High-Precision Mango Orchard Mapping Using a Deep Learning Pipeline Leveraging Object Detection and Segmentation

被引:0
|
作者
Afsar, Muhammad Munir [1 ]
Bakhshi, Asim Dilawar [2 ]
Iqbal, Muhammad Shahid [3 ]
Hussain, Ejaz [1 ]
Iqbal, Javed [1 ]
机构
[1] Natl Univ Sci & Technol, Inst Geog Informat Syst, Islamabad 44000, Pakistan
[2] Natl Univ Sci & Technol, Mil Coll Signals, Dept Elect Engn, Rawalpindi 46000, Pakistan
[3] ARID Agr Univ, Inst Geoinformat & Earth Observat, Rawalpindi 46000, Pakistan
关键词
precision agriculture; mango orchard mapping; canopy segmentation; UAV; object detection; YOLOv7; segment anything model;
D O I
10.3390/rs16173207
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Precision agriculture-based orchard management relies heavily on the accurate delineation of tree canopies, especially for high-value crops like mangoes. Traditional GIS and remote sensing methods, such as Object-Based Imagery Analysis (OBIA), often face challenges due to overlapping canopies, complex tree structures, and varied light conditions. This study aims to enhance the accuracy of mango orchard mapping by developing a novel deep-learning approach that combines fine-tuned object detection and segmentation techniques. UAV imagery was collected over a 65-acre mango orchard in Multan, Pakistan, and processed into an RGB orthomosaic with a 3 cm ground sampling distance. The You Only Look Once (YOLOv7) framework was trained on an annotated dataset to detect individual mango trees. The resultant bounding boxes were used as prompts for the segment anything model (SAM) for precise delineation of canopy boundaries. Validation against ground truth data of 175 manually digitized trees showed a strong correlation (R2 = 0.97), indicating high accuracy and minimal bias. The proposed method achieved a mean absolute percentage error (MAPE) of 4.94% and root mean square error (RMSE) of 80.23 sq ft against manually digitized tree canopies with an average size of 1290.14 sq ft. The proposed approach effectively addresses common issues such as inaccurate bounding boxes and over- or under-segmentation of tree canopies. The enhanced accuracy can substantially assist in various downstream tasks such as tree location mapping, canopy volume estimation, health monitoring, and crop yield estimation.
引用
收藏
页数:20
相关论文
共 50 条
  • [31] Industrial Object Detection: Leveraging Synthetic Data for Training Deep Learning Models
    Ouarab, Sarah
    Boutteau, Remi
    Romeo, Katerine
    Lecomte, Christele
    Laignel, Aristid
    Ragot, Nicolas
    Duval, Fabrice
    INDUSTRIAL ENGINEERING AND APPLICATIONS-EUROPE, ICIEA-EU 2024, 2024, 507 : 200 - 212
  • [32] Sashimi: Automatic high-throughput pipeline for organismal image segmentation using deep learning
    Schwartz, S. T.
    Alfaro, M. E.
    INTEGRATIVE AND COMPARATIVE BIOLOGY, 2021, 61 : E1248 - E1249
  • [33] Individual Tree Segmentation Using Deep Learning and Climbing Algorithm: A Method for Achieving High-precision Single-tree Segmentation in High-density Forests under Complex Environments
    Ma, He
    Zhang, Fangmin
    Chen, Simin
    Yu, Jinge
    PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2025, 91 (02):
  • [34] Lightweight Deep Learning Models for High-Precision Rice Seedling Segmentation from UAV-Based Multispectral Images
    Zhang, Panli
    Sun, Xiaobo
    Zhang, Donghui
    Yang, Yuechao
    Wang, Zhenhua
    PLANT PHENOMICS, 2023, 5
  • [35] Deep Learning Algorithm for Object Detection with Depth Measurement in Precision Agriculture
    Santiago, Aguirre
    Solaque, Leonardo
    Velasco, Alexandra
    ICINCO: PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, 2020, : 490 - 497
  • [36] Dynamic Object Detection Revolution: Deep Learning with Attention, Semantic Understanding, and Instance Segmentation for Real-World Precision
    Shai, Karimunnisa
    Banerjee, Dyuti
    Begum, R. Sabin
    Srikanth, Narne
    Narasimharao, Jonnadula
    El-Ebiary, Yousef A. Baker
    Thenmozhi, E.
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (01) : 443 - 454
  • [37] Research on Multitask Deep Learning Network for Semantic Segmentation and Object Detection
    Rui, Ting
    Xiao, Feng
    Tang, Jian
    Zhang, Fukai
    Yang, Chengsong
    Liu, Min
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING, PT III, 2018, 11166 : 708 - 718
  • [38] A Novel Word Segmentation Method Based on Object Detection and Deep Learning
    Wilkinson, Tomas
    Brun, Anders
    ADVANCES IN VISUAL COMPUTING, PT I (ISVC 2015), 2015, 9474 : 231 - 240
  • [39] High-Precision Mapping of Soil Organic Matter Based on UAV Imagery Using Machine Learning Algorithms
    Zhou, Jingping
    Xu, Yaping
    Gu, Xiaohe
    Chen, Tianen
    Sun, Qian
    Zhang, Sen
    Pan, Yuchun
    DRONES, 2023, 7 (05)
  • [40] Automated Surface Defect Detection in Metals: A Comparative Review of Object Detection and Semantic Segmentation Using Deep Learning
    Usamentiaga, Ruben
    Lema, Dario G.
    Pedrayes, Oscar D.
    Garcia, Daniel F.
    IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2022, 58 (03) : 4203 - 4213