Development of an Algorithm for Evaluation of Geometric Characteristics of Walls by Computer Vision System
DOI:
https://doi.org/10.22213/2413-1172-2019-4-57-63Keywords:
computer vision, wall defects, structured light, evaluation algorithmAbstract
The paper considers the problems of assessing the quality of construction work. The main defects of the walls are revealed: the deviation of the wall from verticality, convexity and concavity, deviations of wall angles from 90 degrees, the taper of door and window openings.
The algorithm of the operating of the computer vision system is presented. It allows for restoring the three-dimensional coordinates of walls by analyzing the deformation of the structured grid projected to them. The key objects for reconstructing the geometry are the intersections of the horizontal and vertical lines of the contrast grid. The obtained coordinates of the key points are compared with the coordinates of the key points in the ideal case, i.e. when projected to an absolutely vertical plane.
The formula for calculating the deviation from the vertical for each key point is presented. The method for approximating the obtained discrete values by an analytically given surface is proposed. It allows to accurately classify defects and determine their quantitative characteristics, as well as calculate the volume of materials to eliminate them. The most applicable types of second-order surfaces are considered.
As part of the study, it is planned to create functional software with a convenient user interface, based on the developed algorithm, and evaluate the developed system in practice.References
Bakri N.N.O., Mydin M.A.O. General building defects: causes, symptoms and remedial work. European Journal of Technology and Design, 2014, no. 1, pp. 4-17.
Galieva А.B. Defects search during the inspection of civil and industrial buildings and structures on the basis of laser scanning technology and information modeling approach (BIM). MATEC Web of Conferences. EDP Sciences, 2018, vol. 146, p. 01007.
Karavaeva M.V. [Analysis of computer vision systems applied for evaluation of the geometric characteristics of building wall] // Технические университеты: интеграция с европейскими и мировыми системами образования : материалы VIII Междунар. конф. (Россия, Ижевск, 23–24 апреля 2019 г.) : в 2 т. Ижевск : Изд-во ИжГТУ имени М. Т. Калашникова, 2019. Т. 2. C. 437–440.
Pribanic T., Mrvos S., Salvi J. Efficient multiple phase shift patterns for dense 3D acquisition in structured light scanning. Proc. Image and Vision Computing, 2010, vol. 28, no. 8, pp. 1255-1266.
Караваева М. В. Определение количественных характеристик дефектов стен зданий по искажению проецируемой структурированной сетки // Интеллектуальные системы в производстве. 2018. № 4. C. 40–44.
Sagawa R. Calibration of lens distortion by structured-light scanning. Proc. IEEE/RSJ International Con-ference on Intelligent Robots and Systems. IEEE, 2005, pp. 832-837.
Chen C., Kak A. Modeling and calibration of a structured light scanner for 3-D robot vision. IEEE International Conference on Robotics and Automation. IEEE, 1987, vol. 4, pp. 807-815.
Гонзалес Р., Вудс Р. Цифровая обработка изображений. М. : Техносфера, 2006. 1072 с.
Яне Б. Цифровая обработка изображений. М. : Техносфера, 2007. 584 с.
Шапиро Л., Стокман Дж. Компьютерное зрение. М. : БИНОМ. Лаборатория знаний, 2006. 752 с.
Culjak I. A brief introduction to OpenCV. Proc. 35th international convention MIPRO. IEEE, 2012, p. 1725-1730.
Laganiere R. Open CV Computer Vision Application Programming Cook book Second Edition. Packt Publ. Ltd, 2014, 376 p.
Марчук Г. И. Методы вычислительной математики. М. : Наука, 1980. 608 с.
Dorninger P., Pfeifer N. A comprehensive automated 3D approach for building extraction, reconstruction and regularization from airborne laser scanning point clouds. Sensors, 2008, vol. 8, no. 11, p. 7323-7343.
Pu S., Vosselman G. Knowledge based reconstruction of building models from terrestrial laser scanning data. ISPRS Journal of Photogrammetry and Remote Sensing, 2009, vol. 64, no. 6, pp. 575-584.
Hidayatullah P., Zuhdi M. Colortexture based object tracking using HSV color space and local binary pattern. International Journal on Electrical Engineering and Informatics, 2015, vol. 7, no. 2, p. 161.
Караваев Ю. Л., Клековкин А. В., Лесин С. К. Мультисенсорная информационно-измерительная система мобильного робота для реализации движения в недетерминированной среде // Интеллектуальные системы в производстве. 2016. T. 4. С. 111–115.
