Multiscale Efficient Channel Attention for Fusion Lane Line Segmentation

Table 2

Comparison of single-modal and multimodal fusion in KITTI and A2D2. “REC” denotes “Recall” and “PRE” denotes “Precision,” and we use the same abbreviation in the following sections.

Dataset	Mode	REC	PRE	F1	F2	Acc
	LiDAR	85.43	25.82	37.84	54.41	95.19
KITTI	Camera	82.30	45.53	55.59	67.06	97.84
	Fusion	93.34	45.89	57.89	71.22	98.16
	LiDAR	84.44	22.60	35.51	48.54	94.45
A2D2	Camera	87.47	24.36	36.27	54.65	95.22
	Fusion	87.06	32.09	45.06	61.57	98.87