Home
Dataset
Results
Classification
Localization
Upload
TSWC2017
Information
Contact Name: Jong Taek Lee
Email: jtlee@utexas.edu
Organization: Electronics and Telecommunications Research Institute (ETRI)
Method's Name: (C) Ensemble of Local Expert and Global Networks
Reference: Jong Taek Lee, et al., "Deep Learning-based Vehicle Classification using an Ensemble of Local Expert and Global Networks", 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
0.9457
0.9142
0.9892
0.9822
0.9212
0.8224
0.9666
0.9461
0.8238
0.9183
0.9981
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
0.9358
0.8774
0.9620
0.9889
0.9212
0.6872
0.9425
0.9507
0.8289
0.8353
0.9966
Accuracy: 0.9792
$$ Acc = \frac{TP}{Number of Testing Images}$$
Mean Recall: 0.9024
$$ {mRec} = {\rm mean}({Rec_i})$$
Mean Precision: 0.9298
$$ {mPre} = {\rm mean}({Pre_i})$$
Cohen Kappa Score: 0.9675
Confusion Matrix (%):
Predicted
Articulated Truck
Bicycle
Bus
Car
Motorcycle
Non-motorized Vehicle
Pedestrian
Pickup Truck
Single Unit Truck
Work Van
Background
True
Articulated Truck
93.58
0.00
0.19
0.50
0.00
0.62
0.00
0.15
4.72
0.08
0.15
Bicycle
0.00
87.74
0.18
0.70
4.20
0.18
6.65
0.00
0.00
0.00
0.35
Bus
0.35
0.00
96.20
0.43
0.00
0.58
0.00
0.12
0.58
1.59
0.16
Car
0.01
0.00
0.00
98.89
0.00
0.01
0.00
0.88
0.01
0.15
0.05
Motorcycle
0.00
0.61
0.00
5.66
92.12
0.40
0.40
0.81
0.00
0.00
0.00
Non-motorized Vehicle
4.79
0.23
0.23
9.13
0.46
68.72
0.46
2.05
10.27
1.60
2.05
Pedestrian
0.00
2.68
0.00
1.02
0.83
0.13
94.25
0.00
0.00
0.00
1.09
Pickup Truck
0.00
0.00
0.03
4.56
0.00
0.06
0.00
95.07
0.18
0.08
0.02
Single Unit Truck
7.73
0.00
0.23
2.11
0.00
0.63
0.00
4.53
82.89
1.56
0.31
Work Van
0.00
0.00
0.21
14.00
0.00
0.04
0.00
1.57
0.66
83.53
0.00
Background
0.01
0.00
0.01
0.28
0.00
0.02
0.02
0.00
0.00
0.00
99.66