Research on Image Stitching Technology for Road Surface Cracks
DOI:
https://doi.org/10.62051/ijcsit.v2n1.38Keywords:
Pavement Crack Image, Feature Point Detection, Image FusionAbstract
Image stitching refers to the combination of multiple images with a certain over lappingarea rate acquired by the image acquisition device into one image, which has a full picture of each image. Image stitching technology is an important part in the field of digital image processing. With the increasing requirements for image quality and the limited resolution of ordinary cameras, it is impossible to obtain large angle of view and clear image at the same time. In this paper, the key technologies involved in pavement crack image stitching are intensively studied, including image feature point detection and matching, internal and external camera parameter estimation and optimization, and image fusion. The work done in this paper and the main innovations include: (1)Two main feature detection and description algorithms, SIFT algorithm and ORBalgorithm, are studied. In view of the fact that the SIFT algorithm has redundancy when the Gaussian pyramid is established, this paper appropriately reduces the number of groups and maintains the number and stability of feature point detection. Combined with the advantages and disadvantages of the improved SIFT algorithm and ORB algorithm, and the performance of the two algorithms in the detection of pavement cracks, the improvedSIF'T algorithm is used as the feature point detection algorithm, and rBRlEF algorithm for describing the feature points in the ORB algorithm is used as the feature point description algorithm. The description algorithm is called the BSIF'T algorithm. Experiments show that the robustness of BSIFT algorithm is similar to that of SIFT algorithm, which is better than ORB algorithm and faster than SIF'T algorithm. (2)Image fiusion algorithms are studied, including best seam-line search and image fusion. Aiming at the ghost phenomenon that may occur in overlapping regions, this paper proposes a best seam-line search algorithm based on distance transform.
Downloads
References
Zhang,2.,Deriche,R.,Faugeras,O, et al. 1995. A robust technique for matching twouncalibrated images through the recovery of the unknown epipolar geometrylC]. ArtificialIntelligence,78:87-119
Lowe, D. G.. Object recognition from local scale-invariant features|P]. Computer Vision, 1999The Proceedings of the Seventh lEEE International Conference on,1999.
D. Lowe. Distinctive image features from scale-invariant keypoints]]. International Journal of Computer Vision, 60(2):91-110,2004.
Simo-Serra, E., Trulls, E., Ferraz, L., et al. Moreno-Noguer, F.: Discriminative Learning of DeepConvolutional Feature Point Descriptors[C].In: ICCV.(2015)
Yi, K., Verdie, Y., Lepetit, V., et al. Leaming to Assign Orientations to Feature PointslC]. In:CVPR.(2016)
Han Chao, Fang Lu, Zhang Sheng. An optimized image registration algorithm. Journal of electronic measurement and instrumentation,2017,31(2):178-184.
Zhang J, Chen G, Jia Z. An image stitching algorithm based on Histogram matching and SIFT algorithm_]. International Journal of Pattern Recognition &. Artificial Intelligence, 2017, 31(04):381-395.
Horun M. H. Multilevel minimum cross entropy threshold selection based on the honeybee mating optimization[1]. Expert System with Applications, 2010,37(6): 4580-4592.
Toh K K V, Isa N.A.M. Noise adaptive fuzzy switching median filter for salt-and-peppernoise reduction1l. Signal Processing Letters, IEEE, 2010, 17(3): 281-284.
LI WJ, ZHANG M, SHEN Z H, et al. Track crack detection meth-od in complex environment [C]//11th International Symposium onComputational Intelligence and Design (ISCID). New York: IEEE,2018:356-359.
YUSOF' N A M, OSMAMN M K, NOOR M H M, et al. Crack de-tection and classification in asphalt pavement images using deepconvolution neural network [C]//8th IEEE International Conference on Control System, Computing and Engineering(ICCSCE)New York: EEE, 2018:227-232.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Chunlin He, Jiaye Wu, Yujie Yang

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







