Abstract
Changes of the flight attitude of unmanned aircraft cause nonlinear distortion in the aerial images. Stitching these images without geometric rectification may cause the problem of mismatching. However, the geometric rectification model produces invalid regions at the edge of images. A direct cutting for these invalid regions leads to removing lots of useful information, whereas a noisy seam is visible in the stitched image if the edge cutting is omitted. We propose a solution of edge detection for detecting invalid and noisy regions. More precisely, our method includes two passes of edge detection for images with geometric rectification. The first pass of image edge detection is to find the boundary between valid and invalid scenes. The second pass is to detect the noisy regions. The invalid and noisy regions are finally removed for image stitching, and the effective areas of the image are kept to the maximum extent. Experimental results demonstrate the efficacy of the proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kim, J., Kim, T., Shin, D., Kim, S.: Fast and robust geometric correction for mosaicking UAV images with narrow overlaps. Int. J. Remote Sens. 38(8–10), 2557–2576 (2017)
Liew, L.H., Lee, B.Y., Wang, Y.C., Cheah, W.S.: Simulation study on distribution of control points for aerial images rectification. In: Yeo, S.-S., et al. (eds.) Computer Science and its Applications. Lecture Notes in Electrical Engineering (LNEE), vol. 203, pp. 169–177. Springer, Dordrecht (2012). https://doi.org/10.1007/978-94-007-5699-1_18
More, G., Pons, X.: Influence of the nature and number of ground control points to the quality of remote sensing geometric corrections. In: International Geoscience and Remote Sensing Symposium (IGARSS), Munich, Germany, pp. 2356–2359 (2012)
Bagheri, H., Sadeghian, S.: Geometric rectification of high resolution satellite images using mathematical intelligent & classical modelling. In: Iranian Conference on Intelligent Systems (ICIS), Bam, Iran, pp. 1–6 (2014)
Deng, H., Wang, L., Liu, J., Li, D., Chen, Z., Zhou, Q.: Study on application of scale invariant feature transform algorithm on automated geometric correction of remote sensing images. In: Advances in Information and Communication Technology, IFIP AICT, vol. 393, PART 2, pp. 352–358 (2013)
Devaraj, C., Shah, C.A.: Automated geometric correction of landsat MSS L1G imagery. IEEE Geosci. Remote Sens. Lett. 11(1), 347–351 (2014)
Brown, M., Lowe, D.G.: Automatic panoramic image stitching using invariant features. Int. J. Comput. Vis. 74(1), 59–73 (2007)
Zhou, G.: Near real-time orthorectification and mosaic of small UAV video flow for time-critical event response. IEEE Trans. Geosci. Remote Sens. 47(3), 739–747 (2009)
Liu, J., Gong, J., Guo, B., Zhang, W.: A novel adjustment model for mosaicking low-overlap sweeping images. IEEE Trans. Geosci. Remote Sens. 55(7), 4089–4097 (2017)
Li, Z.: Geometrical Rectification for Unmanned Aerial Vehicle Remote Sensing Images without Control Points. Thesis, University of Electronic Science and Technology of China (in Chinese), pp. 9–29 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Liu, ZX., Lin, QH., Hao, YG. (2018). Image Edge Detection for Stitching Aerial Images with Geometrical Rectification. In: Huang, T., Lv, J., Sun, C., Tuzikov, A. (eds) Advances in Neural Networks – ISNN 2018. ISNN 2018. Lecture Notes in Computer Science(), vol 10878. Springer, Cham. https://doi.org/10.1007/978-3-319-92537-0_61
Download citation
DOI: https://doi.org/10.1007/978-3-319-92537-0_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92536-3
Online ISBN: 978-3-319-92537-0
eBook Packages: Computer ScienceComputer Science (R0)