• Acta Optica Sinica
  • Vol. 39, Issue 5, 0510002 (2019)
Pengtu Zhao1、2、* and Feipeng Da1、2、*
Author Affiliations
  • 1 Key Laboratory of Measurement and Control of Complex System of Engineering, Ministry of Education, Southeast University, Nanjing, Jiangsu 210096, China
  • 2 School of Automation, Southeast University, Nanjing, Jiangsu 210096, China
  • show less
    DOI: 10.3788/AOS201939.0510002 Cite this Article Set citation alerts
    Pengtu Zhao, Feipeng Da. Image Matching with Large Viewing Angle Based on Local Features[J]. Acta Optica Sinica, 2019, 39(5): 0510002 Copy Citation Text show less
    Flow chart of feature extraction
    Fig. 1. Flow chart of feature extraction
    Schematic of spatial transformation parameters
    Fig. 2. Schematic of spatial transformation parameters
    View transformation and mask maps. (a) Transformation map; (b) mask map
    Fig. 3. View transformation and mask maps. (a) Transformation map; (b) mask map
    Multi-view descriptor
    Fig. 4. Multi-view descriptor
    Matching results of different algorithms. (a)(c) ASIFT algorithm, image pair of Freiburg_center1-4 and Graffiti1-4; (b)(d) proposed algorithm, image pair of Freiburg_center1-4 and Graffiti1-4
    Fig. 5. Matching results of different algorithms. (a)(c) ASIFT algorithm, image pair of Freiburg_center1-4 and Graffiti1-4; (b)(d) proposed algorithm, image pair of Freiburg_center1-4 and Graffiti1-4
    Recall-1-Precision matching results of different image pairs by different algorithms under image transformation. (a) Boat1-2; (b) Bark1-2; (c) Graffiti1-2; (d) Graffiti1-4; (e) Wall1-2; (f) Wall1-4
    Fig. 6. Recall-1-Precision matching results of different image pairs by different algorithms under image transformation. (a) Boat1-2; (b) Bark1-2; (c) Graffiti1-2; (d) Graffiti1-4; (e) Wall1-2; (f) Wall1-4
    Matching results of different algorithms on partial images
    Fig. 7. Matching results of different algorithms on partial images
    Matching result of proposed algorithm on Graffiti1-6
    Fig. 8. Matching result of proposed algorithm on Graffiti1-6
    Matching algorithmDetection complexityFeature point detection time /sFeature point matching time /s
    SIFT11.6140.685
    KAZE11.4240.942
    ORB11.6210.846
    ASIFT264.2426.621
    Proposed263.4282.226
    Table 1. Time schedule for feature point detection