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
  • [31] Oriented Object Detection by Searching Corner Points in Remote Sensing Imagery
    Chen, Xueqing
    Ma, Li
    Du, Qian
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [32] Information balance network for multiscale object detection in remote sensing imagery
    Bin Wen
    Zhang, Jun
    Shen, Yanjun
    Xu, Bingrong
    JOURNAL OF ELECTRONIC IMAGING, 2024, 33 (06)
  • [33] Vehicle Object Detection in Remote Sensing Imagery Based on Multi-Perspective Convolutional Neural Network
    Yang, Chenxi
    Li, Wenjing
    Lin, Zhiyong
    ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2018, 7 (07)
  • [34] Multi-stage Image Restoration for High Resolution Panchromatic Imagery
    Lee, Sanghoon
    KOREAN JOURNAL OF REMOTE SENSING, 2016, 32 (06) : 551 - 566
  • [35] Multi-Oriented Object Detection in High-Resolution Remote Sensing Imagery Based on Convolutional Neural Networks with Adaptive Object Orientation Features
    Dong, Zhipeng
    Wang, Mi
    Wang, Yanli
    Liu, Yanxiong
    Feng, Yikai
    Xu, Wenxue
    REMOTE SENSING, 2022, 14 (04)
  • [36] Semantic-Edge-Supervised Single-Stage Detector for Oriented Object Detection in Remote Sensing Imagery
    Cao, Dujuan
    Zhu, Changming
    Hu, Xinxin
    Zhou, Rigui
    REMOTE SENSING, 2022, 14 (15)
  • [37] Revealing the Unseen: A Single-Stage Attention Based Occluded Object Detection Model in Remote Sensing Imagery
    Saini, Nandini
    Chattopadhyay, Chiranjoy
    Das, Debasis
    PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2023, 2023, 14301 : 540 - 547
  • [38] FREE TRAINING OBJECT DETECTION BASED ON MULTI-STAGE FUSION USING BELIEF FUNCTIONS
    Farhat, Mariem
    Mhiri, Slim
    Tagina, Moncef
    2016 INTERNATIONAL SYMPOSIUM ON SIGNAL, IMAGE, VIDEO AND COMMUNICATIONS (ISIVC), 2016, : 153 - 158
  • [39] Object Detection in High Resolution Remote Sensing Imagery Based on Convolutional Neural Networks With Suitable Object Scale Features
    Dong, Zhipeng
    Wang, Mi
    Wang, Yanli
    Zhu, Ying
    Zhang, Zhiqi
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (03): : 2104 - 2114
  • [40] Multiresolution registration of remote sensing imagery by optimization of mutual information using a stochastic gradient
    Cole-Rhodes, AA
    Johnson, KL
    LeMoigne, J
    Zavorin, I
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2003, 12 (12) : 1495 - 1511