Scholarlink

<p>In the contemporary dynamic environment, integrating technology is crucial for effective solutions. This paper addresses the pressing need for accurate monitoring and management of natural resources, with a specific focus on forests, utilizing satellite imagery. The primary goal is to develop an image analytics system utilizing satellite imagery for automated tree counting. traditional methods, such as on-site evaluations and manual surveys, are expensive, time-consuming, and error-prone. The dataset comprises 91 lower orbit satellite images, each annotated with bounding boxes to ensure precise spatial information. Three algorithms were evaluated for tree counting performance using annotated images and bounding box labels. Metrics such as Mean Squared Error (MSE), Intersection over Union (IOU), recall, precision, and F1 score were utilized for performance assessment. An ensemble network, combining a faster Recurrent Convolutional Neural Network (RCNN) with object detection algorithms, demonstrated superior performance. The model achieved an accuracy of 94.8% and a precision of 0.854 in density regression. The proposed strategy outperformed previous approaches with an average density regression accuracy of 91.58%. The model's precision of 0.854 and accuracy of 94.8% enhance visualization and yield more precise tree counting data. These advancements underscore the superiority of our satellite imagery-based automated tree counting model for sustainable resource management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhanced tree enumeration through satellite imagery and hybrid ensemble cyclic averaging stacked chain deep learning model tuned with BRO algorithm

  • 期刊论文

  • 发表日期：

    2025年6月27日

查看全文
  • Shantanu Kumar Mishra,
  • Anurag Sinha,
  • Nitasha Rathore,
  • Apurva Gupta,
  • Mohammad Nadeem Ahmed,
  • Sudhanshu Maurya,
  • Himanshu Bansal,
  • Garvit Agarwal,
  • Shelly Gupta,
  • Mohammad Rashid Hussain

摘要

In the contemporary dynamic environment, integrating technology is crucial for effective solutions. This paper addresses the pressing need for accurate monitoring and management of natural resources, with a specific focus on forests, utilizing satellite imagery. The primary goal is to develop an image analytics system utilizing satellite imagery for automated tree counting. traditional methods, such as on-site evaluations and manual surveys, are expensive, time-consuming, and error-prone. The dataset comprises 91 lower orbit satellite images, each annotated with bounding boxes to ensure precise spatial information. Three algorithms were evaluated for tree counting performance using annotated images and bounding box labels. Metrics such as Mean Squared Error (MSE), Intersection over Union (IOU), recall, precision, and F1 score were utilized for performance assessment. An ensemble network, combining a faster Recurrent Convolutional Neural Network (RCNN) with object detection algorithms, demonstrated superior performance. The model achieved an accuracy of 94.8% and a precision of 0.854 in density regression. The proposed strategy outperformed previous approaches with an average density regression accuracy of 91.58%. The model's precision of 0.854 and accuracy of 94.8% enhance visualization and yield more precise tree counting data. These advancements underscore the superiority of our satellite imagery-based automated tree counting model for sustainable resource management.