Adaptive Blur Removal Method of Operating Environment Video for High-Speed Railway

doi:10.3778/j.issn.1002-8331.2104-0030

Abstract

Abstract: Motion blur is a common image degradation phenomenon in the high-speed railway operating environment video, which results in a great challenge to the video-based safety inspection task of high-speed railway operating environment. Firstly, a new video acquisition system for high-speed railway operating environment is proposed, which integrates HD vehicle camera, signal synchronization unit, RFID tag reader, GNSS unit and inertial measurement unit to collect the high-resolution video. Then, an adaptive blur removal method for high-speed railway operating environment is proposed. The inertial measurement unit is used to calculate the motion trajectory of the camera in each frame of image exposure time, and a new deconvolution algorithm is designed to deal with the space-variant blur image, so as to obtain the restored image. Finally, the test is carried out on the actual high-speed railway line by using the detection train. The results show that the proposed method can adaptively remove the blur of the vehicle-mounted high-speed railway operating environmental video, and realize the purpose of collecting high-quality video of the operating environment.

Key words: high-speed railway operating environment, video acquisition system, adaptive blur removal, inertial measurement unit

摘要： 运动模糊是车载高速铁路运行环境视频中普遍存在的图像退化现象，对基于视频的高速铁路运行环境安全检查工作造成很大挑战。提出一种新的车载高速铁路运行环境视频采集系统，集成高清车载摄像机、信号同步单元、RFID标签阅读器、GNSS单元和惯性测量单元，能够采集高分辨率的运行环境视频数据。提出一种高速铁路运行环境视频自适应去模糊方法，利用惯性测量单元计算每帧图像曝光时间内摄像机的运动轨迹，并设计新的去卷积算法处理空间变化的模糊图像，从而得到复原图像。利用检测列车在实际高速铁路线路进行试验验证，结果表明：该方法能够自适应地去除车载高速铁路运行环境视频图像的模糊，实现了采集高质量运行环境视频数据的目的。

关键词: 高速铁路运行环境, 视频采集系统, 自适应去模糊, 惯性测量单元

WANG Fan, ZHAO Hongwei, LIU Junbo, WANG Shengchun, WU Siquan, SU Wenjing, LI Weiyi. Adaptive Blur Removal Method of Operating Environment Video for High-Speed Railway[J]. Computer Engineering and Applications, 2022, 58(21): 258-263.

王凡, 赵宏伟, 刘俊博, 王胜春, 武斯全, 苏文婧, 李唯一. 高速铁路运行环境视频自适应去模糊方法[J]. 计算机工程与应用, 2022, 58(21): 258-263.

References

[1] 周雯.面向高速铁路运行安全的智能图像识别方法研究[D].北京：中国铁道科学研究院，2020.
ZHOU W.Research on intelligent image recognition method for high-speed railway operation safety[D].Beijing：China Academy of Railway Sciences，2020.
[2] 王玮，朱力强.基于特征图裁剪的高铁周界入侵实时检测算法[J].铁道学报，2019，41（9）：74-80.
WANG W，ZHU L Q.Real-time intrusion detection algorithm for high-speed railway based on feature map pruning[J].Journal of the China Railway Society，2019，41（9）：74-80.
[3] 王瑞，史天运，包云.一种基于视频的铁路周界入侵检测智能综合识别技术研究[J].仪器仪表学报，2020，41（9）：188-195.
WANG R，SHI T Y，BAO Y.Research on an intelligent comprehensive recognition technology in railway perimeter intrusion detection[J].Chinese Journal of Scientific Instrument，2020，41（9）：188-195.
[4] 鄢化彪，黄绿娥，王鹏.高速运动的轨道图像去模糊[J].铁道学报，2019，41（12）：75-80.
YAN H B，HUANG L E，WANG P.Motion deblurring from fast railway images[J].Journal of the China Railway Society，2019，41（12）：75-80.
[5] 杨东.模糊降质图像恢复技术研究进展[J].计算机应用研究，2016，33（10）：2881-2888.
YANG D.Research development of restoration technique of blur degraded images[J].Application Research of Computers，2016，33（10）：2881-2888.
[6] 张墨华.基于先验学习的图像复原技术研究[D].郑州：战略支援部队信息工程大学，2019.
ZHANG M H.Research on the technology of image restoration based on prior learning[D].Zhengzhou：PLA Strategic Support Force Information Engineering University，2019.
[7] 陈娟.全局运动模糊图像的盲去模糊算法研究[D].西安：西安电子科技大学，2019.
CHEN J.Research on blind deblurring algorithm of global motion blurred image[D].Xi’an：Xidian University，2019.
[8] LEVIN A，WEISS Y，DURAND F，et al.Understanding and evaluating blind deconvolution algorithms[C]//IEEE Conference on Computer Vision and Pattern Recognition.Miami，FL，USA：IEEE Press，2009：1964-1971.
[9] JOSHI N，SZELISKI R，KRIEGMAN D J.PSF estimation using sharp edge prediction[C]//IEEE Conference on Computer Vision and Pattern Recognition，2008：1-8.
[10] HIRSCH M，SRA S，SCH LKOPF B，et al.Efficient filter flow for space-variant multiframe blind deconvolution[C]//IEEE Conference on Computer Vision and Pattern Recognition，2010：607-614.
[11] ?OREL M，FLUSSER J.Space-variant restoration of images degraded by camera motion blur[J].IEEE Transactions on Image Processing，2008，17（2）：105-116.
[12] YUAN L，SUN J，QUAN L，et al.Progressive inter-scale and intra-scale non-blind image deconvolution[J].ACM Transactions on Graphics，2008，27（3）：1-10.
[13] CHAMBOLLE A，POCK T.A first-order primal-dual algorithm for convex problems with applications to imaging[J].Journal of Mathematical Imaging and Vision，2011，40（1）：120-145.
[14] SCHULER C J，HIRSCH M，HARMELING S，et al.Non-stationary correction of optical aberrations[C]//2011 International Conference on Computer Vision，2011：659-666.
[15] KUPYN V，BUDZAN M，MYKHAILYCH D，et al.DeblurGAN：blind motion deblurring using conditional adversarial networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City，UT，USA：IEEE Press，2018：8183-8192.
[16] MARTYNIUK K T，WU J，WANG Z.DeblurGAN-v2：deblurring（orders-of-magnitude） faster and better[C]//IEEE/CVF International Conference on Computer Vision.Seoul，Korea（South）：IEEE Press，2019：8877-8886.
[17] WANG X，CHAN K C K，YU K，et al.EDVR：video restoration with enhanced deformable convolutional networks[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.Long Beach，CA，USA，IEEE Press，2019：1954-1963.
[18] GAO H，TAO X，SHEN X，et al.Dynamic scene deblurring with parameter selective sharing and nested skip connections[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach，CA，USA：IEEE Press，2019：3843-3851.
[19] 李海浪.高速综合检测列车视频监测系统[J].铁路技术创新，2012（1）：20-22.
LI H L.Video monitoring system of high-speed comprehensive inspection train[J].Railway Technology Innovation，2012（1）：20-22.
[20] MITTAL A，MOORTHY A K，BOVIK A C.No-reference image quality assessment in the spatial domain[J].IEEE Transactions on Image Processing，2012，21（12）：4695-4708.