低空空域小型无人机目标检测算法

王传云; 司可意

doi:10.3969/j.issn.2095-1248.2023.02.007

沈阳航空航天大学学报 ›› 2023, Vol. 40 ›› Issue (2) : 54 -62. DOI: 10.3969/j.issn.2095-1248.2023.02.007

信息科学与工程

低空空域小型无人机目标检测算法

王传云 ¹ ,
司可意 ²

作者信息 +

Detection algorithm of small UAV target in low altitude airspace

Chuan-yun WANG ¹ ,
Ke-yi SI ²

Author information +

文章历史 +

PDF (1291K)

摘要

在利用视觉检测算法进行检测与定位的过程中，当空域中目标无人机相对较小时，现有的检测算法容易受到空中其他飞行物、复杂背景和光照强度变化影响导致检测精度较低。为了解决这一问题，提出了一种基于YOLOv3改进的目标检测算法。当空域中目标无人机体积相对较小、视觉特征较弱、存在其他干扰时，通过增加主干特征提取网络对图像特征提取的层级数，提取多个不同尺度特征层进行跨层连接融合，使多个不同层级的特征层之间的语义信息联系得更加紧密，让网络模型可以学习到不同尺度目标的特征信息，以此增强检测算法对小目标无人机检测的精度。最后，利用Drone vs Birds数据集进行实验测试，所提出的算法可以有效地提高小型无人机目标的检测精度，检测速度基本满足实际要求。

Abstract

When the target UAV（Unmanned Aerial Vehicle） in the air domain is relatively small， the existing detection algorithm is prone to be affected by other flying objects in the air， complex background and light intensity changes， resulting in low detection accuracy in the process of using visual detection algorithm for detection and positioning. To solve this problem， an improved target detection algorithm based on YOLOv3 was proposed. When the target UAV in the space domain was relatively small in size， with weak visual features and other disturbances， the main feature extraction network was added to the image feature extraction level， and multiple feature layers of different scales were extracted for cross-layer connection and fusion， so that the semantic information between multiple feature layers of different levels was more closely related. The network model could learn the characteristic information of targets of different scales， so as to enhance the accuracy of detection algorithm for small target UAV detection. Finally， Drone vs Birds dataset was used for experimental testing. The algorithm can effectively improve the detection accuracy of small UAV target， and the detection speed basically meets the actual requirements.