Research on Stereo Matching Method for Ultra-Thin Strip-Shaped Materials of Power Battery Covers Based on Multi-Algorithm Fusion
DOI:
https://doi.org/10.54097/jej2vn81Keywords:
Power battery top cover, Ultra-thin strip material, Stereo matching, Canny edge detection, SIFT algorithm, RANSAC algorithmAbstract
To address the problems of incomplete feature extraction and high mismatch rates in traditional stereo matching of ultra-thin strip materials for power battery top covers, a stereo matching method integrating edge enhancement and robust matching is proposed. First, the Canny edge detection algorithm is employed to accurately extract the edge contours of the power battery top cover, suppressing image noise while ensuring edge continuity and local feature integrity. Then, the SIFT algorithm is used to achieve cross-scale matching of feature points between the left and right images, enhancing robustness against deformation and rotation. Finally, the RANSAC algorithm is applied to eliminate mismatched points and construct a high-precision stereo matching model. Experimental results show that compared with the traditional NCC algorithm, the proposed stereo matching method improves the matching rate by 2.7% and reduces the matching time by 12.4 seconds; compared with the SGM algorithm, it increases the matching rate by 4.68% and shortens the processing time by 9 seconds, significantly optimizing the stereo matching performance for ultra-thin strip materials.
Downloads
References
[1] Pi Y. Research Progress on Top Cover Technology for Lithium-Ion Batteries[J]. Jiangxi Chemical Industry, 2019, (04): 121-124.
[2] Wang Z, Jing J, Wang S. Vehicle external dimension measurement method based on binocular vision[J]. Electronic Measurement Technology, 2023, 46(12): 150-156.
[3] Zhang Y, Wang Z, Fu X. External Dimension Measurement Method of Large Ring Forgings Based on Point Cloud Simplification[J]. Acta Metrologica Sinica, 2023, 44(07): 1027-1032.
[4] Cheng M, Wang J. Research on on-line measurement method of spur gear using machine vision[J]. Journal of Machine Design, 2020, 37(03): 19-22. DOI: 10.13841/j.cnki.jxsj.2020.03.003.
[5] Wang Y, Zhang Y. Length Dimension Measurement of Hot Large Forgings Based on Green Laser Image Recognition[J]. Acta Metrologica Sinica, 2018, 39(03): 316-320.
[6] Wang W, Zhang K, Liu Y, et al. Research on flatness detection method for new energy power battery cover[J]. Chinese Journal of Scientific Instrument, 2020, 41(02): 218-225.
[7] Tokihiko A, Yuji Y, Hironobu F. Stereo Vision by Combination of Machine-Learning Techniques for Pedestrian Detection at Intersections Utilizing Surround-View Cameras[J]. Journal of Robotics and Mechatronics, 2020, 32(3): 494-502. DOI: https://doi.org/10.20965/jrm.2020.p0494
[8] Comlekciler I T, Gunes S, Irgin C. Artificial 3-D contactless measurement in orthognathic surgery with binocular stereo vision[J]. Applied Soft Computing, 2016: 505-514. DOI: https://doi.org/10.1016/j.asoc.2016.01.026
[9] Zhang C, Hu P, Zhu X, et al. Intelligent Online Detection of Laser Welding Defects Based on High-Density Point Clouds (Invited)[J]. Chinese Journal of Lasers, 2024, 51(04): 85-96. DOI: https://doi.org/10.3788/CJL231293
[10] Wang H, Kan B, Rui M, et al. Research on Plate Plane Measurement Based on Binocular Vision[J]. Computer Measurement & Control, 2023, 31(09): 42-47.
[11] Li B, Wang H, Han Y, et al. Research on detection and positioning method of trailer hook based on binocular vision[J]. Electronic Measurement Technology, 2024, 47(03): 1-8.
[12] Guo Y, Zhao X, Liang R, et al. Multi-type obstacle perception for autonomous vehicles based on binocular vision[J]. Journal of Harbin Engineering University, 2023, 44(08): 1406-1411.
[13] Zhang Z. A Flexible New Technique for Camera Calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334. DOI: https://doi.org/10.1109/34.888718
[14] Bao Q, Jing H, Zhang J, et al. An image edge detection method based on improved Canny operator[J]. Modern Electronic Technology, 2024, 47(23): 36-42. DOI: 10.16652/j.issn.1004-373x.2024.23.006.
[15] Huang Y, Hu X, Peng X, et al. Image Edge Detection Algorithm Based on Improved Canny Operator[J/OL]. Mechanical Science and Technology for Aerospace Engineering, 1-11 [2025-04-11].
[16] Zhou Y. SAR image registration based on phase congruency and stable nonlinear SIFT algorithm[J]. Modern Radar, 2022, 44(06): 49-54.
[17] Chen J, Gong Z, Gao X. Design and Simulation of Feature Extraction Method for Weakly Enhanced Image[J]. Computer Simulation, 2022, 39(04): 197-200+370.
[18] Su W, Jiang J, Lyu X. An Improved Method for Edge Line Detection Based on Canny and RANSAC Algorithms[J]. Journal of Fujian University of Technology, 2025, 23(01): 64-70.
[19] Ye J, Lin X, Wu H. Improved RANSAC Point Cloud Plane Fitting Algorithm Based on DBSCAN[J]. Journal of Hunan University (Natural Sciences), 2025, 52(02): 76-87.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Academic Journal of Applied Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
