Abstract
The paper proposes a new initial disparity estimation algorithm based on sparse local feature matching and one-dimensional dynamic programming. The new algorithm solves the problems of long calculation time, high memory consumption and unknown search range of disparity in the classical pyramid SGM dense matching algorithm. Based on the initial disparity, the final accurate disparity can be got by using SGM algorithm within fixed little search range. The new algorithm is more accurate than the traditional SGM algorithm (by testing on a public data set, the accuracy of new algorithm is 1.57% higher than traditional SGM algorithm), it does not need to artificially estimate the search range of disparity, and it is suitable for implementation on FPGA. Based on the new algorithm, the CPU-FPGA collaborative high-speed dense matching for high-resolution aerial images is realized. The average speed of dense matching on CPU-FPGA is 31.81times faster than the original SGM algorithm and 6.46 times faster than pyramid SGM algorithm. The speed of accurate matching by FPGA is 4.75 times faster than running on GPU.
Similar content being viewed by others
References
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vision 47(1–3), 7–42 (2002)
Gehrke, S., Morin, K., Downey, M., Boehrer, N., Fuchs, T.: Semi-global matching: an alternative to LIDAR for DSM generation. In: 2010 ISPRS Congress, Calgary, AB, Canada, 15–18 June 2010
Zitová, B., Flusser, J.: Image registration methods: a survey. Image Vis. Comput. 21(11), 977–1000 (2003)
Hannah M.J.: Computer matching of areas in stereo images. Ph.D. thesis, Stanford University (1974)
Zhang, Y.J., Zhang, Z.X.: Generalized photogrammetry of spaceborne, airborne and terrestrial multi-source remote sensing datasets. Acta Geod. Cartogr. Sin. 50(a), 1–11 (2021)
Zhang, K., Lu, J., Lafruit, G.: Scalable stereo matching with locally adaptive polygon approximation. In: 15th IEEE International Conference on Image Processing, 2008. ICIP, pp. 313–316 (2008)
Huang, C., Zhao, H.Z.: Semi-global stereo matching with adaptive window based on grayscale value. J. Image Graph. 24(08), 1381–1390 (2019)
Lukezic, A., Vojir, T., Zajc, L.C., et al. : Discriminative correlation filter with channel and spatial reliability. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 4847–4856 (2017)
He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1397–1409 (2013)
Rhemann, C., Hosni, A., Bleyer, M., et al.: Fast cost-volume filtering for visual correspondence and beyond. In: IEEE Conference on Computer Vision & Pattern Recognition (2011)
Sun, J., Zheng, N.N., Shum, H.Y.: Stereo matching using belief propagation. IEEE Trans. Pattern Anal. Mach. Intell. 25(7), 787–800 (2003)
Boykov, Y., Veksler, O., Zabin, R.: Efficient approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1222–1239 (2001)
Hirschmüller, H.: Accurate and efficient stereo processing by semi-global matching and mutual information. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 807–814 (2005)
Hirschmüller, H., Scharstein, D.: Evaluation of stereo matching costs on images with radiometric differences. IEEE Trans. Pattern Anal. Mach. Intell. 31(9), 1582–1599 (2009)
Rothermel, M.: Development of a SGM-Based Multi-view Reconstruction Framework for Aerial Imagery. University of Stuttgart, Stuttgart (2017)
Rothermei, M., Wenzei, K., Fritsch, D., et al.: SURE: photogrammetric surface reconstruction from imagery. In: Proceedings of LC3D Workshop. Berlin (2012)
Liu, Y., Pan, J., Su, Z., et al.: Robust dense correspondence using deep convolutional features. Vis. Comput. 36(4), 827–841 (2020)
Li, Y., Luo, F., Li, W., et al.: Self-supervised monocular depth estimation based on image texture detail enhancement. Vis. Comput. 37(2), 2567–2580 (2021)
Shi, J., Sun, Y., Bai, S., et al.: A self-supervised method of single-image depth estimation by feeding forward information using max-pooling layers. Vis. Comput. 37(4), 815–829 (2020)
Lee, C.A., Gasster, S.D., Plaza, A.: Recent developments in high performance computing for remote sensing: a review. IEEE. J. Sel. Top. Appl. Earth. Observ. Remote. Sens. 4(3), 508–527 (2011)
Nurvitadhi, E., Sheffield. D., Sim. J.: Accelerating binarized neural networks: comparison of FPGA, CPU, GPU, and ASIC. In: International Conference on Field-Programmable Technology, pp. 77–84 (2017)
Puglia, L., Vigliar, M., Raiconi, G.: Real-time low-power FPGA architecture for stereo vision. IEEE. Trans. Circuits Syst. II Exp. Briefs. 64(1), 1307–1311 (2017)
Yao, P., Feng, J.: Ensemble learning with advanced fast image filtering features for semi-global matching. Mach. Vis. Appl. 32(4), 1–15 (2021)
Passalis, N., Tefas, A.: Deep supervised hashing using quadratic spherical mutual information for efficient image retrieval. Signal Process. Image Commun. 93(3), 116–146 (2021)
Gehrig, S.K., Eberli, F., Meyer, T.: A real-time low-power stereo vision engine using semi-global matching. In: Computer Vision Systems. Springer, pp. 134–143 (2009)
Banz, C., Hesselbarth, S., Flatt, H., Blume, H., Pirsch, P.: Real-time stereo vision system using semi-global matching disparity estimation: architecture and FPGA-implementation. In: IEEE International Conference on Embedded Computer Systems (SAMOS), pp. 93–101 (2010)
Hermann, S., Klette, R.: Evaluation of a new coarse-to-fine strategy for fast semi-global stereo matching. In: Advances in Image and Video Technology-pacific Rim Symposium, pp. 395–406 (2012)
Qamar, A., Muslim, F.B., et al.: High-level synthesis for semi-global matching: is the juice worth the squeeze? IEEE Access 6(5), 8419–8432 (2017)
Cambuim, L.F., Barbosa, J.P., Barros, E.N.: Hardware module for low-resource and real-time stereo vision engine using semi-global matching approach. In: 2017 30th Symposium on Integrated Circuits and Systems Design (SBCCI), Fortaleza, pp. 53–58 (2017)
Yoon, K.J., Kweon, I.S.: Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 650–656 (2006)
Ttofis, C., Kyrkou, C., Theocharides, T.: A hardware-efficient architecture for accurate real-time disparity map estimation. ACM Trans. Embed. Comput. Syst. 14(2), 1–26 (2015)
Ttofis, C., Kyrkou, C., Theocharides, T.: A Low-cost real-time embedded stereo vision system for accurate disparity estimation based on guided image filtering. IEEE Trans. Comput. 65(9), 1–11 (2015)
Scharstein, D., Hirschmüller, H., Kitajima, Y., et.al.: High-resolution stereo datasets with subpixel-accurate ground truth. In: German Conference on Pattern Recognition (GCPR 2014), Münster, Germany, pp. 31–42, September 2014
Shahbazi, M., Sohn, G., Theau, J.: High-density stereo image matching using intrinsic curves. ISPRS J. Photogramm. Remote. Sens. 146(12), 373–388 (2018)
Spangenberg, R., Langner, T., Adfeldt, S., Rojas, R.: Large scale semi-global matching on the CPU. In: Proceedings of IEEE Symposium on Intelligent Vehicles Proceedings, pp. 195–201. IEEE, Dearborn (2014)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: IEEE Proceedings of International Conference on Computer Vision, pp. 508–515. IEEE, Vancouver (2001)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient belief propagation for early vision. Int. J. Comput. Vis. 70, 41–54 (2006)
Funding
This study was funded by Natural Science Foundation of Guangxi Province (2020GXNSFAA159091), Guangxi Key laboratory for optoelectronics information Processing (GD18108), Innovation Project of Guangxi Graduate Education (JGY2022131) and Graduate education innovation program of Guilin University of Electronic technology (2022YCXS157).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Peng, Z., Wu, L. & Xiao, B. High-speed dense matching algorithm for high-resolution aerial image based on CPU-FPGA. Vis Comput 39, 5263–5278 (2023). https://doi.org/10.1007/s00371-022-02658-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-022-02658-0