Machine Learning-Enhanced ORB Matching Using EfficientPS for Error Reduction

被引：0
|
作者：
Li, Zhanrong [1 ,2 ,3 ,4 ]
Su, Haosheng [1 ]
Jiang, Chao [1 ]
Han, Jiajie [1 ]
机构：
[1] School of Computer and Electronic Information, Guangxi University, Guangxi, Nanning,530004, China
[2] Nanning Huishi Technology Co. Ltd., Guangxi, Nanning,530000, China
[3] Guangxi Intelligent Digital Services Research Center of Engineering Technology, Guangxi, Nanning,530004, China
[4] Key Laboratory of Parallel Distributed and Intelligent Computing (Guangxi University), Education Department of Guangxi Zhuang Autonomous Region, Guangxi, Nanning,530004, China
来源：
Applied Mathematics and Nonlinear Sciences | 2024年 / 9卷 / 01期
关键词：
The study comes up with a new way to improve the accuracy of image matching in binocular vision systems; especially those that are mounted on vehicles. It combines machine learning with the ORB (Oriented FAST and Rotated BRIEF) image-matching algorithms. Standard ORB matching frequently encounters mismatches in complex and repetitive environments. To minimize false positives in matches; our strategy utilizes the EfficientPS (Efficient Panoptic Segmentations) algorithm; a panoramic segmentation technique that uses machine learning in conjunction with ORB. The procedure begins with the EfficientPS approach; which delivers fine-grained and efficient segmentation of images; assigning semantic category labels and unique identifiers to each pixel. The ORB feature point matching process is refined using semantic data to filter out mismatches between foreground objects and the background effectively. This machine-learning-augmented method significantly decreases the frequency of erroneous matches in intricate settings. Empirical findings from the KITTI dataset demonstrate that in non-targeted environments; the accuracy of our proposed method (0.978) is marginally less than that of LoFTR (0.983). Still; it surpasses other methods when utilizing 50 ORB parameters. In more intricate situations; such as multi-target scenarios with an increased number of ORB parameters (200); our method maintains a high level of accuracy (0.883); outperforming the conventional ORB (0.732) and rivaling the performance of DL-BDLMR (0.790) and ORB-MFD-FPMC (0.835). Our method's processing time is competitive and slightly higher than the standard ORB; but it improves accuracy. In scenarios without targets and with single targets; our method's processing time (0.195 seconds and 0.211 seconds; respectively) is greater than that of ORB and ORB-MFD-FPMC. Yet; it is significantly lower than that of LoFTR. In multi-target scenarios; our method's processing time (0.226 seconds) is considerably better than LoFTR's (0.445 seconds); effectively balancing processing speed and accuracy. We highlight the efficacy of incorporating machine learning to enhance the robustness of image-matching algorithms in dynamic and complex environments. © 2024 Zhanrong Li et al; published by Sciendo;
D O I：
10.2478/amns-2024-2721
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [41] Machine learning-enhanced detection of minor radiation-induced defects in semiconductor materials using Raman spectroscopy
    Chia, Jia Yi
    Thamrongsiripak, Nuatawan
    Thongphanit, Sornwit
    Nuntawong, Noppadon
    JOURNAL OF APPLIED PHYSICS, 2024, 135 (02)
  • [42] Prediction of Electron Beam Welding Penetration Depth Using Machine Learning-Enhanced Computational Fluid Dynamics Modelling
    Yin, Yi
    Tian, Yingtao
    Ding, Jialuo
    Mitchell, Tim
    Qin, Jian
    SENSORS, 2023, 23 (21)
  • [43] Real-time in-situ coatings corrosion monitoring using machine learning-enhanced triboelectric nanogenerator
    Wang, Di
    Li, Yunwei
    Claesson, Per
    Zhang, Fan
    Pan, Jinshan
    Shi, Yijun
    Sensors and Actuators A: Physical, 2024, 379
  • [44] Smart Cushions with Machine Learning-Enhanced Force Sensors for Pressure Injury Risk Assessment
    Xiang, Xinhao
    Zhang, Ke
    Qin, Yi
    Ma, Xingchen
    Dai, Ying
    Zhang, Xiaoqing
    Niu, Wenxin
    He, Pengfei
    ACS APPLIED MATERIALS & INTERFACES, 2024, 16 (29) : 38466 - 38477
  • [45] Machine learning-enhanced soil classification by integrating borehole and CPTU data with noise filtering
    Xiao, Te
    Zou, Hai-Feng
    Yin, Ke-Sheng
    Du, Yu
    Zhang, Li-Min
    BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2021, 80 (12) : 9157 - 9171
  • [46] Machine learning-enhanced optimal catalyst selection for water-gas shift reaction
    Golder, Rahul
    Pal, Shraman
    Kumar, C. Sathish
    Ray, Koustuv
    DIGITAL CHEMICAL ENGINEERING, 2024, 12
  • [47] Machine learning-enhanced soil classification by integrating borehole and CPTU data with noise filtering
    Te Xiao
    Hai-Feng Zou
    Ke-Sheng Yin
    Yu Du
    Li-Min Zhang
    Bulletin of Engineering Geology and the Environment, 2021, 80 : 9157 - 9171
  • [48] Machine Learning-Enhanced Survival Analysis: Identifying Significant Predictors of Mortality in Heart Failure
    Lee, Heejeong Jasmine
    Yoo, Sang-Sun
    Lee, Kang-Yoon
    KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2024, 18 (09): : 2495 - 2511
  • [49] Machine learning-enhanced surface plasmon resonance based photonic crystal fiber sensor
    Ehyaee, Arefe
    Rahmati, Alireza
    Bosaghzadeh, Alireza
    Olyaee, Saeed
    OPTICS EXPRESS, 2024, 32 (08): : 13369 - 13383
  • [50] Reduction in On-Product Overlay Random Error Using Machine Learning Algorithm
    Song, Gilwoo
    Kim, Sungchai
    Park, Sungwon
    Jo, Taeyong
    Kum, Euiseok
    Hwang, Jonghyun
    Lee, Seonho
    METROLOGY, INSPECTION, AND PROCESS CONTROL XXXVI, 2022, 12053
12345