基于旋转目标检测的飞机蒙皮损伤检测  

Aircraft Skin Damage Detection Based on Rotating Object Detection

作　　者：王童 王宏伟[1] 王红[1] Wang Tong;Wang Hongwei;Wang Hong(Computer Science and Technology College,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学计算机科学与技术学院,天津300300

出　　处：《激光与光电子学进展》2023年第10期250-258,共9页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(U1633110);空中交通管理系统与技术国家重点实验室开放基金(SKLATM201902)。

摘　　要：飞机蒙皮作为航空器的重要部件,直接影响到飞行安全,故飞机蒙皮损伤检测对于有效预防航空安全事故具有重要意义,基于边界框边缘感知向量(BBAVectors)提出一种改进的旋转目标检测方法。首先针对损伤尺度变化大的问题,采用特征融合网络(FFN)提升多尺度检测效果;其次针对飞机蒙皮图片存在大量背景噪声的问题,引入coordinate attention(CA)机制来增强目标特征信息;最后针对蒙皮损伤分布方向任意的问题,通过BBAVectors表示任意角度的损伤位置,以提升目标定位的准确性。实验结果表明,改进的旋转目标检测方法相比原模型检测精度提升了5.7个百分点,并且检测精度高于主流的水平目标检测方法,在有效解决方向任意的飞机蒙皮损伤检测效果的基础上,为航空器损伤检测方法的提升提供更好的技术支持。As an important part of an aircraft,aircraft skin is directly related to the occurrence of aircraft accidents,so the detection of aircraft skin damage is of great significance for the effective prevention of aviation safety accidents.In this paper,an improved rotated object detection method based on box boundaryaware vectors(BBAVectors)is proposed.First,for the problem of large variation of damage scale,the feature fusion network(FFN)is used to improve the multiscale detection effect.Second,for the problem of lots of background noise in aircraft skin images,coordinate attention(CA)mechanism is introduced to enhance the object feature information.Finally,for the problem of arbitrary skin damage distribution direction,the damage position of arbitrary angle is represented by the BBAVectors to improve the accuracy of object localization.The experimental results show that the improved rotated object detection method improves the mean average precision by 5.7 percentage points compared with the original model,and the detection performance is better than the horizontal object detection method.On the basis of effectively solving the effect of aircraft skin damage detection in arbitrary directions,it provides better technical support for the improvement of aircraft damage detection methods.

关 键 词：图像处理 旋转目标检测 飞机蒙皮损伤检测 特征融合 注意力机制 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]