• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International ocean and polar engineering conference;International Society of Offshore and Polar Engineers >Image-based Ship Detection and Classification for Unmanned Surface Vehicle Using Real-Time Object Detection Neural Networks
【24h】

Image-based Ship Detection and Classification for Unmanned Surface Vehicle Using Real-Time Object Detection Neural Networks

机译：基于图像的实时目标检测神经网络的无人水面舰船检测与分类

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

摘要

An unmanned surface vehicle (USV) requires the ability to detectadjacent objects and correctly classify them into ships and non-ships. Inthis study, one of the state-of-the-art neural network based objectdetection algorithms is applied to detect ships from the images andvideos taken on the sea. Firstly, the universally pre-trained “referencemodel,” which is to detect and classify objects into a range of 20general classes such as person, dog, cat, table, car, or boat, is preparedand tested. Secondly, the “proposed model” is trained using a publicmaritime dataset so that it can detect all types of floating objects andclassify them into ten specific classes, e.g., ship, speedboat, buoy, etc.The proposed model outperforms the reference model in detectingmaritime objects. It also shows real-time speed about 30 frames persecond.
机译：无人水面战车（USV）需要具备检测能力 相邻物体并将其正确分类为船只和非船只。在 这项研究是基于最新神经网络的对象之一 检测算法应用于从图像中检测船只，并 在海上拍摄的视频。首先，普遍接受预训练的“参考 模型”，它可以检测和分类对象到20个范围内 准备了一般课程，例如人，狗，猫，桌子，汽车或船 并经过测试。其次，“提议的模型”是通过公众培训的 海事数据集，以便它可以检测所有类型的漂浮物和 将它们分为十个特定类别，例如，船舶，快艇，浮标等。 在检测中，该模型优于参考模型。 海上物体。它还显示了大约30帧/秒的实时速度 第二。

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