A hierarchical object detection method in large-scale optical remote sensing satellite imagery using saliency detection and CNN

被引:27
|
作者
Song, Zhina [1 ]
Sui, Haigang [2 ]
Hua, Li [3 ]
机构
[1] Coll Wuhan Univ, Remote Sensing & Informat Engn, Wuhan, Peoples R China
[2] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, 129 Luoyu Rd, Wuhan, Hubei, Peoples R China
[3] Huazhong Agr Univ, Coll Resources & Environm, Wuhan, Peoples R China
基金
中国国家自然科学基金;
关键词
AUTOMATIC SHIP DETECTION; AIRPLANE DETECTION; AIRPORT DETECTION; NETWORKS; CLASSIFICATION; EFFICIENT; FUSION;
D O I
10.1080/01431161.2020.1826059
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Detecting geospatial objects, especially small, time-sensitive targets such as airplanes and ships in cluttered scenes, is a substantial challenge in large-scale, high-resolution optical satellite images. Directly detecting targets in countless image blocks results in higher false alarms and is also inefficient. In this paper, we introduce a hierarchical architecture to quickly locate related areas and detect these targets effectively. In the coarse layer, we use an improved saliency detection model that utilizes geospatial priors and multi-level saliency features to probe suspected regions in broad and complicated remote sensing images. Then, in the fine layer of each region, an efficacious end-to-end neural network that predicts the categories and locations of the objects is adopted. To improve the detection performance, an enhanced network, adaptive multi-scale anchors, and an improved loss function are designed to overcome the great diversity and complexity of backgrounds and targets. The experimental results obtained for both a public dataset and our collected images validated the effectiveness of our proposed method. In particular, for large-scale images (more than 500 km(2)), the adopted method far surpasses most unsupervised saliency models in terms of the performance in region saliency detection and can quickly detect targets within 1 minute, with 95.0% recall and 93.2% precision rates on average.
引用
收藏
页码:2827 / 2847
页数:21
相关论文
共 50 条
  • [41] AN IMPROVED OBJECT DETECTION CNN MODULE FOR REMOTE SENSING IMAGES
    Li, Yingqi
    He, Lin
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 1173 - 1176
  • [42] Object Detection Based on Sparse Representation and Hough Voting for Optical Remote Sensing Imagery
    Yokoya, Naoto
    Iwasaki, Akira
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2015, 8 (05) : 2053 - 2062
  • [43] A Small-Ship Object Detection Method for Satellite Remote Sensing Data
    Fan, Xiyu
    Hu, Zhuhua
    Zhao, Yaochi
    Chen, Junfei
    Wei, Tianjiao
    Huang, Zixun
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 11886 - 11898
  • [44] OBJECT DETECTION AND INSTANCE SEGMENTATION IN REMOTE SENSING IMAGERY BASED ON PRECISE MASK R-CNN
    Su, Hao
    Wei, Shunjun
    Yan, Min
    Wang, Chen
    Shi, Jun
    Zhang, Xiaoling
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 1454 - 1457
  • [45] Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
    Seydi, Seyd Teymoor
    Hasanlou, Mahdi
    Amani, Meisam
    Huang, Weimin
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 10941 - 10952
  • [46] AN AUTOMATIC APPROACH FOR CHANGE DETECTION IN LARGE-SCALE REMOTE SENSING IMAGES
    Liu, Sicong
    Ye, Zhen
    Tong, Xiaohua
    Zheng, Yongjie
    2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 5480 - 5483
  • [47] Cascade Saliency Attention Network for Object Detection in Remote Sensing Images
    Yu, Dayang
    Zhang, Rong
    Qin, Shan
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 217 - 223
  • [48] FEATURE-ATTENTIONED OBJECT DETECTION IN REMOTE SENSING IMAGERY
    Li, Chengzheng
    Xu, Chunyan
    Cui, Zhen
    Wang, Dan
    Zhang, Tong
    Yang, Jian
    2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 3886 - 3890
  • [49] Automatic Cloud Detection in Remote Sensing Imagery Using Saliency-Based Mixed Features
    Wang, Mi
    Wang, Xinsheng
    Pi, Yingdong
    Ke, Shiyun
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [50] Ship detection and classification based on cascaded detection of hull and wake from optical satellite remote sensing imagery
    Liu, Yingfei
    Zhang, Ruihao
    Deng, Ruru
    Zhao, Jun
    GISCIENCE & REMOTE SENSING, 2023, 60 (01)