• Laser & Optoelectronics Progress
  • Vol. 58, Issue 4, 0410023 (2021)
Weigang Wang, Bingwei Wang*, and Yunwei Zhang
Author Affiliations
  • School of Electronic and Optical Engineering, School of Microelectronics, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210023, China
  • show less
    DOI: 10.3788/LOP202158.0410023 Cite this Article Set citation alerts
    Weigang Wang, Bingwei Wang, Yunwei Zhang. TDFF: Strong Robust Algorithm for Smoke Image Detection[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410023 Copy Citation Text show less
    Different types of features in heterogeneous modes. (a1)--(a4) Linear features; (b1)--(b4) T-type features; (c1)(c2) cross and diagonal features
    Fig. 1. Different types of features in heterogeneous modes. (a1)--(a4) Linear features; (b1)--(b4) T-type features; (c1)(c2) cross and diagonal features
    Processing flow of TDFF algorithm
    Fig. 2. Processing flow of TDFF algorithm
    Extraction results of different features. (a1)(a2) Traditional LBP features; (b1)(b2) T-MFLBP features
    Fig. 3. Extraction results of different features. (a1)(a2) Traditional LBP features; (b1)(b2) T-MFLBP features
    Comparison of detection rates of different methods in different datasets
    Fig. 4. Comparison of detection rates of different methods in different datasets
    Comparison of false alarm rates of different methods in different datasets
    Fig. 5. Comparison of false alarm rates of different methods in different datasets
    Detection rate comparison curves of different methods in different dimensions
    Fig. 6. Detection rate comparison curves of different methods in different dimensions
    Comparison curves of false alarm rates in different dimensions by different methods
    Fig. 7. Comparison curves of false alarm rates in different dimensions by different methods
    Comparison curves of detection rates of different feature fusion methods under different number of iterations
    Fig. 8. Comparison curves of detection rates of different feature fusion methods under different number of iterations
    Comparison curves of false alarm rates of different feature fusion methods under different number of iterations
    Fig. 9. Comparison curves of false alarm rates of different feature fusion methods under different number of iterations
    DatasetLBP+GaborT-MFLBP+GaborTDFF
    Detection rateFalse alarm rateDetection rateFalse alarm rateDetection rateFalse alarm rate
    194109461004
    297139611998
    39779941002
    49313929996
    Table 1. Performance comparison of different feature fusion methods unit: %
    Weigang Wang, Bingwei Wang, Yunwei Zhang. TDFF: Strong Robust Algorithm for Smoke Image Detection[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410023
    Download Citation