激光与光电子学进展, 2019, 56 (19): 191003, 网络出版: 2019-10-12   

基于YOLO v3的机场场面飞机检测方法 下载: 1819次

Airport Scene Aircraft Detection Method Based on YOLO v3
作者单位
1 宁夏大学信息工程学院, 宁夏 银川 750021
2 中国民用航空西北地区空中交通管理局宁夏分局, 宁夏 银川 750009
摘要
小目标、飞机相互遮挡等难以检测的问题,对飞机检测的准确性及实时性提出很大的挑战。将实时性较高的YOLO v3算法应用到机场场面飞机检测领域,并提出两点改进:将骨干网络中的卷积层替换为空洞卷积,保持较高分辨率及较大感受野,提高模型对小目标检测的准确率;通过线性衰减置信得分的方式,对非极大值抑制(NMS)算法进行优化,以提升模型对被遮挡飞机的检测能力。结果表明,改进后的YOLO v3能够较好地检测小目标和遮挡飞机,且在保证实时性的前提下,将检测准确率从72.3%提高到83.7%。
Abstract
The difficulty to detect small targets or occlusion aircrafts poses a great challenge to the accuracy and real-time of aircraft detection. In this paper, YOLO v3 algorithm with high real-time performance is applied to the field of aircraft detection in airport scene, and two improvements are proposed: replacing the convolution layer in backbone network with void convolution, maintaining high resolution and large field of receptivity and improving the accuracy of small target detection; optimizing the NMS algorithm by linear attenuation confidence score to improve the detection accuracy of occlusion aircrafts. The results show that the improved YOLO v3 can well detect small targets and occlusion aircraft, and the detection accuracy is improved from 72.3% to 83.7% as the real-time performance is ensured.

郭进祥, 刘立波, 徐峰, 郑斌. 基于YOLO v3的机场场面飞机检测方法[J]. 激光与光电子学进展, 2019, 56(19): 191003. Jinxiang Guo, Libo Liu, Feng Xu, Bin Zheng. Airport Scene Aircraft Detection Method Based on YOLO v3[J]. Laser & Optoelectronics Progress, 2019, 56(19): 191003.

本文已被 9 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!