High Quality Object Detection for Multiresolution Remote Sensing Imagery Using Cascaded Multi-Stage Detectors

被引:5
|
作者
Wu, Binglong [1 ,2 ]
Shen, Yuan [1 ]
Guo, Shanxin [1 ,3 ]
Chen, Jinsong [1 ,3 ]
Sun, Luyi [1 ,3 ]
Li, Hongzhong [1 ,3 ]
Ao, Yong [2 ]
机构
[1] Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr Geospatial Informat, Shenzhen 518055, Peoples R China
[2] Changan Univ, Sch Earth Sci & Resources, 126 Yanta Rd, Xian 710054, Peoples R China
[3] Shenzhen Engn Lab Ocean Environm Big Data Anal &, Shenzhen 518055, Peoples R China
基金
中国国家自然科学基金;
关键词
object detection; cascaded detectors; Intersection over Union (IoU) threshold; classification ensemble; bounding box regression; multiresolution remote sensing images; NETWORK; TEMPLATE;
D O I
10.3390/rs14092091
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Deep-learning-based object detectors have substantially improved state-of-the-art object detection in remote sensing images in terms of precision and degree of automation. Nevertheless, the large variation of the object scales makes it difficult to achieve high-quality detection across multiresolution remote sensing images, where the quality is defined by the Intersection over Union (IoU) threshold used in training. In addition, the imbalance between the positive and negative samples across multiresolution images worsens the detection precision. Recently, it was found that a Cascade region-based convolutional neural network (R-CNN) can potentially achieve a higher quality of detection by introducing a cascaded three-stage structure using progressively improved IoU thresholds. However, the performance of Cascade R-CNN degraded when the fourth stage was added. We investigated the cause and found that the mismatch between the ROI features and the classifier could be responsible for the degradation of performance. Herein, we propose a Cascade R-CNN++ structure to address this issue and extend the three-stage architecture to multiple stages for general use. Specifically, for cascaded classification, we propose a new ensemble strategy for the classifier and region of interest (RoI) features to improve classification accuracy at inference. In localization, we modified the loss function of the bounding box regressor to obtain higher sensitivity around zero. Experiments on the DOTA dataset demonstrated that Cascade R-CNN++ outperforms Cascade R-CNN in terms of precision and detection quality. We conducted further analysis on multiresolution remote sensing images to verify model transferability across different object scales.
引用
收藏
页数:18
相关论文
共 50 条
  • [41] An Efficient and Robust Integrated Geospatial Object Detection Framework for High Spatial Resolution Remote Sensing Imagery
    Han, Xiaobing
    Zhong, Yanfei
    Zhang, Liangpei
    REMOTE SENSING, 2017, 9 (07)
  • [42] Mean-shift based object detection and clustering from high resolution remote sensing imagery
    SushmaLeela, T.
    chandrakanth, R.
    Saibaba, J.
    Varadan, Geeta
    Mohan, Sambhu S.
    2013 FOURTH NATIONAL CONFERENCE ON COMPUTER VISION, PATTERN RECOGNITION, IMAGE PROCESSING AND GRAPHICS (NCVPRIPG), 2013,
  • [43] Object-based quality evaluation procedure for fused remote sensing imagery
    Rodriguez-Esparragon, Dionisio
    Marcello, Javier
    Eugenio, Francisco
    Garcia-Pedrero, Angel
    Gonzalo-Martin, Consuelo
    NEUROCOMPUTING, 2017, 255 : 40 - 51
  • [44] Multi-stage detection using constellation structure
    Sen Gupta, Ananya
    Singer, Andrew C.
    2006 FORTIETH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, VOLS 1-5, 2006, : 585 - +
  • [45] Evaluation of Urban Road Vehicle Detection from High Resolution Remote Sensing Imagery Using Object-oriented Method
    Tan, Qulin
    Wei, Qingchao
    Yang, Songlin
    Wang, Jinfei
    2009 JOINT URBAN REMOTE SENSING EVENT, VOLS 1-3, 2009, : 284 - +
  • [46] CHANGE DETECTION FOR HIGH-RESOLUTION REMOTE SENSING IMAGERY USING OBJECT-ORIENTED CHANGE VECTOR ANALYSIS METHOD
    Li, Liang
    Li, Xue
    Zhang, Yun
    Wang, Lei
    Ying, Guowei
    2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 2873 - 2876
  • [47] Attentive context and semantic enhancement mechanism for printed circuit board defect detection with two-stage and multi-stage object detectors
    Kiobya, Twahir
    Zhou, Junfeng
    Maiseli, Baraka
    Khan, Maqbool
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [48] Aan Accurate Multi-Stage Energy Detection Spectrum Sensing
    Shata, Amr M.
    Nasr, Omar A.
    Fahmy, Yasmine A.
    2016 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, 2016,
  • [49] High-Quality Angle Prediction for Oriented Object Detection in Remote Sensing Images
    Wang, Guanchun
    Zhang, Xiangrong
    Zhu, Peng
    Tang, Xu
    Chen, Puhua
    Jiao, Licheng
    Zhou, Huiyu
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [50] ANGLE TOKENIZATION GUIDED MULTI-SCALE VISION TRANSFORMER FOR ORIENTED OBJECT DETECTION IN REMOTE SENSING IMAGERY
    Zhang, Cong
    Liu, Tianshan
    Lam, Kin-Man
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 3063 - 3066