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
  • [31] AVALANCHE DETECTION IN SAR IMAGES USING DEEP LEARNING
    Waldeland, Anders U.
    Reksten, Jarle Hamar
    Salberg, Arnt-Borre
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 2386 - 2389
  • [32] CHIRP SCALING BASED DETECTION OF MOVING TARGETS IN SAR IMAGES
    Cristallini, Diego
    Lombardo, Pierfrancesco
    Pastina, Debora
    Mennella, Angela
    2009 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-5, 2009, : 3765 - 3768
  • [33] Ensemble-based deep learning model for welding defect detection and classification
    Vasan, Vinod
    Sridharan, Naveen Venkatesh
    Balasundaram, Rebecca Jeyavadhanam
    Vaithiyanathan, Sugumaran
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 136
  • [34] Deep learning model-based algorithm for SAR ATR
    Friedlander, Robert D.
    Levy, Michael
    Sudkamp, Elizabeth
    Zelnio, Edmund
    ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXV, 2018, 10647
  • [35] Object detection using deep ensemble model for enhancing security towards sustainable agriculture
    Singh P.
    Krishnamurthi R.
    International Journal of Information Technology, 2023, 15 (6) : 3113 - 3126
  • [36] Change Detection in SAR Images Based on Deep Learning
    Hatem Magdy Keshk
    Xu-Cheng Yin
    International Journal of Aeronautical and Space Sciences, 2020, 21 : 549 - 559
  • [37] Classification of SAR and PolSAR images using deep learning: a review
    Parikh, Hemani
    Patel, Samir
    Patel, Vibha
    INTERNATIONAL JOURNAL OF IMAGE AND DATA FUSION, 2020, 11 (01) : 1 - 32
  • [38] Target Classification Using the Deep Convolutional Networks for SAR Images
    Chen, Sizhe
    Wang, Haipeng
    Xu, Feng
    Jin, Ya-Qiu
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (08): : 4806 - 4817
  • [39] Object Detection from SAR Images based on Curvelet Despeckling
    Devapal, Devi
    Hashna, N.
    Aparna, V. P.
    Bhavyasree, C.
    Mathai, Jeena
    Soman, Sangeetha K.
    MATERIALS TODAY-PROCEEDINGS, 2019, 11 : 1102 - 1116
  • [40] Change Detection in SAR Images Based on Deep Learning
    Keshk, Hatem Magdy
    Yin, Xu-Cheng
    INTERNATIONAL JOURNAL OF AERONAUTICAL AND SPACE SCIENCES, 2020, 21 (02) : 549 - 559