Real-Time Small Drones Detection Based on Pruned YOLOv4.
Real-Time Small Drones Detection Based on Pruned YOLOv4.
复制标题
基于剪枝YOLOv4的实时小型无人机检测
DOI：
10.3390/s21103374
复制
发表时间：
2021-05-12
期刊：
影响因子：
--
通讯作者：
Li N
中科院分区：
文献类型：
--
作者：
Liu H;Fan K;Ouyang Q;Li N
为了解决无人机侵入高安全区域的威胁，迫切需要对无人机进行实时检测以保护这些区域。无人机的实时检测主要有两个难点。其中之一是无人机移动迅速，这导致需要更快的探测器。另一个问题是，小型无人机很难被发现。在本文中，首先，我们通过评估三种最先进的目标检测方法来实现高检测精度：RetinaNet，FCOS，YOLOv 3和YOLOv 4。然后，为了解决第一个问题，我们修剪了YOLOv 4的卷积通道和快捷层，以开发更薄和更浅的模型。此外，为了提高小型无人机检测的准确性，我们通过复制和粘贴小型无人机来实现小型物体检测的特殊增强。实验结果表明，与YOLOv 4模型相比，0.8通道剪枝率和24层剪枝的剪枝后的YOLOv 4模型的mAP达到了90.5%，处理速度提高了60.4%。此外，经过小对象增强后，剪枝后的YOLOv 4的准确率和召回率分别提高了22.8%和12.7%。实验结果表明，我们的修剪YOLOv 4是一种有效的和准确的无人机检测方法。
To address the threat of drones intruding into high-security areas, the real-time detection of drones is urgently required to protect these areas. There are two main difficulties in real-time detection of drones. One of them is that the drones move quickly, which leads to requiring faster detectors. Another problem is that small drones are difficult to detect. In this paper, firstly, we achieve high detection accuracy by evaluating three state-of-the-art object detection methods: RetinaNet, FCOS, YOLOv3 and YOLOv4. Then, to address the first problem, we prune the convolutional channel and shortcut layer of YOLOv4 to develop thinner and shallower models. Furthermore, to improve the accuracy of small drone detection, we implement a special augmentation for small object detection by copying and pasting small drones. Experimental results verify that compared to YOLOv4, our pruned-YOLOv4 model, with 0.8 channel prune rate and 24 layers prune, achieves 90.5% mAP and its processing speed is increased by 60.4%. Additionally, after small object augmentation, the precision and recall of the pruned-YOLOv4 almost increases by 22.8% and 12.7%, respectively. Experiment results verify that our pruned-YOLOv4 is an effective and accurate approach for drone detection.
登录
查看更多内容
具有多种监控技术的反无人机系统：架构、实施和挑战
影响因子：
11.2
作者：
Shi, Xiufang;Yang, Chaoqun;Chen, Jiming
通讯作者：
Chen, Jiming
影响因子：
6.8
作者：
Anwar, Muhammad Zohaib;Kaleem, Zeeshan;Jamalipour, Abbas
通讯作者：
Jamalipour, Abbas
DOI：
10.1109/tpami.2016.2572683
发表时间：
2017-04-01
影响因子：
23.6
作者：
Shelhamer, Evan;Long, Jonathan;Darrell, Trevor
通讯作者：
Darrell, Trevor
影响因子：
5
作者：
Nowak, Aleksander;Naus, Krzysztof;Maksimiuk, Dariusz
通讯作者：
Maksimiuk, Dariusz
影响因子：
5
作者：
Koga, Yohei;Miyazaki, Hiroyuki;Shibasaki, Ryosuke
通讯作者：
Shibasaki, Ryosuke