Remote Sensing Technology and Application, Volume. 39, Issue 5, 1249(2024)

Comparison of the Deep Learning Algorithms for Detecting Circular Ancient Tombs

Mingai TIAN, Lijun YU, Tingchen JIANG, Jianfeng ZHU, Danlu CAI, Siyi HUANG, Yuanzhi ZHANG, Yueping NIE, and Hui WANG
Author Affiliations
  • School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang222005, China
  • show less
    Figures & Tables(9)
    Study area (The collection area of self-built dataset-Altai region (except the area covered by images A, B and C), test area for satellite images–A, B and C
    Example of ancient circular tomb
    Precision-recall curve of different algorithms
    Example of the detection results for test set
    Example of detection results from satellite images
    • Table 1. Comparison of evaluation indexes of different algorithms

      View table
      View in Article

      Table 1. Comparison of evaluation indexes of different algorithms

      算法名称APFPS/(frame·s-1)
      Faster R-CNN0.6317.54
      Cascade R-CNN0.7819.25
      YOLOv50.8174.23
      YOLOv70.8785.79
    • Table 2. Comparison of detection results by different algorithms on WorldView2/3 images

      View table
      View in Article

      Table 2. Comparison of detection results by different algorithms on WorldView2/3 images

      算法名称TPFPFNPrecisionRecall
      Faster R-CNN3019210.610.59
      Cascade R-CNN3612150.750.71
      YOLOv53911120.780.76
      YOLOv742790.860.82
    • Table 3. Comparison of detection results on WorldView2 and GF2 images in the same region

      View table
      View in Article

      Table 3. Comparison of detection results on WorldView2 and GF2 images in the same region

      算法名称TPFPFNPrecisionRecall
      WorldView2GF2WorldView2GF2WorldView2GF2WorldView2GF2WorldView2GF2
      Faster R-CNN111068780.650.560.610.56
      Cascade R-CNN131145570.760.690.720.61
      YOLOv5131334550.810.760.720.72
      YOLOv7151422340.880.880.830.78
    • Table 4. Comparison of the method in this paper with other cases of tomb detection

      View table
      View in Article

      Table 4. Comparison of the method in this paper with other cases of tomb detection

      应用场景检测目标模型PrecisionRecallAP参考
      欧亚草原墓葬CNN1.000.84-Caspari等(2019)
      阿尔泰山脉俄罗斯部分区域墓葬Cascade R-CNN0.300.600.52Chen等(2021)
      加利比亚地区墓葬YOLOv30.970.640.68Berganzo-Besga等(2021)
      荷兰中部地区墓葬、炭窑和田地Faster R-CNN0.900.710.79Verschoof-van der Vaart等(2021)
      新疆阿勒泰地区墓葬YOLOv70.910.930.87本文方法
    Tools

    Get Citation

    Copy Citation Text

    Mingai TIAN, Lijun YU, Tingchen JIANG, Jianfeng ZHU, Danlu CAI, Siyi HUANG, Yuanzhi ZHANG, Yueping NIE, Hui WANG. Comparison of the Deep Learning Algorithms for Detecting Circular Ancient Tombs[J]. Remote Sensing Technology and Application, 2024, 39(5): 1249

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Feb. 13, 2023

    Accepted: --

    Published Online: Jan. 7, 2025

    The Author Email:

    DOI:10.11873/j.issn.1004-0323.2024.5.1249

    Topics