Abnormal Driving Behavior Detection Based on Covariance Manifold and LogitBoost

Table 1. One-against-one binary classifiers
View table
Table 1. One-against-one binary classifiers
Item 2 3 n-1 n
1 F(1,2) F(1,3) F(1,n-1) F(1,n)
2 F(2,3) F(2,n-1) F(2,n)
n-1 F(n-1,n)
n

Table 2. One-against-all binary classifiers
View table
Table 2. One-against-all binary classifiers
Item 1 2 … n-1 n
Classifier F(1) F(2) … F(n-1) F(n)

Table 3. Performance comparison among traditional LogitBoost classifier and LogitBoost classifier based on binary classifiers
View table
Table 3. Performance comparison among traditional LogitBoost classifier and LogitBoost classifier based on binary classifiers
Method Accuracy /% Time comsuming /h
LogitBoost 0.728 6.5
One-against-one binary 0.811 23.2
One-against-all binary 0.785 12.3

Table 4. Recognition accuracy of different methods
View table
Table 4. Recognition accuracy of different methods
Method Accuracy /%
SVC+Bbox+PCA 0.407
Porposed method 0.811

Table 5. Recognition accuracy of different methods for the same targets
View table
Table 5. Recognition accuracy of different methods for the same targets
Method Accuracy /%
SVC+Bbox+PCA 0.750
Proposed method 0.983

Tools

Get Citation

Copy Citation Text

Cijun Li, Yunpeng Liu. Abnormal Driving Behavior Detection Based on Covariance Manifold and LogitBoost[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111503

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites