Scholarlink

<p>Instance segmentation is a novel technique to automatically detect and count the number of objects from satellite imagery for various applications using deep learning frameworks such as Mask-R-CNN and YOLO. In this paper, we have implemented the YOLOv5 and YOLOv7 instance segmentation models on high-resolution satellite imagery (0.31–1.74 m) of both panchromatic (16-bit PAN) and multi-spectral (16-bit 9-channels MS) sensors and evaluated the comparative performance of these models. After training both models for 300 epochs, the models showed very good comparative accuracies. YOLOv7 outperformed YOLOv5 on the mean Average Precision (mAP) parameter with a 99.20% mAP value compared to YOLOv5’s 99.12% mAP value. We have also obtained the model results on panchromatic and multi-spectral remote sensing data of Indian Remote Sensing Data over Mumbai, Pune, and Ahmedabad airports, with an accuracy of above 94% to segment the larger aircraft and above 88% to segment the smaller aircraft.</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

Automatic detection of the number of aircraft over satellite data using deep learning

  • 期刊论文

  • 发表日期：

    2025年10月25日

查看全文
  • Jai Gopal Singla,
  • Gautam Kumar Jaiswal,
  • Renu Chaudhary,
  • Darshan Kumar Patel

摘要

Instance segmentation is a novel technique to automatically detect and count the number of objects from satellite imagery for various applications using deep learning frameworks such as Mask-R-CNN and YOLO. In this paper, we have implemented the YOLOv5 and YOLOv7 instance segmentation models on high-resolution satellite imagery (0.31–1.74 m) of both panchromatic (16-bit PAN) and multi-spectral (16-bit 9-channels MS) sensors and evaluated the comparative performance of these models. After training both models for 300 epochs, the models showed very good comparative accuracies. YOLOv7 outperformed YOLOv5 on the mean Average Precision (mAP) parameter with a 99.20% mAP value compared to YOLOv5’s 99.12% mAP value. We have also obtained the model results on panchromatic and multi-spectral remote sensing data of Indian Remote Sensing Data over Mumbai, Pune, and Ahmedabad airports, with an accuracy of above 94% to segment the larger aircraft and above 88% to segment the smaller aircraft.