• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SPIE Defense + Security Conference >Systematic evaluation of deep learning based detection frameworks for aerial imagery
【24h】

Systematic evaluation of deep learning based detection frameworks for aerial imagery

机译：基于深度学习的航空影像检测框架的系统评估

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Object detection in aerial imagery is crucial for many applications in the civil and military domain. In recent years, deep learning based object detection frameworks significantly outperformed conventional approaches based on hand-crafted features on several datasets. However, these detection frameworks are generally designed and optimized for common benchmark datasets, which considerably differ from aerial imagery especially in object sizes. As already demonstrated for Faster R-CNN, several adaptations are necessary to account for these differences. In this work, we adapt several state-of-the-art detection frameworks including Faster R-CNN, R-FCN, and Single Shot MultiBox Detector (SSD) to aerial imagery. We discuss adaptations that mainly improve the detection accuracy of all frameworks in detail. As the output of deeper convolutional layers comprise more semantic information, these layers are generally used in detection frameworks as feature map to locate and classify objects. However, the resolution of these feature maps is insufficient for handling small object instances, which results in an inaccurate localization or incorrect classification of small objects. Furthermore, state-of-the-art detection frameworks perform bounding box regression to predict the exact object location. Therefore, so called anchor or default boxes are used as reference. We demonstrate how an appropriate choice of anchor box sizes can considerably improve detection performance. Furthermore, we evaluate the impact of the performed adaptations on two publicly available datasets to account for various ground sampling distances or differing backgrounds. The presented adaptations can be used as guideline for further datasets or detection frameworks.
机译：航空影像中的目标检测对于民用和军事领域的许多应用至关重要。近年来，基于深度学习的对象检测框架大大优于基于一些数据集上手工制作特征的传统方法。但是，这些检测框架通常是针对常见基准数据集进行设计和优化的，这些基准数据集与航空影像有很大的不同，尤其是在物体大小方面。正如已经为Faster R-CNN演示的那样，必须进行几种修改才能解决这些差异。在这项工作中，我们将几种最先进的检测框架（包括Faster R-CNN，R-FCN和Single Shot MultiBox Detector（SSD））应用于航空影像。我们详细讨论了主要提高所有框架的检测准确性的适应方法。由于更深的卷积层的输出包含更多的语义信息，因此这些层通常在检测框架中用作特征图来定位和分类对象。但是，这些特征图的分辨率不足以处理小对象实例，从而导致小对象的定位不正确或分类不正确。此外，最新的检测框架执行包围盒回归以预测确切的对象位置。因此，所谓的锚点或默认框用作参考。我们演示了如何锚箱尺寸的合适的选择可以大大提高检测性能。此外，我们评估了进行的改编对两个公开可用数据集的影响，以说明各种地面采样距离或不同背景。提出的改编可以用作进一步的数据集或检测框架的指南。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号