Depth Map Reconstruction Method in Control Problems for Robots and Mechatronic Systems
https://doi.org/10.17587/mau.23.104-112
Abstract
In modern robotic and mechatronic systems, technologies are in demand that makes it possible to build an optimal trajectory of movement of their actuators. Such technologies are formed by combining navigation methods and building a 3-D map of the surrounding space based on vision systems and are successfully used in robotics and mechatronics. But there is a problem, consisting of a decrease in the accuracy of planning the trajectory of movement, caused by incorrect sections on the map (depth map) due to incorrect determination of the distance to objects. Such defects appear as a result of poor lighting, specular or fine-grained surfaces of objects. This leads to the impossibility of obtaining reliable information about the depth. As a result, the effect of increasing the boundaries of objects (obstacles) appears, and the overlapping of objects makes it impossible to distinguish one object from another. This problem can be solved using image reconstruction methods. The article presents an approach based on a modified algorithm for searching for similar blocks using the concept of quaternions and anisotropic gradient. The analysis of the research results shows that the proposed method allows you to correctly restore the boundaries of objects on the depth map image when reconstructing 3-D scenes, which contributes to an increase in the accuracy of planning the trajectory of motion of the actuators robotic and mechatronic systems.
Keywords
trajectory planning,
RTC navigation,
video sequence reconstruction,
quaternion space,
anisotropic gradient,
neural network
Supporting agencies: The study was supported by a grant from the Russian Science Foundation No. 21-79-10392, https://rscf.ru/project/21-79-10392/.
About the Authors
A. A. Zelensky
Center for Cognitive Technology and Machine Vision, Moscow State University of Technology "STANKIN"
Russian Federation
Russian Federation
Moscow, 115432
N. V. Gapon
Center for Cognitive Technology and Machine Vision, Moscow State University of Technology "STANKIN"; Don State Technical University
Russian Federation
Russian Federation
Moscow, 115432
Rostov-on-Don, 344000
M. M. Zhdanova
Center for Cognitive Technology and Machine Vision, Moscow State University of Technology "STANKIN"
Russian Federation
Russian Federation
Moscow, 115432
V. V. Voronin
Center for Cognitive Technology and Machine Vision, Moscow State University of Technology "STANKIN"
Russian Federation
Russian Federation
Voronin Viacheslav V., Ph.D., Associate Professor
Moscow, 115432
Y. V. Ilyukhin
Center for Cognitive Technology and Machine Vision, Moscow State University of Technology "STANKIN"
Russian Federation
Russian Federation
Moscow, 115432
References
1. Zelensky A. A., Franz V. A., Semenishchev E. A. Algorithm for planning the trajectory of the working body of the manipulator for binding the basic coordinate systems using technical vision, Vestnik Mashinostroeniya, 2019, no. 10, pp. 3—7 (in Russian)
2. Zelensky A. A., Stebulyanin M. M., Abdullin T. Kh., Kharkov M. A. Implementation of accelerated computations of the direct problem of kinematics for industrial robots, Vestnik Mashinostroeniya, 2019, no. 11, pp. 28—31 (in Russian)
3. Gharatappeh S., Ghorbanian M., Keshmiri M., Taghirad H. D. Modified fast-SLAM for 2D mapping and 3D localization, 3rd RSI International Conference on Robotics and Mechatronics (ICROM), 2015, pp. 108—113.
4. Dissanayake G., Newman P. Durrant-Whyte H. F., Clark S., Csorba M. A solution to the simultaneous localization and map building (SLAM) problem, IEEE transaction robotic automation, 2001, no. 17(3), pp. 229—241.
5. Bertalmio M., Bertozzi A. L., Sapiro G. Navier—Stokes, uid dynamics, and image and video inpainting, Proc. IEEE Conf. Comput. Vis. Pattern Recognition, 2001, pp. 355—362.
6. Telea A. An image inpainting technique based on the fast marching method, Journal of graphics tools, 2004, vol. 9, no. 1, pp. 23—34.
7. Voronin V. V., Marchuk V. I., Egiazarian K. O., Sherstobitov A. I. Image inpainting using cubic spline-based edge reconstruction, Proceedings of SPIE Image Processing: Algorithms and Systems X, 2012, vol. 8295, pp. 82950I.
8. Chaudhury S., Roy H. Can fully convolutional networks perform well for general image restoration problems? IEEE: Fifteenth IAPR International Conference on Machine Vision Applications (MVA), 2017, pp. 254—257.
9. Liu M. Image inpainting and super-resolution using nonlocal recursive deep convolutional network with skip connections, Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, no. 10420, pp. 104203A.
10. Jiang L., Xiao S., He C. Kinect depth map inpainting using a multi-scale deep convolutional neural network, Proceedings of the 2018 International Conference on Image and Graphics Processing, 2018, pp. 91—95.
11. Voronin V. V., Marchuk V. I., Fisunov A. V., Tokareva S. V., Egiazarian K. O. Depth map occlusion filling and scene reconstruction using modified exemplar-based inpainting, Proc. SPIE 9399, Image Processing: Algorithms and Systems XIII, 2015, pp. 93990S.
12. Marchuk V. I., Voronin V. V., Frantz V. A. Development of 2D adaptive method of estimation reproduction for image reconstruction in incomplete a priori information, Telecommunications and Radio Engineering, 2013, vol. 72(13), pp. 1255—1262.
13. Criminisi A., Perez P., Toyama K. Region lling and object removal by exemplar-based image inpainting, IEEE Transactions on Image Processing, 2004, no. 13, pp. 1200—1212.
14. Katkovnik V., Egiazarian K., Astola J. Local Approximation Techniques in Signal and Image Processing, SPIE Press, Bellingham. USA, 2006, vol. PM157
15. Voronin V., Zelensky A., Agaian S. The quaternion-based anisotropic gradient for the color images, Electronic Imaging, Image Processing: Algorithms and Systems XVII, 2019, pp. 277-1—277-6.
16. Voronin V. V., Marchuk V. I., Egiazarian K. O. Images reconstruction using modied exemplar based method, SPIE Electronic Imaging, 2011, vol. 7870, pp. 78700N.
17. Grigoryan A. M., Agaian S. S. Retooling of color imaging in the quaternion algebra, Applied Mathematics and Sciences: An International Journal (MathSJ), 2014, vol. 1, no. 3, pp. 23—39.
18. Voronin V., Gapon N., Khamidullin I., Tokareva O., Cen Y., Zelensky A. Infrared image inpainting using hypercomplex analysis, Proc. SPIE 11537, SPIE Security + Defence, ElectroOptical and Infrared Systems: Technology and Applications XVII, 2020, pp. 115370U.
19. Foi A., Katkovnik V., Egiazarian K. Pointwise shapeadaptive DCT for high-quality denoising and deblocking of grayscale and color images, IEEE transactions on image processing, 2007, vol. 16, no. 5, pp. 1395—1411.
20. Kim Y., Ham B., Oh C., Sohn K. Structure selective depth super-resolution for RGB-D cameras, IEEE Trans. on Image Processing, 2016, vol. 25, no. 11, pp. 5527—38.
21. Sturm J., Engelhard N., Endres F., Burgard W., Cremers D. A Benchmark for the Evaluation of RGB-D SLAM Systems, Proc. of the International Conference on Intelligent Robot Systems (IROS), 2012, pp. 573—580.
Review
For citations:
Zelensky A.A., Gapon N.V., Zhdanova M.M., Voronin V.V., Ilyukhin Y.V. Depth Map Reconstruction Method in Control Problems for Robots and Mechatronic Systems. Mekhatronika, Avtomatizatsiya, Upravlenie. 2022;23(2):104-112. (In Russ.) https://doi.org/10.17587/mau.23.104-112
Views:
573
.png)
Email this article 