Information
Contact Name: PyongKun Kim
Email: iros@etri.re.kr
Organization: Electronics and Telecommunications Research Institute (ETRI)
Method's Name: (C) bagging + CNN
Reference: PyongKun Kim, et al., " Vehicle Type Classification Using Bagging and Convolutional Neural Network on Multi View Surveillance Image", Traffic Surveillance Workshop and Challenge, CVPR 2017.
Project Website:
Evaluation Metrics

Precision of each category :

$$ Pre_i = \frac{TP_i}{TP_i + FP_i}$$


Articulated Truck Bicycle Bus Car Motorcycle Non-motorized Vehicle Pedestrian Pickup Truck Single Unit Truck Work Van Background
0.9438 0.9156 0.9916 0.9834 0.9720 0.8540 0.9513 0.9375 0.8339 0.9112 0.9968

Recall of each category:

$$ Rec_i = \frac{TP_i}{TP_i + FN_i}$$


Articulated Truck Bicycle Bus Car Motorcycle Non-motorized Vehicle Pedestrian Pickup Truck Single Unit Truck Work Van Background
0.9412 0.8739 0.9593 0.9866 0.9131 0.7078 0.9610 0.9510 0.8273 0.8258 0.9980

Accuracy: 0.9786

$$ Acc = \frac{TP}{Number of Testing Images}$$


Mean Recall: 0.9041

$$ {mRec} = {\rm mean}({Rec_i})$$


Mean Precision: 0.9355

$$ {mPre} = {\rm mean}({Pre_i})$$


Cohen Kappa Score: 0.9666

Confusion Matrix (%):

Predicted
Articulated Truck Bicycle Bus Car Motorcycle Non-motorized Vehicle Pedestrian Pickup Truck Single Unit Truck Work Van Background
True Articulated Truck 94.12 0.04 0.19 0.46 0.00 0.85 0.00 0.15 3.79 0.00 0.39
Bicycle 0.00 87.39 0.18 0.35 1.40 0.00 9.63 0.00 0.00 0.00 1.05
Bus 0.47 0.00 95.93 0.66 0.00 0.23 0.00 0.00 0.81 1.55 0.35
Car 0.01 0.00 0.01 98.66 0.00 0.00 0.01 1.04 0.01 0.18 0.08
Motorcycle 0.00 2.83 0.00 4.44 91.31 0.00 1.21 0.20 0.00 0.00 0.00
Non-motorized Vehicle 5.02 0.23 0.68 7.76 0.00 70.78 0.23 1.37 7.99 0.23 5.71
Pedestrian 0.00 1.85 0.00 0.58 0.32 0.06 96.10 0.00 0.06 0.00 1.02
Pickup Truck 0.03 0.00 0.01 4.45 0.00 0.04 0.00 95.10 0.23 0.10 0.04
Single Unit Truck 7.58 0.00 0.16 1.64 0.00 0.39 0.00 5.70 82.73 1.64 0.16
Work Van 0.00 0.00 0.17 14.29 0.00 0.21 0.00 1.78 0.95 82.58 0.04
Background 0.01 0.00 0.00 0.14 0.00 0.02 0.03 0.00 0.00 0.00 99.80