Abstract
The depth data of automobile castings obtained by RGB-D sensor are usually combined with noise, the classical regularization method can eliminate the noise efficiently. Yet the regularization step is too time-consuming to reconstruct the geometric details of automobile castings efficiently. Given this, we present a fast method called fast restoration of automobile castings (FRAC) to restore the geometric details of automobile castings in fast manner. First, the implicit surface data is extracted from globally aligned RGB-D images, the voxel data structure is extended to index and process the implicit surface in real time. Then, an inverse shading formula is constructed to compute TSDF (truncated signed distance field) values of casting surfaces quickly, and an objective function is designed to optimize the geometric details of casting surfaces in real time. Finally, a GPU-based Gauss–Newton solver is used to accelerate restoration of castings further. The defective casting models scanned by RGB-D sensor are quickly refined to a complete model with better accuracy. Experimental results show that with respect to the sampled automobile castings which include 359,470 points in average, the average optimization time reaches 0.66 s per frame, the average restoration time is about 6.48 s. Computing TSDF requires only about 34.8 MB GPU caches in average. FRAC is able to restore the geometric details of automobile castings in real time.
Similar content being viewed by others
References
Werner, D., Al-Hamadi, A., Werner, P.: Truncated signed distance function: experiments on voxel size. ICIAR 2014, pp. 357–364 (2014)
Rasmusson, A., Sørensen, T.S., Ziegler, G.: Connected Components Labeling on the GPU with Generalization to Voronoi Diagrams and Signed Distance Fields. ISVC 2013, pp. 206–215 (2013)
Slavcheva, M., Kehl, W., Navab, N., Ilic, S.: Sdf-2-sdf registration for real-time 3d reconstruction from RGB-D data. Int. J. Comput. Vis. 2, 1–22 (2017)
Li, D.W., Dai, N., Jiang, X.T., Chen, X.S.: Interior structural optimization based on the density-variable shape modeling of 3D printed objects. Int. J. Adv. Technol. J. 83(9–12), 1627–1635 (2015)
Wang, X.C., Zhang, W.W., Wu, X.C., Xiao, L.Y., Qian, Y.B., Fang, Z.: Real-time vehicle type classification with deep convolutional neural networks. J. Real Time Image Proc. (2017). https://doi.org/10.1007/s11554-017-0712-5
Zhu, X., Meng, Q., Gu, L.: Real-time image recognition using weighted spatial pyramid networks. J. Real Time Image Proc. (2017). https://doi.org/10.1007/s11554-017-0743-y
Takimoto, R.Y., Tsuzuki, M.D.S.G., Vogelaar, R., Martins, T.D.C., Sato, A.K., Iwao, Y., et al.: 3d reconstruction and multiple point cloud registration using a low precision RGB-D sensor. Mechatronics 35(January), 11–22 (2016)
Fuhrmann, S., Goesele, M.: Floating scale surface reconstruction. ACM Trans. Graph. 33(4), 1–11 (2014)
Coutinho, M.G.: Appendix G: Constructing signed distance fields for 3D polyhedra. Guide to dynamic simulations of rigid bodies and particle systems, pp. 351–364 (2013)
Barclay, J., Dhokia, V., Nassehi, A.: Additive manufacturing simulation using signed distance fields. Sustainable design and manufacturing, pp. 435–444 (2016)
Garcia-Garcia, A., Orts-Escolano, S., Garcia-Rodriguez, J., et al.: Interactive 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors. J. Real Time Image Proc. 14(3), 585–604 (2018)
Whelan, T., Johannsson, H., Kaess, M.: Robust real-time visual odometry for dense RGB-D mapping. IEEE international conference on robotics and automation, pp. 5724–5731 (2013)
Richardt, C., Stoll, C., Dodgson, N.A.: Coherent spatio temporal filtering, up sampling and rendering of RGBZ videos. Comput. Graph. Forum 31(2pt1), 247–256 (2012)
Denker, K., Hamann, B., Umlauf, G.: On-line CAD reconstruction with accumulated means of local geometric properties. International conference on curves and surfaces 2014, pp: 181–201 (2015)
Wöhler, C.: Geometric approaches to three-dimensional scene reconstruction. 3D computer vision, pp. 3–126 (2009)
Cavallari, T., Stefano, L.D.: On-Line Large Scale semantic fusion. ECCV 2016, pp. 83–99 (2016)
Nießner, M., Izadi, S., Stamminger, M.: Real-time 3d reconstruction at scale using voxel hashing. Acm Trans. Graph. 32(6), 1–11 (2013)
Minh, P., Hoai, V., Quoc, L.: WSDF: weighting of signed distance function for camera motion estimation in RGB-D data. Int. J. Adv. Res. Artif. Intell. 5(9), 27–32 (2016)
Stefani, S.A., Nagarajah, C.R., Toncich, D.J.: Non-contact inspection for the detection of internal surface defects in hollow cylindrical work-pieces. Int. J. Adv. Technol. J. 11(2), 146–154 (1996)
Stavridis, J., Papacharalampopoulos, A., Stavropoulos, P.: Quality assessment in laser welding: a critical review. Int. J. Adv. Technol. J. 94(5–8), 1825–1847 (2018)
Wang, K., Zhang, G., Bao, H.: Robust 3d reconstruction with a RGB-D camera. IEEE Trans. Image Process. 23(11), 4893–4906 (2014)
Harooni, M., Carlson, B., Kovacevic, R.: Detection of defects in laser welding of AZ31B magnesium alloy in zero-gap lap joint configuration by a real-time spectroscopic analysis. Opt. Lasers Eng. 56, 54–66 (2014)
Chang, C.C., Chiang, H.W.: Three-dimensional image reconstructions of complex objects by an abrasive computed tomography apparatus. Int. J. Adv. Technol. J. 22(9–10), 708–712 (2003)
Qin, Y., Brockett, A., Ma, Y., Razali, A., Zhao, J., Harrison, C., Pan, W., Dai, X., Loziak, D.: Micro-manufacturing: research, technology outcomes and development issues. Int. J. Adv. Technol. J. 47(9–12), 821–837 (2009)
Guo, K., Xu, F., Yu, T., Liu, X., Dai, Q., Liu, Y.: Real-time geometry, albedo, and motion reconstruction using a single RGB-D camera. ACM Trans. Graph., 36(3), 32 (2017)
Zollhöfer, M., Dai, A., Innmann, M., Wu, C., Stamminger, M., Theobalt, C.: Shading-based refinement on volumetric signed distance functions. ACM Trans. Graph. 34(4), 1–14 (2015)
Lin, J., Yao, Y., Ma, L., Wang, Y.: Detection of a casting defect tracked by deep convolution neural network. Int. J. Adv. Manuf. Technol. 97(1–4), 1–9 (2018)
Acknowledgements
This project is supported by National High-tech R&D Program (Grant no. 2014AA7031010B) and Science-Technology Project of the thirteenth Five-Year Plan (Grant no. 2016345).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lin, J., Ma, L. Fast restoration of geometric details of automobile castings scanned by RGB-D sensor. J Real-Time Image Proc 17, 871–886 (2020). https://doi.org/10.1007/s11554-018-0835-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-018-0835-3