Abstract
Seam-line searching algorithm is one of the widely used image fusion method to stitch images. The major methods of generating seam-line mainly take considering the correlation between the pixels, resulting in a so-called “seam-line crossing the object” phenomenon, which greatly deteriorates the visual experience of the final stitching result. To overcome the above problem, this paper proposes an improved seam-line searching algorithm based on object detection. After image registration of reference and target images with the as-projective-as-possible warp or the adaptive as-natural-as-possible warp, the Single-Shot Detector model is applied to detect objects in the overlapping regions of the registered images. Considering the smallest difference in color and structure, the seam-line is allowed to extend along the edge of these objects which are not supposed to be crossed as much as possible if this line crosses these objects. The experimental results show that our method can effectively avoid “seam-line crossing the object” phenomenon and make the mosaic images look more natural. At the same time, our method can also be combined with global warp and other more advanced local-warp-based alignment methods to obtain better stitching results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, F., Liu, F.: Parallax-tolerant image stitching. In: CVPR 2014, pp. 3262–3269 (2014)
Lin, C.-C., Pankanti, S., Ramamurthy, K.N., Aravkin, A.Y.: Adaptive as-natural-as-possible image stitching. In: CVPR 2015, pp. 1155–1163 (2015)
Szeliski, R.: Image alignment and stitching. In: Paragios, N., Chen, Y., Faugeras, O. (eds.) Handbook of Mathematical Models in Computer Vision, pp. 273–292. Springer, Boston (2005). https://doi.org/10.1007/0-387-28831-7_17
Chen, Y.-S., Chuang, Y-Yu.: Natural image stitching with the global similarity prior. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 186–201. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_12
Zaragoza, J., Chin, T.-J., Brown, M.S., Suter, D.: As-projective-as-possible image stitching with moving DLT. In: CVPR 2013, pp. 2339–2346 (2013)
Chang, C.-H., Sato, Y., Chuang, Y.-Y.: Shape-preserving half-projective warps for image stitching. In: CVPR 2014, pp. 3254–3261 (2014)
He, C., Zhou, J.: Mesh-based image stitching algorithm with linear structure protection. J. Image Graph. 23(7), 973–983 (2018)
Zhang, J., Chen, G., Jia, Z.: An image stitching algorithm based on histogram matching and sift algorithm. IJPRAI 31(4), 1–14 (2017)
Tian, F., Shi, P.: Image mosaic using orb descriptor and improved blending algorithm. JMPT 5(3), 98–108 (2014)
Fang, X., Pan, Z., Xu, D.: An improved algorithm for image mosaic. J. Comput. Aided Des. Comput. Gra 15(11), 1362–1365 (2003)
Liu, Q., Cai, H., Chen, G., Dou, S., Yang, Y.: An image mosaic method based on improving seam line. In: ICNC-FSKD, pp. 414–418 (2016)
Li, L., Yao, J., Li, H., Xia, M., Zhang, W.: Optimal seamline detection in dynamic scenes via graph cuts for image mosaicking. Mach. Vis. Appl. 28(8), 819–837 (2017)
Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Acknowledgment
This work is supported by the National Natural Science Foundation of China under Grant Nos. 61631016 and 61371191, and the Project of State Administration of Press, Publication, Radio, Film and Television under Grant No. 2015-53.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sun, R., Li, C., Zhong, W., Ye, L. (2019). An Improved Seam-Line Searching Algorithm Based on Object Detection. In: Zhai, G., Zhou, J., An, P., Yang, X. (eds) Digital TV and Multimedia Communication. IFTC 2018. Communications in Computer and Information Science, vol 1009. Springer, Singapore. https://doi.org/10.1007/978-981-13-8138-6_2
Download citation
DOI: https://doi.org/10.1007/978-981-13-8138-6_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-8137-9
Online ISBN: 978-981-13-8138-6
eBook Packages: Computer ScienceComputer Science (R0)