摘要
飞机在夜间起降时机场跑道上侵入的异物严重威胁航空运输安全,而暗光背景下依靠人工步行巡查小尺度异物更易留存致命的安全隐患。将智能视觉检测算法引入机场跑道异物入侵领域,针对现有模型倾向关注局部特征而造成检测精度低等问题,设计了一种融合自注意力特征嵌入的CSPTNet夜间机场跑道异物检测算法。为改善卷积神经网络关注局部特征而忽视全局特征的缺陷,将标准瓶颈模块替换为Transformer瓶颈模块,特征图子块扁平化分割后嵌入位置特征编码,有利于图像从像素表示转化为向量表示,在高维向量空间中捕捉像素间关系。采用多头自注意力机制从注意力分支子空间中获取不同分支聚合的特征信息,从而实现全局特征与局部特征信息的融合。针对数据集目标尺度较小导致轮廓边缘模糊以及定位困难等问题,引入CIoU损失函数以实现预测框尺寸和中心位置的修正优化,提高异物目标轮廓的定位精确性。实验结果表明,本文模型的检测速度达到38 frame/s,满足实时检测的要求;平均精度最高为88.1%,应用融合自注意力特征嵌入的Transformer模块相比于标准瓶颈模块提升5.7%,与当前先进的YOLOv5模型相比提升5.2%,从而验证了CSPTNet算法对夜间机场跑道异物检测的有效性和工程实用性。
Foreign object debris(FOD)on an airport runway threaten aircraft safety during takeoff and landing,especially at night.This study introduces an intelligent vision algorithm to detect debris on airport runways at night.Considering the problems of existing models such as low detection accuracy owing to a tendency to focus on local features,a CSPTNet debris detection algorithm fused with self-attentional fea⁃ture embedding is proposed.This algorithm replaces the standard BottleNeck module prevalent in conven⁃tional models with a Transformer BottleNeck module.In addition,the feature patch is flat segmented and embedded with position feature encoding to transform image representation from the pixel format to vector format.After capturing the relationship between the pixels in a high-dimensional vector space,the multihead self-attention mechanism is employed to achieve the fusion of global and local features by obtaining feature information aggregated by different branches from the attention branch subspace.To solve the problems of blurred contour edges and difficult positioning due to the small scale of objects in datasets,we introduce the CIoU loss function to optimize predicted frame sizes and center positions.Thereby,the posi⁃tioning accuracy of foreign object contours is enhanced.The experimental results show that the detection speed of this algorithm reaches 38 frames/s,which meets the requirements of real-time detection,and its average accuracy is 88.1%.Compared with the experimental results of the standard bottleneck module,the accuracy is increased by 5.7%through the Transformer BottleNeck module fusion with self-attentional feature embedding.In addition,compared with the state-of-the-art model YOLOv5,our is 5.2% more ac⁃curate.The obtained results demonstrate the effectiveness and engineering practicability of CSPTNet for FOD detection on airport runways at night.
作者
何自芬
陈光晨
王森
张印辉
郭琳伟
HE Zifen;CHEN Guangchen;WANG Sen;ZHANG Yinhui;GUO Linwei(Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,China)
出处
《光学精密工程》
EI
CAS
CSCD
北大核心
2022年第13期1591-1605,共15页
Optics and Precision Engineering
基金
国家自然科学基金资助项目(No.62171206,No.62061022,No.61761024)。
关键词
夜间机场跑道
异物入侵检测
目标定位损失
特征嵌入
多头自注意力
night airport runways
foreign object debris intrusion detection
target positioning loss
fea⁃ture embedding
multi-headed self-attention
