• Laser & Optoelectronics Progress
  • Vol. 55, Issue 11, 111503 (2018)
Cijun Li1、2、3、4、5、* and Yunpeng Liu1、2、4、5
Author Affiliations
  • 1 Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China
  • 2 Institute for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China
  • 3 University of Chinese Academy of Sciences, Beijing 100049, China
  • 4 Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China
  • 5 Key Laboratory of Image Understanding and Computer Vision, Liaoning Province, Shenyang, Liaoning 110016, China
  • show less
    DOI: 10.3788/LOP55.111503 Cite this Article Set citation alerts
    Cijun Li, Yunpeng Liu. Abnormal Driving Behavior Detection Based on Covariance Manifold and LogitBoost[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111503 Copy Citation Text show less
    Region division sample
    Fig. 1. Region division sample
    Unified distribution mapping in tangent space
    Fig. 2. Unified distribution mapping in tangent space
    Effect of basic feature selection on recognition rate
    Fig. 3. Effect of basic feature selection on recognition rate
    Effect of region division on recognition rate
    Fig. 4. Effect of region division on recognition rate
    Effect of regression tree parameter minleaf on recognitino rate
    Fig. 5. Effect of regression tree parameter minleaf on recognitino rate
    Item23n-1n
    1F(1,2)F(1,3)F(1,n-1)F(1,n)
    2F(2,3)F(2,n-1)F(2,n)
    n-1F(n-1,n)
    n
    Table 1. One-against-one binary classifiers
    Item12n-1n
    ClassifierF(1)F(2)F(n-1)F(n)
    Table 2. One-against-all binary classifiers
    MethodAccuracy /%Time comsuming /h
    LogitBoost0.7286.5
    One-against-one binary0.81123.2
    One-against-all binary0.78512.3
    Table 3. Performance comparison among traditional LogitBoost classifier and LogitBoost classifier based on binary classifiers
    MethodAccuracy /%
    SVC+Bbox+PCA0.407
    Porposed method0.811
    Table 4. Recognition accuracy of different methods
    MethodAccuracy /%
    SVC+Bbox+PCA0.750
    Proposed method0.983
    Table 5. Recognition accuracy of different methods for the same targets
    Cijun Li, Yunpeng Liu. Abnormal Driving Behavior Detection Based on Covariance Manifold and LogitBoost[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111503
    Download Citation