Dejitter design for infrared laser vehicle cloud platforms

Xiong Jingying; Dai Ming; Zhao Chunlei

doi:10.3788/IRLA201847.0126002

The quality of vehicle records was seriously influenced along with the bumping and shaking driving, and the jittering videos would impact observer reading and interpreting the information. In order to improve the quality of the records, a real-time image stabilization method for vehicle cloud platforms had been proposed. Firstly, the nonlinear filter was adopted to build scale space for the purpose of highlighting edge information; Secondly, a feature detection combined fast image brightness test and gradient calculation was put forward for more quality features, furthermore, increasing the self-salience and differences between descriptors brought discriminative power; Finally, similar features was availably distinguished by location verification for accurate estimation of global motion vector. The time experimental results shown that the proposed approach fulfile the task of real-time, and the average frame rate is over 60 even when the resolution is 720 P. In effective capability experiments, the repeatability of new method is more than 65%, which indicates the enhancement of detection power. Furthermore, the ITF of 6 group tested increase 46.8%, 30.8%, 28.44%, 28.1%, 33.9% and 53.4% after dejitter design, which illustrates that the method significantly improves the effectiveness and precision of the vehicle image stabilization algorithm.

Dejitter design for infrared laser vehicle cloud platforms

1. Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China;

2. University of Chinese Academy of Sciences,Beijing 100049,China

Received Date: 2017-06-05

Rev Recd Date: 2017-08-03

Publish Date: 2018-01-25

Key words:

Abstract: The quality of vehicle records was seriously influenced along with the bumping and shaking driving, and the jittering videos would impact observer reading and interpreting the information. In order to improve the quality of the records, a real-time image stabilization method for vehicle cloud platforms had been proposed. Firstly, the nonlinear filter was adopted to build scale space for the purpose of highlighting edge information; Secondly, a feature detection combined fast image brightness test and gradient calculation was put forward for more quality features, furthermore, increasing the self-salience and differences between descriptors brought discriminative power; Finally, similar features was availably distinguished by location verification for accurate estimation of global motion vector. The time experimental results shown that the proposed approach fulfile the task of real-time, and the average frame rate is over 60 even when the resolution is 720 P. In effective capability experiments, the repeatability of new method is more than 65%, which indicates the enhancement of detection power. Furthermore, the ITF of 6 group tested increase 46.8%, 30.8%, 28.44%, 28.1%, 33.9% and 53.4% after dejitter design, which illustrates that the method significantly improves the effectiveness and precision of the vehicle image stabilization algorithm.

HTML

Reference (15)

[1]	Ji Shujiao, Zhu Ming, Hu Hanping. Aero-borne electronic image stabilization based on feature point matching[J]. Chinese Optics, 2013, 6(6):841-849. (in Chinese)
[2]	Lai Lijun, Xu Zhiyong, Zhang Xuyao. Improved gradient optical flow for digital image stabilization[J]. Infrared and Laser Engineering, 2016, 45(4):0428004. (in Chinese)
[3]	Wu Wei, Xu Tingfa, Wang Yawei, et al. High precision digital image stabilization with full frame compensation[J]. Chinese Optics, 2013, 6(3):378-385.
[4]	David G L. Object recognition from local scale-invariant features[C]//The Seventh IEEE International Conference on Computer Vision, 1999, 2(3):1150-1157.
[5]	Herbert Bay, Tinne Tuytelaars, Luc V G. SURF:Speeded up robust features[J]. Computer Vision-ECCV, 2006, 110(3):404-417.
[6]	He Linying, Liu Jinghong, Li Gang, et al. Fast image registration approach based on improved BRISK[J]. Infrared and Laser Engineering, 2014, 43(8):2722-2727. (in Chinese)
[7]	Ji Shujiao, Zhu Ming, Lei Yanmin, et al. Video stabilization with improved motion vector estimation[J]. Optics and Precision Engineering, 2015, 23(5):1458-1465. (in Chinese)
[8]	Dai Xuemei, Lang Lang, Chen Mengyuan. Research of image feature point matching based on improved ORB algorithm[J]. Journal of Electronic Measurement and Instrumentation, 2016, 30(2):233-240. (in Chinese)
[9]	Chris Whiten, Robert Laganiere, Guillaume A. Bilodeau. efficient action recognition with MoFREAK[C]//Computer and Robot Vision(CRV), 2013 International Conference, 2013, 10(1):319-325.
[10]	Yu Fei, Zhan Xingqun, Liu Ming. Stereo vision tracking and measurement system based on KAZE feature[J]. Computer Measurement Control, 2016, 24(2):30-33. (in Chinese)
[11]	Geng Zexun, Xu Zhijun, Lu Lanxin, et al. Improved KAZE feature matching algorithm with viewpoint change robustness[J]. Optics and Precision Engineering, 2016, 24(3):616-625. (in Chinese)
[12]	Elmar Mair, Gregory D H, Darius Burschka, et al. Adaptive and generic corner detection based on the accelerated segment test[C]//Proceedings of the European Conference on Computer Vision (ECCV'10), 2010, 6312:183-196.
[13]	Zhao Chenchen, Gong Zhihui, Long Yican, et al. The oblique stereo image matching with Shi-Tomasi feature[J]. Journal of Geomatics Science and Technology, 2015(1):66-71. (in Chinese)
[14]	Krystian Mikolajczyk, Tinne Tuytelaars, Cordelia Schmid, et al. A comparison of affine region detectors[J]. Proceedings of the International Journal of Computer Vision, 2005, 65(1):43-72.
[15]	Vinay A, Vinay S S, Akshay K C, et al. Affine-scale invariant feature transform and two-dimensional principal component analysis:a novel framework for affine and scale invariant face recognition[J]. Iet Computer Vision, 2016, 10(1):43-59.

Dejitter design for infrared laser vehicle cloud platforms

doi: 10.3788/IRLA201847.0126002

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views