A Comparison of Deep Learning Object Detection Models for Satellite Imagery

机译：卫星影像深度学习目标检测模型的比较

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this work, we compare the detection accuracy and speed of several state-of-the-art models for the task of detecting oil and gas fracking wells and small cars in commercial electrooptical satellite imagery. Several models are studied from the single-stage, two-stage, and multi-stage object detection families of techniques. For the detection of fracking well pads (50m- 250m), we find single-stage detectors provide superior prediction speed while also matching detection performance of their two and multi-stage counterparts. However, for detecting small cars, two-stage and multi-stage models provide substantially higher accuracies at the cost of some speed. We also measure timing results of the sliding window object detection algorithm to provide a baseline for comparison. Some of these models have been incorporated into the Lockheed Martin Globally-Scalable Automated Target Recognition (GATR) framework.

机译：在这项工作中，我们比较了几种最新模型的检测精度和速度，这些模型可用于检测商业电光卫星图像中的油气压裂井和小型汽车。从单阶段，两阶段和多阶段目标检测技术族研究了几种模型。对于压裂井场（50m-250m）的检测，我们发现单级检测器提供了卓越的预测速度，同时还使其两级和多级对应物的检测性能相匹配。但是，对于检测小型汽车，两阶段和多阶段模型以一定速度为代价提供了更高的准确度。我们还测量滑动窗口对象检测算法的计时结果，以提供比较的基准。其中一些模型已合并到洛克希德·马丁公司全球可扩展自动目标识别（GATR）框架中。

著录项

来源
《IEEE Applied Imagery Pattern Recognition Workshop》|2019年|1-10|共10页
会议地点
作者
Austen Groener; Gary Chern; Mark Pritt;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
ATR; Object Detection; Deep Learning; Artificial Intelligence; Neural Networks; Machine Learning; Satellite Imagery;

机译：ATR;目标检测;深度学习;人工智能;神经网络;机器学习;卫星影像;

相似文献

外文文献
中文文献
专利

1. Comparison between Object-based Method and Deep Learning Method for Extracting Road Features Using Submeter-grade High-resolution Satellite Imagery [J] . Lee Dong Gook, You Ji Ho, Park Sung Geun, Sensors and materials . 2019,第10期

机译：亚米级高分辨率卫星影像提取道路特征的基于对象的方法与深度学习方法的比较
2. An evaluation of deep learning based object detection strategies for threat object detection in baggage security imagery [J] . Dhiraj, Jain Deepak Kumar Pattern recognition letters . 2019,第APRa期

机译：基于深度学习的对象检测策略对行李安全图像中威胁对象检测的评估
3. Deep learning-based object recognition in multispectral satellite imagery for real-time applications [J] . Povilas Gudzius, Olga Kurasova, Vytenis Darulis, Machine Vision and Applications . 2021,第4期

机译：基于深度学习的对象识别在多光谱卫星图像中的实时应用
4. FPGA based Deep Learning Models for Object Detection and Recognition Comparison of Object Detection Comparison of object detection models using FPGA [C] . S.P. Kaarmukilan, Soumyajit Poddar, Amal Thomas K International Conference on Computing Methodologies and Communication . 2020

机译：用于对象检测和识别的基于FPGA的深度学习模型对象检测比较使用FPGA的对象检测模型比较
5. Using Synthetic Satellite Imagery from Virtual Worlds to Train Deep Learning Models for Object Recognition [D] . Huang, Bohao. 2021

机译：使用虚拟世界的合成卫星图像来培训对象识别的深度学习模型
6. Intelligent Image-Based Railway Inspection System Using Deep Learning-Based Object Detection and Weber Contrast-Based Image Comparison [O] . Jinbeum Jang, Minwoo Shin, Sohee Lim, 2019

机译：基于深度学习的目标检测和基于Weber对比度的图像比较的基于图像的铁路智能检查系统
7. A Comparison of Deep Learning Object Detection Models for Satellite Imagery [O] . Austen Groener, Gary Chern, Mark Pritt 2019

机译：卫星图像深度学习对象检测模型的比较

A Comparison of Deep Learning Object Detection Models for Satellite Imagery

摘要

著录项

相似文献

相关主题

期刊订阅