All Issue

2025 Vol.67, Issue 2 Preview Page
Development of Agricultural Parcel Detection Model based on YOLO-Seg Using CAS500-1 Satellites Images

국토위성영상을 이용한 YOLO-Seg 기반의 농경지 추출 모델 개발

Solhee Kima
,
Jeongbae Jeonb
,
Seungwon Seokc
,
Jaeyoung Jungd
,
Taegon Kime†
김 솔희a
,
전 정배b
,
석 승원c
,
정 재영d
,
김 태곤e†
aAssistant Research Professor, Department of Smart Farm, Jeonbuk National University
bSenior Researcher, Spatial Information Research Institute, Korea Land and Geospatial Informatix Corporation
cResearcher, Department of Smart Farm, Jeonbuk National University
dResearcher, Department of Smart Farm, Jeonbuk National University
eAssistant Professor, Department of Smart Farm, Institute of Agricultural Science & Technology, Jeonbuk National University
† Corresponding author Tel.: +82-63-270-2557, Fax: +82-63-270-2556 E-mail: taegon@jbnu.ac.kr
2025. pp. 55-67
PDF XML Citation
Abstract

This study developed an agricultural parcel detection model based on the YOLO-Seg algorithm using high-resolution satellite imagery of CAS500-1 (Compact Advanced Satellite 500-1). We analyzed the effects of grid overlap and confidence threshold settings on object detection accuracy. The main results showed that a 60% grid overlap achieved optimal performance with 70% detection accuracy and about 5% false detection rate within one minute of processing time. By analyzing ratios of overlapping from 10% to 90%, the detection accuracy improved, but the processing time significantly increased, requiring a balance between accuracy and efficiency. The proposed method of spatial continuity correction using polygon centroids improved detection accuracy by approximately 5%p while significantly reducing false detection rates. The system demonstrated 80% detection accuracy when the confidence threshold was set between 0.5 and 0.7, which outperformed traditional detection methods. Additionally, our approach addressed the boundary detection issues in split grid analysis through an optimized overlap strategy. This automated detection system can be effectively applied to agricultural monitoring, resource management, and policy development, providing a cost-effective solution for large-scale agricultural parcel monitoring.

Keywords
YOLO
segmentation
satellite image
tiling move
image overlap
References

REFERENCES

1
H. J. Al Dawasari, M. Bilal, M. Moinuddin, K. Arshad and K. Assaleh, Sensors, DeepVision: Enhanced drone detection and recognition in visible imagery through deep learning networks, 23(21); 8711 (2023)10.3390/s2321871137960411PMC10649875
2
G. E. Abanoub, S. Elmoushy, A. E. Nagib and A. Atia, In 2024 Intelligent Methods, Systems, and Applications (IMSA)Improving land cover change detection using YOLO segmentation and comparative polygon analysis; 70-75, IEEE. (2024)10.1109/imsa61967.2024.10652756
3
R. B. Antwi, M. Kimollo, S. Y. Takyi, E. E. Ozguven, T. Sando, R. Moses and M. A. Dulebenets, Smart Cities, Turning features detection from aerial images: Model development and application on Florida's public roadways, 7(3); 1414-1440 (2024)10.3390/smartcities7030059
4
A. K. Bandla, N. R. Nagireddy, S. Ch, A. B. Shaik and T. Vanitha, Journal of Computational Analysis and Applications, AI in agriculture: Precision farming and crop monitoring, 33(4); 231-240, Available at: https://www.eudoxuspress.com/index.php/pub/article/view/652 (2024)
5
C. M. Badgujar, A. Poulose and H. Gan, arXiv preprint, Agricultural object detection with You Look Only Once (YOLO) algorithm: A bibliometric and systematic literature review, arXiv:2401.10379 (2024)10.48550/arXiv.2401.10379
6
Z. Cai and N. Vasconcelos, In Proceedings of the IEEE Conference on Computer Vision and Pattern RecognitionCascade R-CNN: Delving into high quality object detection; 6154-6162 (2018)10.1109/cvpr.2018.00644
7
S. Chen, S. Xiang, C. L. Liu and C. H. Pan, IEEE Geoscience and Remote Sensing Letters, Vehicle detection in satellite images by hybrid deep convolutional neural networks, 11(10); 1797-1801 (2014)10.1109/lgrs.2014.2309695
8
X. Chen, L. Deng, C. Hu, T. Xie and C. Wang, Applied Sciences, Dense small object detection based on an improved YOLOv7 model, 14(17); 7665 (2024)10.3390/app14177665
9
O. Decitre and K. E. Joyce, Drones, Using YOLOv5, SAHI, and GIS with drone mapping to detect giant clams on the Great Barrier Reef, 8(9); 458 (2024)10.3390/drones8090458
10
M. Everingham, S. M. A. Eslami, L. Van Gool, C. K. I. Williams, J. Winn and A. Zisserman, International Journal of Computer Vision, The Pascal Visual Object Classes Challenge: A retrospective, 111(1); 98-136 (2015)10.1007/s11263-014-0733-5
11
A. Farhadi and J. Redmon, In Computer Vision and Pattern RecognitionYolov3: An incremental improvement; 1-6, Berlin/Heidelberg, Germany. Springer. (2018)10.48550/arXiv.1804.02767
12
J. Franke and G. Menz, Precision Agriculture, Multi-temporal wheat disease detection by multi-spectral remote sensing, 8; 161-172 (2007)10.1007/s11119-007-9036-y
13
I. Hong, Journal of the Korean Cartographic Association, Land cover object detection using aerial photography and YOLOv5, 23(2); 37-48 (2023)10.16879/jkca.2023.23.2.037
14
G. Hulley, S. Hook, J. Fisher and C. Lee, In 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)ECOSTRESS, a NASA Earth-Ventures instrument for studying links between the water cycle and plant health over the diurnal cycle; 5494-5496, IEEE. (2017)10.1109/igarss.2017.8128248
15
F. S. Hosseini, M. B. Seo, S. V. Razavi-Termeh, A. Sadeghi-Niaraki, M. Jamshidi and S. M. Choi, Sustainability, Geospatial artificial intelligence (GeoAI) and satellite imagery fusion for soil physical property predicting, 15(19); 14125 (2023)10.3390/su151914125
16
Y. Inoue, Soil Science and Plant Nutrition, Satellite- and drone-based remote sensing of crops and soils for smart farming: A review, 66(6); 798-810 (2020)10.1080/00380768.2020.1738899
17
J. Jeon, Journal of Cadastre &Land InformatiX, Detecting high-resolution usage status of individual parcel of land using object detecting deep learning technique, 54(1); 19-32 (2024)10.22640/lxsiri.2024.54.1.19
18
G. Jocher, A. Chaurasia and J. Qiu, YOLO by Ultralytics (Version 8.0.0) [Computer software], Available at: https://github.com/ultralytics/ultralytics (2023)
19
S. Khanal, K. Kc, J. P. Fulton, S. Shearer and E. Ozkan, Remote Sensing, Remote sensing in agriculture—accomplishments, limitations, and opportunities, 12(22); 3783 (2020)10.3390/rs12223783
20
Y. Kang, Journal of the Korean Geographical Society, GeoAI application areas and research trends, 58(4); 395-418 (2023)10.22776/kgs.2023.58.4.395.18052372
21
H. Kim, R. Na, D. Joo, G. Choi and Y. Oh, Journal of Korean Society of Rural Planning, A study on the detection of solar power plant for high-resolution aerial imagery using YOLO v2, 28(2); 87-96 (2022)10.7851/ksrp.2022.28.2.087
22
S. Kim and Y. Lee, The Geographical Journal of Korea, Atmospheric correction of CAS500-1 images using 6SV-based AI model, 57(4); 587-595 (2023)10.22905/kaopqj.2023.57.4.16
23
S. Kunhoth and S. Al-Maadeed, Diagnostics, An analytical study on the utility of RGB and multispectral imagery with band selection for automated tumor grading, 14(15); 1625 (2024)10.3390/diagnostics1415162539125501PMC11312293
24
G. Lee, S. Kim and Y. Choi, Journal of the Korean Association of Geographic Information Studies, A comparative study of image classification method to detect water body based on UAS, 18(3); 113-127 (2015)10.11108/kagis.2015.18.3.113
25
T. Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár and C. L. Zitnick, In Computer Vision – ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VMicrosoft COCO: Common objects in context; 740-755, Springer International Publishing. (2014)10.1007/978-3-319-10602-1_48
26
M. Lippi, N. Bonucci, R. F. Carpio, M. Contarini, S. Speranza and A. Gasparri, In 2021 29th Mediterranean Conference on Control and Automation (MED)A YOLO-based pest detection system for precision agriculture; 342-347, IEEE. (2021)10.1109/med51440.2021.9480344
27
Y. Long, Y. Gong, Z. Xiao and Q. Liu, IEEE Transactions on Geoscience and Remote Sensing, Accurate object localization in remote sensing images based on convolutional neural networks, 55(5); 2486-2498 (2017)10.1109/tgrs.2016.2645610
28
V. Mnih and G. E. Hinton, In Computer Vision – ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part VILearning to detect roads in high-resolution aerial images; 210-223, Springer Berlin Heidelberg. (2010)10.1007/978-3-642-15567-3_16
29
T. T. Nguyen, T. D. Hoang, M. T. Pham, T. T. Vu, T. H. Nguyen, Q. T. Huynh and J. Jo, Applied Soft Computing, Monitoring agriculture areas with satellite images and deep learning, 95; 106565 (2020)10.1016/j.asoc.2020.106565
30
M. Peng, Y. Liu, A. Khan, B. Ahmed, S. K. Sarker, Y. Y. Ghadi, U. A. Bhatti, M. A. Razgen and Y. A. Ali, Big Data Research, Crop monitoring using remote sensing land use and land change data: Comparative analysis of deep learning methods using pre-trained CNN models, 36; 100448 (2024)10.1016/j.bdr.2024.100448
31
J. Redmon, S. Divvala, R. Girshick and A. Farhadi, In Proceedings of the IEEE Conference on Computer Vision and Pattern RecognitionYou only look once: Unified, real-time object detection; 779-788 (2016)10.1109/cvpr.2016.91
32
S. Ren, K. He, R. Girshick and J. Sun, IEEE Transactions on Pattern Analysis and Machine Intelligence, Faster R-CNN: Towards real-time object detection with region proposal networks, 39(6); 1137-1149 (2016)10.1109/tpami.2016.257703127295650
33
T. Y. Ross and G. K. H. P. Dollar, In Proceedings of the IEEE Conference on Computer Vision and Pattern RecognitionFocal loss for dense object detection; 2980-2988 (2017)10.1109/iccv.2017.324
34
A. Sharifi and H. Mahdipour, Environmental Earth Sciences, Utilizing geospatial artificial intelligence for remote sensing applications, 83; 274 (2024)10.1007/s12665-024-11584-4
35
A. Smith and R. Johnson, PIX4Dmapper Documentation, How to verify that there is enough overlap between the images; 89-105, Available at: https://support.pix4d.com/hc/en-us/articles/203756125 (2022)
36
Z. Tang, Z. Chen, F. Qi, L. Zhang and S. Chen, In 2021 IEEE International Conference on Data Mining (ICDM)Pest-YOLO: Deep image mining and multi-feature fusion for real-time agriculture pest detection; 1348-1353, IEEE. (2021)10.1109/icdm51629.2021.00169
37
A. Taravat, M. P. Wagner, R. Bonifacio and D. Petit, Remote Sensing, Advanced fully convolutional networks for agricultural field boundary detection, 13(4); 722 (2021)10.3390/rs13040722
38
M. P. Wagner and N. Oppelt, Remote Sensing, Deep learning and adaptive graph-based growing contours for agricultural field extraction, 12(12); 1990 (2020)10.3390/rs12121990
39
Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang and J. Xiao, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition3D ShapeNets: A deep representation for volumetric shapes; 1912-1920 (2015)10.1109/cvpr.2015.7298801
40
W. Xinming and T. S. Hong, AgBioForum, Comparative study on leaf disease identification using YOLO v4 and YOLO v7 algorithm, 25(1); 58-67 (2023)
41
X. Yang, Y. Song, Y. Zhou, Y. Liao, J. Yang, J. Huang, Y. Huang and Y. Bai, Remote Sensing, An efficient detection framework for aerial imagery based on uniform slicing window, 15(17); 4122 (2023)10.3390/rs15174122
42
Z. Yang, X. Wang, J. Wu, Y. Zhao, Q. Ma, X. Miao, L. Zhang and Z. Zhou, IEEE/ACM Transactions on Networking, EdgeDuet: Tiling small object detection for edge-assisted autonomous mobile vision, 31(4); 1765-1778 (2022)10.1109/tnet.2022.3223412
43
J. K. Yu, J. Ahn, G. D. Han, H. M. Kang, H. Jo and Y. S. Chung, Journal of Environmental Science International, Utilization of satellite technologies for agriculture, 33(7); 547-552 (2024)10.5322/jesi.2024.33.7.547
44
W. Zhang, H. Huang, Y. Sun and X. Wu, Frontiers in Plant Science, AgriPest-YOLO: A rapid light-trap agricultural pest detection method based on deep learning, 13; 1079384 (2022)10.3389/fpls.2022.107938436589124PMC9800973
45
W. Zhu, Y. Ying, J. Zhang, X. Wang and Y. Zheng, Neural Processing Letters, Point cloud registration network based on convolution fusion and attention mechanism, 55(9); 12625-12645 (2023)10.1007/s11063-023-11435-6
Information
  • Publisher :The Korean Society of Agricultural Engineers
  • Publisher(Ko) :한국농공학회
  • Journal Title :Journal of Korean Society of Agricultural Engineers
  • Journal Title(Ko) :한국농공학회논문집
  • Volume : 67
  • No :2
  • Pages :55-67
  • Received Date : 2024-11-27
  • Revised Date : 2025-02-18
  • Accepted Date : 2025-02-20
  • DOI :https://doi.org/10.5389/KSAE.2025.67.2.055
Journal Informaiton Journal of Korean Society of Agricultural Engineers Journal of Korean Society of Agricultural Engineers
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
Journal Informaiton Journal Informaiton - close