yi
    Gao, Gui
    Zhang, Jie
    Li, Zhongwei
    Cao, Chenghui
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [16] Moving target detection using 2 SAR images
    Oriot, Helene
    Flecheux, Marc
    2017 IEEE RADAR CONFERENCE (RADARCONF), 2017, : 1064 - 1068
  • [17] Model-based classification of radar images
    Chiang, HC
    Moses, RL
    Potter, LC
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2000, 46 (05) : 1842 - 1854
  • [18] Moving Vehicle Detection Based on RPCA Using Multisquint Spaceborne SAR Images
    Li, Yulun
    Li, Chunsheng
    Yang, Wei
    Wang, Yamin
    Li, Yihan
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [19] Deep learning based moving object detection for oblique images without future frames
    Heo, Won Yeong
    Kim, Seongjo
    Yoon, DeukRyeol
    Jeong, Jongmin
    Sung, HyunSeong
    AUTOMATIC TARGET RECOGNITION XXX, 2020, 11394
  • [20] Classification of SAR images based on deep deconvolutional network
    Wang, Yunyan
    He, Chu
    Zhao, Shouneng
    Chen, Dong
    Liao, Mingsheng
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2015, 40 (10): : 1371 - 1376