Improving Faster R-CNN Framework for Fast Vehicle Detection

Table 6

Comparison of the results of the proposed method and other methods on the LSVH test set.

Method	Average precision (%)	Processing time (s)
Faster R-CNN [2]	40.22	0.48
MS-CNN [4]	72.66	0.35
YOLO [20]	23.78	0.03
YOLOv2 [19]	54.00	0.03
Proposed approach	64.72	0.10