面向三维建模的改进型GAN网络无人机倾斜摄影图像修复方法  

Improved GAN Network-Based UAV Oblique Photography ImageRestoration Method for Three-Dimensional Modeling

作　　者：刘佳嘉 姜国梁 魏琪 LIU Jia-jia;JIANG Guo-liang;WEI Qi(Aviation Electronic and Electrical Institute,Civil Aviation Flight University of China,Guanghan 618307,China)

机构地区：[1]中国民用航空飞行学院航空电子电气学院,广汉618307

出　　处：《科学技术与工程》2024年第30期13199-13209,共11页Science Technology and Engineering

基　　金：中央高校基本科研业务费专项(J2023-024)。

摘　　要：为解决无人机采集倾斜影像时不可避免遇到人和车等移动物体,造成三维建模扭曲或错位从而降低模型质量的问题,提出了一种改进型GAN(generative adversarial network)网络图像修复方法。该方法在GAN网络的基础上,在生成器中引入U-Net网络结构并在连接层中融入CBAM(convolutional block attention module)双通道注意力机制,增强局部细节恢复能力;同时在判别器中引入VGG16模型并融入SE-Net通道注意力机制,提升修复后影像的真实度。最后利用Context Capture软件对影像分析、处理,实现自动化的三维立体建模。通过该方法可将分辨率高、影像范围广的倾斜影像中的人和车等移动物体提前剔除,减小对后续三维建模的影响,提高模型的精度。将本文算法与GAN网络和WGAN-GP网络对比,在峰值信噪比(peak signal-to-noise ratio,PSNR)和结构相似性(structure similarity index measure,SSIM)指标上分别提升3.32996 dB、0.0979和2.28894 dB、0.0478;且通过三维立体模型对比,本文方法能有效减少模型几何变形、道路纹理映射错误,提高模型精细度。The issue of distortion or misalignment in 3D modeling resulting from moving objects such as people and vehicles during UAV-obtained oblique image acquisition was addressed.An enhanced GAN-based image restoration technique was proposed,which modifies the GAN network by incorporating a U-Net architecture in the generator,fortified with a dual-channel attention mechanism via CBAM in the connecting layers,thereby enhancing the technique s capability for restoring local image details.The discriminator was augmented with the VGG16 model and the SE-Net channel attention mechanism has been undertaken to ensure the high fidelity of generated images in the present approach.Image analysis and processing were carried out using Context Capture software,facilitating automatic 3D modeling.This methodology enables proactive removal of moving entities,such as people and vehicles,from high-resolution,extensive oblique imagery,thus minimizing their detrimental effects on subsequent 3D modeling and enhancing model accuracy.The presented algorithm demonstrates superior performance compared to conventional GAN and WGAN-GP networks,exhibiting increases of 3.32996 dB and 0.0979 in PSNR values and 2.28894 dB and 0.0478 in SSIM indices,respectively.Moreover,through comparison with generated 3D models,the method effectively reduces geometric deformation and road texture mapping errors,leading to heightened model precision.

关 键 词：倾斜影像 图像修复 神经网络 三维建模 注意力机制 

分 类 号：V279.2[航空宇航科学与技术—飞行器设计] TP391.9[自动化与计算机技术—计算机应用技术]