Abstract
Structure from Motion (SfM) is a 3D reconstruction approach for estimating camera poses and 3D structure from calibrated images. The recovered 3D structure is a sparse 3D point cloud that not permit to well define the shape of the object/scene. We must therefore move to a dense 3D reconstruction that requires a step of the dense matching between pairs of consecutive images, which requires a long calculation time. To reduce computation time, we have proposed an algorithm for the good choice of image pairs that will be used by the Modified Match Propagation (MMP) to improve the sparse 3D reconstruction. These image pairs will be selected on the basis of the result already achieved by SfM. The MMP algorithm will be applied for each image pair to retrieve new matches and their 3D coordinates. The final 3D point cloud is achieved by fusion of results obtained from the image pairs selected. The realistic 3D model is recovered after applying the Poisson surface reconstruction method with texture mapping. The results of the experiments show the speed of the proposed approach without losing quality of 3D reconstructed models.
Similar content being viewed by others
References
El Hazzat S, Merras M, El Akkad N, Saaidi A, Satori K (2018) 3D reconstruction system based on incremental structure from motion using a camera with varying parameters. Vis Comput 34(10):1443–1460
Mouragnon E, Lhuillier M, Dhome M, Dekeyser F, Sayd P (2009) Generic and real-time structure from motion using local bundle adjustment. Image Vis Comput 27(8):1178–1193
Cui H, Gao X, Shen S, Hu Z (2017) HSfM: hybrid structurefrom-motion. Proc Comput Vision Pattern Recogn (CVPR):1212–1221
Wu C (2013) Towards linear-time incremental structure from motion. International conference on 3D vision (3DV): 127–134.
El Hazzat S, Saaidi A, Satori K (2015) Structure from motion for 3D object reconstruction based on local and global bundle adjustment. Proc 2015 Third World Conf Complex Syst:1–6
Merras M, El Hazzat S, Saaidi A, Satori K (2017) 3D face reconstruction using images from cameras with varying parameters. Int J Autom Comput 14(6):661–671
Zhang K, Xu B, Tang L et al (2006) Modeling of binocular vision system for 3D reconstruction with improved genetic algorithms. Int J Adv Manuf Technol 29(7–8):722–728
El Akkad N, El hazzat S, Saaidi A, Satori K (2016) Reconstruction of 3D scenes by camera self-calibration and using genetic algorithms. 3D Res 7(1):1–17
El Hazzat S, Saaidi A, Karam A, Satori K (2015) Incremental multi-view 3D reconstruction starting from two images taken by a stereo pair of cameras. 3D Res 6(1):1–18
Furukawa Y, Ponce J (2010) Accurate, dense, and robust multi-view stereopsis. IEEE Trans Pattern Anal Mach Intell 32(8):1362–1376
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Harris C, Stephens M (1988) A combined corner and edge detector. Fourth Alvey vision conference: 147–151
Lin C, Li Y, Xu G, Cao Y (2017) Optimizing ZNCC calculation in binocular stereo matching. Signal Process Image Commun 52:64–73
Kazhdan M, Bolithp M, Hoppe H (2006) Poisson surface reconstruction. Proc Eurograph Symp Geomet Process:61–70
Zhang Z (2000) A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell 22(11):1330–1334
Wang Y, Liu K, Hao Q, Wang X, Lau DL, Hassebrook LG (2012) Robust active stereo vision using Kullback-Leibler divergence. IEEE Trans Pattern Anal Mach Intell 34(3):548–563
Li YF, Lu RS (2004) Uncalibrated euclidean 3-D reconstruction using an active vision system. IEEE Trans Robot Autom 20(1):15–25
Furukawa Y, Curless B, Seitz SM, Szeliski R (2010) Towards Internet-scale multi-view stereo. Proc Comput Vision Pattern Recogn (CVPR):1434–1441
Kolev K, Klodt M, Brox T, Cremers D (2009) Continuous global optimization in multiview 3D reconstruction. Int J Comput Vis 84(1):80–96
El Hazzat S, Saaidi A, Satori K (2014) Multi-view passive 3D reconstruction: comparison and evaluation of three techniques and a new method for 3D object reconstruction. Fifth Int Conf Next Gen Netw Serv (NGNS):194–201
El Hazzat S, Merras M, El Akkad N, Saaidi A, Satori K (2019) Enhancement of sparse 3D reconstruction using a modified match propagation based on particle swarm optimization. Multimed Tools Appl 78(11):14251–14276
Vu H, Keriven R, Labatut P et al (2009) Towards high resolution large-scale multi-view stereo. Proc Comput Vision Pattern Recogn (CVPR)
Haro G, Pardas M (2010) Shape from incomplete silhouettes based on the reprojection error. Image Vis Comput 28(9):1354–1368
Laurentini A (1994) The visual hull concept for silhouette-based image understanding. IEEE Trans Pattern Anal Mach Intell 16(2):150–162
Kutulakos KN, Seitz SM (2000) A theory of shape by space carving. Int J Comput Vis 38(3):199–218
Blumenthal-Barby D, Eisert P (2014) High-resolution depth for binocular image-based modeling. Comput Graph 39:89–100
Tola E, Strecha C, Fua P (2012) Efficient large-scale multi-view stereo for ultra high-resolution image sets. Mach Vis Appl 23(5):903–920
Tola E, Lepetit V, Fua P (2008) A fast local descriptor for dense matching. Proc IEEE Conf Computer Vision and Pattern Recognition
Wu B, Zhou X, Zhao S, Yue X, Keutzer K (2019). SqueezeSegV2: improved model structure and unsupervised domain adaptation for road-object segmentation from a LiDAR point cloud. Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA): 4376–4382
Yan C, Xie H, Liu S et al (2018) Effective Uyghur language text detection in complex background images for traffic prompt identification. IEEE Trans Intell Transp Syst 19(1):220–229
Yan C, Xie H, Chen J, Zha Z, Hao X, Zhang Y, Dai Q (2018) Cross-modality bridging and knowledge transferring for image understanding. IEEE Trans Multimed 21(10):2675–2685
Lu X, Yao H, Zhao S, Sun X, Zhang S (2019) Action recognition with multi-scale trajectory-pooled 3D convolutional descriptors. Multimed Tools Appl 78(1):507–523
Zhao S, Chen L, Yao H, Zhang Y, Sun X (2015) Strategy for dynamic 3D depth data matching towards robust action retrieval. Neurocomputing 151:533–543
Yang MD, Chao CF, Huang KS, Lu LY, Chen YP (2013) Image-based 3D scene reconstruction and exploration in augmented reality. Autom Constr 33:48–60
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
El Hazzat, S., El Akkad, N., Merras, M. et al. Fast 3D reconstruction and modeling method based on the good choice of image pairs for modified match propagation. Multimed Tools Appl 79, 7159–7173 (2020). https://doi.org/10.1007/s11042-019-08379-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08379-2