Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs.
Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs.
复制标题
DOI：
10.3390/s22020464
复制
发表时间：
2022-01-08
期刊：
影响因子：
--
通讯作者：
Eslamiat H
中科院分区：
文献类型：
--
作者：
Nepal U;Eslamiat H
飞行中的系统故障是城市环境中无人机（UAV）运行的主要安全问题之一。为了解决这个问题，可以利用由以下三个主要任务组成的安全框架：（1）监测UAV的健康状况并检测故障，（2）在步骤1中检测到严重故障的情况下找到潜在的安全着陆点，以及（3）将UAV转向到步骤2中找到的安全着陆点。在本文中，我们具体看第二个任务，在那里我们调查的可行性，利用物体检测方法来现场的情况下，无人机遭受飞行中的故障安全着陆点。特别是，我们研究了不同版本的YOLO目标检测方法，并比较了它们在检测飞行中失败的无人机的安全着陆位置的具体应用中的性能。我们比较了YOLOv3，YOLOv4和YOLOv5l的性能，同时在个人计算机（PC）和伴侣计算机（CC）中使用称为DOTA的大型航空图像数据集进行训练。我们计划在可以连接到UAV的CC上使用所选择的算法，并且PC用于验证我们在CC上看到的算法之间的趋势。我们确认了利用这些算法进行有效的紧急着陆点检测的可行性，并报告了它们在特定应用中的准确性和速度。我们的调查还表明，YOLOv5l算法在检测准确性方面优于YOLOv4和YOLOv3，同时保持略慢的推理速度。
In-flight system failure is one of the major safety concerns in the operation of unmanned aerial vehicles (UAVs) in urban environments. To address this concern, a safety framework consisting of following three main tasks can be utilized: (1) Monitoring health of the UAV and detecting failures, (2) Finding potential safe landing spots in case a critical failure is detected in step 1, and (3) Steering the UAV to a safe landing spot found in step 2. In this paper, we specifically look at the second task, where we investigate the feasibility of utilizing object detection methods to spot safe landing spots in case the UAV suffers an in-flight failure. Particularly, we investigate different versions of the YOLO objection detection method and compare their performances for the specific application of detecting a safe landing location for a UAV that has suffered an in-flight failure. We compare the performance of YOLOv3, YOLOv4, and YOLOv5l while training them by a large aerial image dataset called DOTA in a Personal Computer (PC) and also a Companion Computer (CC). We plan to use the chosen algorithm on a CC that can be attached to a UAV, and the PC is used to verify the trends that we see between the algorithms on the CC. We confirm the feasibility of utilizing these algorithms for effective emergency landing spot detection and report their accuracy and speed for that specific application. Our investigation also shows that the YOLOv5l algorithm outperforms YOLOv4 and YOLOv3 in terms of accuracy of detection while maintaining a slightly slower inference speed.
登录
查看更多内容
影响因子：
46.9
作者：
Noble, William S.
通讯作者：
Noble, William S.
DOI：
10.3390/s20174938
发表时间：
2020-08-31
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Li M;Zhang Z;Lei L;Wang X;Guo X
通讯作者：
Guo X
DOI：
10.3390/s21030974
发表时间：
2021-02-02
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Rahman EU;Zhang Y;Ahmad S;Ahmad HI;Jobaer S
通讯作者：
Jobaer S
航空图像中的目标检测：大规模基准和挑战
DOI：
10.1109/tpami.2021.3117983
发表时间：
2022-11-01
影响因子：
23.6
作者：
Ding, Jian;Xue, Nan;Zhang, Liangpei
通讯作者：
Zhang, Liangpei
DOI：
10.1109/tpami.2016.2577031
发表时间：
2017-06-01
影响因子：
23.6
作者：
Ren, Shaoqing;He, Kaiming;Sun, Jian
通讯作者：
Sun, Jian