Table 1.
Summary of the classifier performances over VC.
Fig 1.
An outline of the envisaged framework for vehicle classification.
Fig 2.
Sample images from various vehicle datasets.
(A) Stanford car dataset (B) Vehicle–Rear dataset (C) MVVTR dataset (D) Indian Vehicle dataset (E) TRANCOS dataset (F) Thai Vehicle Classification Dataset (G) 2023 Car Model dataset (H) UFPR-ALPR dataset (I) VehicleX dataset (J) CompCars dataset.
Fig 3.
The intensity variation map.
Fig 4.
Prediction of each segmentation mask over region of interest.
Fig 5.
The segmented mask images, the pixel values are scaled up to model based on array processing.
Fig 6.
Detection of vehicle with bounding box and class label output.
Fig 7.
Result of VC under different lighting conditions.
Table 2.
Shows the comparison of various vehicle dataset with different classifier model.
Fig 8.
Confusion matrices from UFPR-ALPR dataset showing the relative performance.
(A) CB (B) RF (C) KNN (D) SVM.
Fig 9.
Accuracy comparison of proposed model over different dataset for VC.
Fig 10.
Sensitivity of proposed model over different dataset for VC.
Fig 11.
Specificity of proposed model over different dataset for VC.
Fig 12.
ROC curves of the test results of the different networks.
Fig 13.
Precision comparison of various model over UFPR-ALPR dataset.
Fig 14.
The recall graph of the complex dataset of VC using VGG16 with different classifier.
Fig 15.
The f1-score graph is highlighted on various dataset for VC using ensemble classifier.