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
  • [1] Multi-stage progressive change detection on high resolution remote sensing imagery
    Ning, Xiaogang
    Zhang, Hanchao
    Zhang, Ruiqian
    Huang, Xiao
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2024, 207 : 231 - 244
  • [2] Cascaded Object Detection Algorithm in Remote Sensing Imagery
    Zhang X.
    Li C.
    Xu J.
    Xie J.
    Cui Z.
    Yang J.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2021, 33 (10): : 1524 - 1531
  • [3] Multi-Stage Feature Fusion Object Detection Method for Remote Sensing Image
    Chen L.
    Zhang F.
    Guo W.
    Huang Y.
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2023, 51 (12): : 3520 - 3528
  • [4] NOVEL OBJECT DETECTION IN REMOTE SENSING IMAGERY
    Du, Dawei
    Funk, Christopher
    Doctor, Katarina
    Hoogs, Anthony
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 5798 - 5801
  • [5] Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
    Azimi, Seyed Majid
    Vig, Eleonora
    Bahmanyar, Reza
    Koerner, Marco
    Reinartz, Peter
    COMPUTER VISION - ACCV 2018, PT III, 2019, 11363 : 150 - 165
  • [6] YOLOrs: Object Detection in Multimodal Remote Sensing Imagery
    Sharma, Manish
    Dhanaraj, Mayur
    Karnam, Srivallabha
    Chachlakis, Dimitris G.
    Ptucha, Raymond
    Markopoulos, Panos P.
    Saber, Eli
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 1497 - 1508
  • [7] YOLOrs: Object Detection in Multimodal Remote Sensing Imagery
    Sharma, Manish
    Dhanaraj, Mayur
    Karnam, Srivallabha
    Chachlakis, Dimitris G.
    Ptucha, Raymond
    Markopoulos, Panos P.
    Saber, Eli
    Markopoulos, Panos P. (pxmeee@rit.edu), 1600, Institute of Electrical and Electronics Engineers Inc. (14): : 1497 - 1508
  • [8] Multi-stage Reinforcement Learning for Object Detection
    Koenig, Jonas
    Malberg, Simon
    Martens, Martin
    Niehaus, Sebastian
    Krohn-Grimberghe, Artus
    Ramaswamy, Arunselvan
    ADVANCES IN COMPUTER VISION, CVC, VOL 1, 2020, 943 : 178 - 191
  • [9] THE REGISTRATION OF HIGH-RESOLUTION REMOTE SENSING IMAGE USING MULTI-FEATURE AND MULTI-STAGE STRATEGY
    Liu, Jiang
    Zhang, Ye
    Zhang, Junping
    2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2014, : 1612 - 1615
  • [10] Multi-scale object detection in remote sensing imagery with convolutional neural networks
    Deng, Zhipeng
    Sun, Hao
    Zhou, Shilin
    Zhao, Juanping
    Lei, Lin
    Zou, Huanxin
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 145 : 3 - 22