Information
Contact Name: Rajkumar Theagarajan
Email: rthea001@ucr.edu
Organization: University of California, Riverside
Method's Name: (C) Ensemble of Deep Networks: Network A,B and C
Reference: Rajkumar Theagarajan, et al., "EDeN: Ensemble of Deep Networks for Vehicle Classification", 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
0.9368 0.9361 0.9910 0.9889 0.9587 0.8661 0.9650 0.8997 0.8868 0.9585 0.9951

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
0.9451 0.8984 0.9794 0.9790 0.9374 0.7237 0.9348 0.9624 0.8445 0.9059 0.9980

Accuracy: 0.9780

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


Mean Recall: 0.9190

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


Mean Precision: 0.9439

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


Cohen Kappa Score: 0.9658

Confusion Matrix (%):

Predicted
Articulated Truck Bicycle Bus Car Motorcycle Non-motorized Vehicle Pedestrian Pickup Truck Single Unit Truck Work Van Background
True Articulated Truck 94.51 0.00 0.15 0.19 0.00 1.04 0.00 0.08 3.52 0.15 0.35
Bicycle 0.00 89.84 0.18 0.18 1.40 0.00 7.18 0.00 0.00 0.00 1.23
Bus 0.31 0.00 97.94 0.89 0.00 0.08 0.00 0.31 0.08 0.16 0.23
Car 0.01 0.00 0.01 97.90 0.00 0.00 0.00 1.93 0.00 0.09 0.06
Motorcycle 0.00 1.41 0.00 1.82 93.74 0.00 0.40 0.00 0.00 0.00 2.63
Non-motorized Vehicle 6.39 0.23 0.46 1.37 0.23 72.37 0.46 3.88 5.25 1.83 7.53
Pedestrian 0.00 1.73 0.00 0.13 0.45 0.06 93.48 0.06 0.06 0.00 4.03
Pickup Truck 0.02 0.00 0.01 3.56 0.00 0.02 0.00 96.24 0.09 0.04 0.02
Single Unit Truck 8.83 0.00 0.16 0.70 0.00 0.23 0.00 3.75 84.45 1.17 0.70
Work Van 0.08 0.00 0.21 6.77 0.00 0.12 0.00 1.24 0.33 90.59 0.66
Background 0.01 0.00 0.01 0.12 0.00 0.02 0.02 0.01 0.00 0.01 99.80