EURASIP Journal on Advances in Signal Processing

Table 5 Comparison with different methods on KITTI dataset

From: Multiclass objects detection algorithm using DarkNet-53 and DenseNet for intelligent vehicles

Method	Backbone	AP (%)					mAP
Method	Backbone	Car	Pedestrian	Cyclist	Van	Truck	(%)
Faster R-CNN	VGG-16	81.42	62.36	73.66	81.05	88.78	77.45
Faster R-CNN	ResNet-101	80.68	61.40	71.58	80.91	81.78	75.27
YOLOv3	DarkNet53	92.22	78.97	83.24	92.99	94.30	88.34
Ours	DarkNet53	92.74	81.96	89.83	94.50	96.61	91.13

Back to article page