浏览全部资源
扫码关注微信
收稿：2020-01-17，
修回：2020-8-24，
录用：2020-8-31，
纸质出版：2021-03-16
移动端阅览
目的
2
双目测距和单目测距是目前常用的两种基于光学传感器的测距方法，双目测距需要相机标定和图像配准，计算量大且测量范围有限，而单目测距减少了对设备和场地的要求，加快了计算时间。为了解决现有的单目测距方法存在精度低、鲁棒性差等缺点，本文提出了一种基于单模糊图像和B样条小波变换的自适应距离测量方法。
方法
2
引入拉普拉斯算子量化评估图像模糊程度，并根据模糊程度值自动定位阶跃边缘；利用B样条小波变换代替高斯滤波器主动模糊化目标图像，并通过分析图像模糊程度、模糊次数以及测量误差之间的关系模型，自适应地计算不同景物图像的最优模糊次数；根据最优模糊图像中阶跃边缘两侧模糊程度变化求解目标边缘和相机之间的相对距离。
结果
2
本文方法与基于高斯模糊图像的距离测量方法相比精度更高，平均相对误差降低5%。使用不同模糊次数对同样的图像进行距离测量时，本文算法能够自适应选取最优模糊次数，保证所测量距离的精度更高。
结论
2
本文提出的单视觉测距方法，综合了传统的方法和B样条小波的优点，测距结果更准确，自适应性和鲁棒性更高。
Objective
2
In the robot's path planning and obstacle avoidance process
measuring the relative distance between the target and the sensor is very important. Distance measurement methods based on optical sensors have the advantages of portability
intuitiveness
and low cost. Therefore
they are widely used in real applications. Visual distance measurement methods commonly include monocular visual measurement and binocular visual measurement. There are two main methods for binocular image measurement: estimating the distance between the target and the camera by comparing two blurred images with different optical parameters or measuring the distance by comparing the parallax maps of these two images. However
both methods require sufficient baseline distance between the left and right cameras. Therefore
they are not suitable for smaller installation sites (unmanned boats). Furthermore
they are computationally expensive and difficult to be used in real-time applications. Monocular vision measurement was first proposed by Pentland. The basic principle is calculating the distance between the edge in the target image and the camera through the brightness changes on both sides of the target edge. Compared with binocular vision measurement
monocular vision measurement requires only one camera
and its calculation principle is simple. However
the following problems still exist in practical applications. 1) These methods are based on the exact position evaluation of the target step edge in a single image. However
this condition is difficult to be satisfied in practical applications. Therefore
a preprocessing module for detecting edges should be added
which increases the complexity and reduces the adaptability of these methods. 2) When using the Gaussian filter to approximate the fuzzy point spread function
the problems of losing the edge of slow change and the low accuracy of edge positioning in Gaussian filtering are ignored. The positioning accuracy directly affects the accuracy of monocular measurement. 3) The blurring degree of an image is related directly to the accuracy of measurement. In spite of this
the distance measurement is performed by the method to re-blur the target image multiple times. Moreover
the quantitative relationship between the number of re-blur process and the accuracy of the distance measurement is unknown. Therefore
the distance measurement accuracy is difficult to control and improve from the perspective of active blurring.
Method
2
This study proposes an adaptive method of measuring distance on the basis of a single blurred image and the B-spline wavelet function. First
the Laplacian operator is introduced to quantitatively evaluate the blurring degree of the original image and locate the target edge automatically. According to the principle of blurring
the blurring degree of the original image increases as the number of re-blur increases. When the blurring degree reaches a certain amount
it will change more slowly until it cannot judge the change in the blurring degree caused by two adjacent re-blurs. On the other hand
as the re-blur number increases
the distance measurement accuracy first increases and then decreases rapidly when the re-blur number reaches a certain value. Therefore
the relationship among the calculated blurring degree
re-blur number
and distance measurement error is established. Then
the B-spline wavelet function is used to replace the traditional Gaussian filter to re-blur the target image actively
and the optimal re-blur number is adaptively calculated for different scene images on the basis of the relationship among the blurring degree of image
number of blurs
and measurement error. Finally
according to the change ratio of the blurring degree on both sides of the step edge in the original blurred image
the distance between the edge and the camera is calculated.
Result
2
A comparison experiment with respect to different practical images is conducted. The experimental results show that the method in this study has higher accuracy than the method of measuring distance on the basis of re-blur with the Gaussian function. Comparatively
the average relative error decreases by 5%. Furthermore
when the distance measurement is performed on the same image with different re-blur numbers
the measurement accuracy is higher with the optimal re-blur number obtained with the relationship among the blurring degree of image
number of blurs
and measurement error.
Conclusion
2
Our proposed distance measurement method combines the advantages of traditional distance measurement method with the Gaussian function and the cubic B-spline function. Owing to the advantages of B-spline in progressive optimization and the optimal re-blur number achievement method
our method has higher measurement accuracy
adaptivity
and robustness.
Chahal N, Pippal M and Chaudhury S. 2016. Depth estimation from single image using machine learning techniques//Proceedings of the 10th Indian Conference on Computer Vision, Graphics and Image Processing. Guwahati, India: ACM: 1-8[ DOI: 10.1145/3009977.3010019 http://dx.doi.org/10.1145/3009977.3010019 ]
Ens J and Lawrence P. 1993. An investigation of methods for determining depth from focus. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(2): 97-108[DOI: 10.1109/34.192482]
Guo C Y and Li J P. 2013. Development and future of wavelet analysis//Proceedings of the 10th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). Chengdu, China: IEEE: 335-338[ DOI: 10.1109/ICCWAMTIP.2013.6716661 http://dx.doi.org/10.1109/ICCWAMTIP.2013.6716661 ]
He L, Wang G H and Hu Z Y. 2018. Learning depth from single images with deep neural network embedding focal length. IEEE Transactions on Image Processing, 27(9): 4676-4689[DOI: 10.1109/TIP.2018.2832296]
Jin H Z. 1990. Infrared ranging principle and its application in survey and design. Infrared Technology, 12(3): 24-26
金和钟. 1990. 红外测距原理及其在勘测设计中的应用. 红外技术, 12(3): 24-26
Lan K T and Lan C H. 2008. Notes on the distinction of Gaussian and Cauchy mutations//Proceedings of the 8th International Conference on Intelligent Systems Design and Applications. Kaohsiung, China: IEEE Computer Society: 272-277[ DOI: 10.1109/ISDA.2008.237 http://dx.doi.org/10.1109/ISDA.2008.237 ]
Li Y, Wang K, Wang Q Z, Sun B and Kang W W. 2010. Structure of dual-tree complex wavelet filter on B-spline in image edge detection//Proceedings of the 2nd International Conference on Advanced Computer Control. Shenyang, China: IEEE: 427-431[ DOI: 10.1109/ICACC.2010.5486888 http://dx.doi.org/10.1109/ICACC.2010.5486888 ]
Liu J Y, Wei Y J, Yu P, Liu Z, Yang Y, Liu L Q and Li H K. 2015. Auto-feeding technique of AFM probes based on machine vision//roceedings of 2015 China Automation Congress(CAC 2015). Wuhan, China: IEEE: 2404-2410
刘静怡, 魏阳杰, 于鹏, 刘柱, 杨洋, 刘连庆, 李洪奎. 2015. 基于机器视觉的AFM探针自动逼近技术研究//2015年中国自动化大会. 武汉, 中国: IEEE: 2404-2410
Mahmoudpour S and Kim M. 2016. Superpixel-based depth map estimation using defocus blur//Proceedings of 2016 IEEE International Conference on Image Processing. Phoenix, USA: IEEE: 2613-2617[ DOI: 10.1109/ICIP.2016.7532832 http://dx.doi.org/10.1109/ICIP.2016.7532832 ]
Mancini M, Costante G, Valigi P, Ciarfuglia T A, Delmerico J and Scaramuzza D. 2017. Toward domain independence for learning-based monocular depth estimation. IEEE Robotics and Automation Letters, 2(3): 1778-1785[DOI: 10.1109/LRA.2017.2657002]
Namboodiri V P and Chaudhuri S. 2008. Recovery of relative depth from a single observation using an uncalibrated(real-aperture) camera//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, USA: 1-6[ DOI: 10.1109/CVPR.2008.4587779 http://dx.doi.org/10.1109/CVPR.2008.4587779 ]
Pentland A P. 1987. A new sense for depth of field. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-9(4): 523-531[DOI: 10.1109/TPAMI.1987.4767940]
Sui W P. 2003. Research on High-Precision Real-Time Ultrasonic Ranging Technology. Changsha: National University of Defense Technology
隋卫平. 2003. 高精度实时超声测距技术研究. 长沙: 国防科学技术大学
Unser M A. 1997. Ten good reasons for using spline wavelets//Proceedings Volume 3169, Wavelet Applications in Signal and Image Processing V. San Diego, USA: SPIE: 422-431[ DOI: 10.1117/12.292801 http://dx.doi.org/10.1117/12.292801 ]
Xiao B. 2010. Methods for laser distance measurement. Geospatial Information, 8(4): 162-164
肖彬. 2010. 激光测距方法探讨. 地理空间信息, 8(4): 162-164[DOI: 10.3969/j.issn.1672-4623.2010.04.053]
Xu Y X, Xu Y L and Deng C X. 2011. A type of construction of compactly supported symmetric and anti-symmetric multi-wavelet//Proceedings of International Conference on Wavelet Analysis and Pattern Recognition. Guilin, China: IEEE: 197-201[ DOI: 10.1109/ICWAPR.2011.6014469 http://dx.doi.org/10.1109/ICWAPR.2011.6014469 ]
Yang Z B, Chen X F, Zhang X W and He Z J. 2013. Free vibration and buckling analysis of plates using B-spline wavelet on the interval Mindlin element. Applied Mathematical Modelling, 37(5): 3449-3466[DOI: 10.1016/j.apm.2012.07.055]
Zhuo S J and Sim T. 2009. On the recovery of depth from a single defocused image//Proceedings of Computer Analysis of Images and Patterns. Berlin, Germany: Springer: 889-897[ DOI: 10.1007/978-3-642-03767-2_108 http://dx.doi.org/10.1007/978-3-642-03767-2_108 ]
相关作者
相关机构
京公网安备11010802024621
