光电工程, 2018, 45 (12): 180350, 网络出版: 2018-12-18
遥感图像中飞机的改进YOLOv3实时检测算法
180350
遥感图像 飞机目标 实时检测 卷积神经网络 remote-sensing image airplane target real-time detection convolutional neural network
摘要
针对遥感图像中的飞机目标,本文提出一种遥感图像飞机的改进YOLOv3 实时检测算法。首先,针对单一的遥感图像飞机目标,提出一种有49 个卷积层的卷积神经网络。其次,在提出的卷积神经网络上应用密集相连模块进行改进,并提出使用最大池化加强密集连接模块间的特征传递。最后,针对遥感图像中飞机多为小目标的现实,提出将YOLOv3 的3 个尺度检测增加至4 个并以密集相连融合不同尺度模块特征层的信息。在本文设计的遥感飞机测试集上进行训练和测试,实验表明,该算法的检测精度达到96.26%、召回率达到93.81%。
Abstract
Focusing on the airplanes in remote-sensing images, a real-time algorithm based on improved YOLOv3 is proposed to detect airplanes in remote-sensing images. Firstly, a convolutional neural network that consists of 49 convolutional layers is proposed to detect airplanes in remote-sensing images specifically. Secondly, dense connection is employed on proposed convolutional neural network, and maxpool is employed to enhance the feature transmit between dense blocks. Finally, to deal with the fact that airplanes in remote-sensing images are small targets mainly, we propose to increase the scale detection from 3 to 4 and employ dense connection to merge feature map among different scales. The algorithm is trained and tested on the designed airplane dataset. The experiment results show that our algorithm obtain 96.26% on precision and 93.81% on recall.
戴伟聪, 金龙旭, 李国宁, 郑志强. 遥感图像中飞机的改进YOLOv3实时检测算法[J]. 光电工程, 2018, 45(12): 180350. 戴伟聪, 金龙旭, 李国宁, 郑志强. 180350[J]. Opto-Electronic Engineering, 2018, 45(12): 180350.