• Laser & Optoelectronics Progress
  • Vol. 61, Issue 18, 1837012 (2024)
Zhoumeng He1,2, Guoliang Chen1,2,*, Mingcong Shu1,2, Kaiyu Di1,2, and Hu Liu1,2
Author Affiliations
  • 1School of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, Jiangsu, China
  • 2Key Laboratory of Land Environment and Disaster Monitoring of Ministry of Natural Resources, China University of Mining and Technology, Xuzhou 221116, Jiangsu, China
  • show less
    DOI: 10.3788/LOP232682 Cite this Article Set citation alerts
    Zhoumeng He, Guoliang Chen, Mingcong Shu, Kaiyu Di, Hu Liu. Indoor Structure Method Based on Motion Assisted by Geomagnetic Features[J]. Laser & Optoelectronics Progress, 2024, 61(18): 1837012 Copy Citation Text show less
    Workflow of indoor structure from motion assisted by geomagnetic features
    Fig. 1. Workflow of indoor structure from motion assisted by geomagnetic features
    Process of matching points between local models
    Fig. 2. Process of matching points between local models
    Schematic diagrams of experimental scenes and location relationship of data acquisition devices. (a) Experimental scene on the same floor; (b) experimental scene on different floors; (c) device location relationship
    Fig. 3. Schematic diagrams of experimental scenes and location relationship of data acquisition devices. (a) Experimental scene on the same floor; (b) experimental scene on different floors; (c) device location relationship
    Data preprocessing. (a) Smoothing of geomagnetic sequences; (b) original image (left) and smooth image (right)
    Fig. 4. Data preprocessing. (a) Smoothing of geomagnetic sequences; (b) original image (left) and smooth image (right)
    Comparison of reconstruction effect of proposed method and traditional method. (a) Proposed method; (b) traditional method
    Fig. 5. Comparison of reconstruction effect of proposed method and traditional method. (a) Proposed method; (b) traditional method
    DatasetBefore processingAfter processing
    Number of geomagnetismsNumber of imagesNumber of geomagnetismsNumber of images
    Same floor3300019800991991
    Different floors274001644016621662
    Table 1. Collected data and preliminary processed relevant information
    AlgorithmK-MeansBi-KMeansDBSCAN
    Precision56.3689.0970.91
    Table 2. Accuracy table of three algorithms for clustering geomagnetic data
    DatasetProposed methodDatasetTraditional method
    aa
    ba+b
    ca+b+c
    da+b+c+d
    ea+b+c+d+e
    Table 3. The local reconstruction of proposed method does not run RGPA and the reconstruction of different data subsets by traditional method
    Reconstructed viewProposed methodTraditional method
    Front view
    Left view
    Top view
    Complete model
    Table 4. Comparison reconstructions of proposed method and traditional method
    DatasetNumber of imagesTraditional methodProposed method
    Time /sCamera registration rate /%Sparse point clouds /103Point cloud generation rate /sSingle-image time-consuming /sTime /sCamera registration rate /%Sparse point clouds /103Point cloud generation rate /s-1Single-image time-consuming /s
    Same floor991190684148.001781.92975100158.8761630.98
    Different floors1662398681261.622662.40296085274.541931.78
    Table 5. Comparison performance of traditional method and proposed method
    Zhoumeng He, Guoliang Chen, Mingcong Shu, Kaiyu Di, Hu Liu. Indoor Structure Method Based on Motion Assisted by Geomagnetic Features[J]. Laser & Optoelectronics Progress, 2024, 61(18): 1837012
    Download Citation