首页> 外文OA文献 >Vision-Based UAV Maritime Search and Rescue Using Point Target Detection
【2h】

Vision-Based UAV Maritime Search and Rescue Using Point Target Detection

机译:使用点目标检测的基于视觉的无人机海上搜索与救援

摘要

Human maritime search and rescue missions have always been challengingudand an element of chance is involved in the detection of survivors at sea. Thisudresearch is proposing the use of machine vision to assist UAVs to increase theudchances of success in locating humans lost at sea.ududThis paper presents an application of current image processing methods for targetuddetection in a synthetic maritime scenario. An evaluation of the algorithm’sudperformance is also provided. The difficulties faced in the automatic detection ofudhuman targets in a maritime search environment are also considered.ududThe paper concludes that there is a range of greyscale intensities, approximately 26%udbased on current data set, where the target was unable to be detected which may limitudthe applicability of the algorithm. The effect on performance of target intensity level,udthreshold and forgetting factor are also investigated.
机译:人类海上搜索和救援任务一直是具有挑战性的 udd,机会因素涉及海上幸存者的发现。这项研究提议使用机器视觉来协助无人机增加成功定位海上迷路人员的机会。 ud ud本文介绍了在合成海上场景中用于目标 uddetect检测的当前图像处理方法的应用。还提供了对该算法 udperformance的评估。还考虑了在海上搜索环境中自动检测 udhuman目标所面临的困难。 ud ud本文得出的结论是,存在一定范围的灰度强度,基于当前数据集,灰度强度约为26% ud,而目标无法被检测到,这可能会限制算法的适用性。还研究了目标强度水平,阈值和遗忘因子对性能的影响。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利

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