基于U-net模型的航拍图像去绳带方法

光启云端号平台是用电缆绳索牵引气囊的, 由于空中航拍摄像系统悬挂在气囊下方, 摄取的图像不可避免地含有绳带信息, 这些绳带信息影响图像质量, 所以在场景分析和目标检测中需要剔除。提出一种基于U-net模型的绳带检测算法, 引入深度可分离卷积提高计算速度, 采用一种带权重的交叉熵作为损失函数, 解决类别不均衡带来的收敛不稳定问题, 最终的模型能够用较少的样本在较短的时间内, 快速准确地检测绳带, 利用快速行进修复算法(FMM)对绳带图像进行了修复。实验结果表明: 该算法的mIOU达到62.8%, 得到了较好的去绳结果。

Abstract

The Kuang-chi cloud platform is used to pull the airbag with a cable rope. Since the aerial photography system is suspended under the airbag, the captured image inevitably contains the rope information, which affects the image quality and needs to eliminated in the scene analysis and object detection. A rope detection algorithm based on U-net model was proposed, which introduced the separable convolution to improve the detection speed and adopted a weighted cross entropy as a loss function to solve the problem of convergence instability caused by category imbalance. The final model was able to quickly and accurately detect the rope with fewer data in less time , and then the rope image waseliminated using the fast marching method algorithm (FMM). The test results show that the mean intersection over union(mIOU) of the algorithm reaches 62.8% and has obtained good results.

参考文献

[1] BURNS J B, HANSON A R, RISEMAN E M.Extracting straight lines［J］.IEEE Trans. Pattern Analysis and Machine Intelligence, 1986, 8(4): 425-455.

[2] XU L, OJA E, KULTANEN P. A new curve detection method: randomized Hough transform (RHT)［J］. Pattern Recognition Letters, 1990, 11(5): 331-338.

[3] 乔寅骐, 肖健华, 黄银, 等.基于最小二乘修正的随机Hough变换直线检测［J］. 计算机应用, 2015, 35(11): 3312-3315.

QIAO Yinqi, XIAO Jianhua, HUANG Yin, et al. Random Hough transform line detection based on least squares correction［J］. Journal of Computer Applications, 2015, 35(11): 3312-3315.

[4] 洪汉玉.现代图像图形处理与分析［M］.武汉: 中国地质大学出版社, 2011.

HONG Hanyu. Modern image graphics processing and analysis ［M］. Wuhan: China University of Geosciences Press, 2011.

[5] 徐威, 唐振民, 吕建勇. 基于图像显著性的路面裂缝检测［J］. 中国图像图形学报, 2013, 18(1): 69-77.

XU Wei, TANG Zhenmin, LYU Jianyong. Detection of pavement crack based on image saliency［J］. Journal of Image and Graphics, 2013, 18(1): 69-77.

[6] ALEXANDRU T.An image inpainting technique based on the fast marching method［J］. Journal of Graphics Tools, 2004, 9(1): 23-34.

[7] 高凯珺, 孙韶媛, 姚广顺, 等. 基于深度学习的无人车夜视图像语义分割［J］. 应用光学, 2017, 38(3): 421-427.

GAO Kaiwei, SUN Yiyuan, YAO Guangshun, et al. Semantic segmentation of night vision images of unmanned vehicles based on deep learning［J］. Journal of Applied Optics, 2017, 38(3): 421-427.

[8] LONG J , SHELHAMER E , DARRELL T . Fully convolutional networks for semantic segmentation［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 39(4): 640-651.

[9] BADRINARAYANAN V, KENDALL A, CIPOLLA R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation［J］. ArXiv Preprint ArXiv, 2015, 1511: 00561.

[10] RONNEBERGER O, FISCHER P, BROX T. U-net: Convolutional networks for biomedical image segmentation［C］//International Conference on MedicalImage Computing and Computer-assistedIntervention. Cham: Springer, 2015: 234-241.

[11] 刘哲, 张晓林, 宋余庆, 等. 结合改进的U-Net和Morphsnakes的肝脏分割［J］.中国图象图形学报, 2018, 23(8): 1254-1262.

LIU Zhe, ZHANG Xiaolin, SONG Yuqing, et al. Combined liver segmentation of U-Net and morphsnakes［J］. Journal of Image and Graphics, 2018, 23(8): 1254-1262.

[12] OTSU N . A threshold selection method from Gray-level histograms［J］. IEEE Transactions on Systems, Man, and Cybernetics, 2007, 9(1): 62-66.

[13] BEN P, SUBHANEIL L, MAITHRA R, et al. Exponential expressivity in deep neural networks through transient chaos［C］//Advances in Neural Information Processing Systems.［S.l］: arXiv, 2016: 3360-3368.

[14] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift［C］//Proceedings of the 32nd International Conference on International Conference on Machine Learning.［S.l］: arXiv, 2015: 448-456.

[15] CHOLLET F. Xception: Deep learning with depthwise separable convolutions［C］// IEEE Conference on Computer Vision and Pattern Recognition.USA: IEEE, 2016: 1800-1807.

[16] HE K, ZHANG X, REN S, et al. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification［C］//Proceedings of the IEEE International Conference on Computer Vision.USA: IEEE, 2015: 1026-1034.

[17] 张红英, 彭启琮. 数字图像修复技术综述［J］. 中国图象图形学报, 2007, 12(1): 1-10.

ZHANG Hongying, PENG Qizhen. Overview of digital image restoration technology ［J］. Journal of Image and Graphics, 2007, 12(1): 1-10.

洪汉玉, 孙建国, 栾琳, 王硕, 郑新波. 基于U-net模型的航拍图像去绳带方法[J]. 应用光学, 2019, 40(5): 786. HONG Hanyu, SUN Jianguo, LUAN Ling, WANG Shuo, ZHENG Xinbo. Aerial image de-roping based on U-net model[J]. Journal of Applied Optics, 2019, 40(5): 786.

基于U-net模型的航拍图像去绳带方法

关于本站 Cookie 的使用提示

全站搜索

基于U-net模型的航拍图像去绳带方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索