• Acta Optica Sinica
  • Vol. 42, Issue 9, 0911002 (2022)
Jing Weng1, Pan Yuan1, Minghe Wang1, Li Li1、*, Weiqi Jin1、2, Wei Cao2, and Bingcai Sun3
Author Affiliations
  • 1MoE Key Lab of Photoelectronic Imaging Technology and System, Beijing Institute of Technology, Beijing 100081, China
  • 2Beijing Wisdom Sharing Technical Co., Ltd., Beijing 100125, China
  • 3CNPC Research Institute of Safety & Environment Technology, Beijing 102206, China;
  • show less
    DOI: 10.3788/AOS202242.0911002 Cite this Article Set citation alerts
    Jing Weng, Pan Yuan, Minghe Wang, Li Li, Weiqi Jin, Wei Cao, Bingcai Sun. Thermal Imaging Detection Method of Leak Gas Clouds Based on Support Vector Machine[J]. Acta Optica Sinica, 2022, 42(9): 0911002 Copy Citation Text show less
    Schematic diagram of SVM
    Fig. 1. Schematic diagram of SVM
    Wide band gas infrared imaging system
    Fig. 2. Wide band gas infrared imaging system
    Original images and difference images of different infrared video and their rendering pictures. (a)(e) ith frame; (b)(f) (i+5)th frame; (c)(g) difference images of ith frame and (i+5)th frame; (d)(h) color rendering of difference results on original image
    Fig. 3. Original images and difference images of different infrared video and their rendering pictures. (a)(e) ith frame; (b)(f) (i+5)th frame; (c)(g) difference images of ith frame and (i+5)th frame; (d)(h) color rendering of difference results on original image
    Samples of positive and negative datasets. (a)--(c) Positive sample images; (d)--(f) negative sample images, which are people, trees, and pumping units
    Fig. 4. Samples of positive and negative datasets. (a)--(c) Positive sample images; (d)--(f) negative sample images, which are people, trees, and pumping units
    Optimization results for parameters C and γ by grid search method
    Fig. 5. Optimization results for parameters C and γ by grid search method
    Detection results of test set. (a) Positive sample; (b) negative sample
    Fig. 6. Detection results of test set. (a) Positive sample; (b) negative sample
    ParameterAccuracy /%Errorrate /%Precision /%Recall /%
    Value92.507.5091.0093.81
    Table 1. Test results of SIFT-SVM algorithm
    ParameterAccuracy /%Errorrate /%Precision /%Recall /%
    Value82.5017.5086.0080.37
    Table 2. Test results of HOG-SVM algorithm
    AlgorithmSingle data size /kBIterationsTraining time /sNumber of support vectors
    SIFT-SVM2--61763.6165326
    HOG-SVM41--63824137.7023502
    Table 3. Performance comparison of two algorithms
    Jing Weng, Pan Yuan, Minghe Wang, Li Li, Weiqi Jin, Wei Cao, Bingcai Sun. Thermal Imaging Detection Method of Leak Gas Clouds Based on Support Vector Machine[J]. Acta Optica Sinica, 2022, 42(9): 0911002
    Download Citation