Train rolling stock video segmentation and classification for bogie part inspection automation: a deep learning approach

Journal of Engineering and Applied Science

Table 4 Evaluation of the proposed method using mNI

Baseline methods/datasets	SSD	R-CNN	Fast R-CNN	Faster R-CNN	Yolo v1	Yolo v2	Yolo v2 with skip	Yolo v2 bifold skip	B-MHAC
D-1	0.5563	0.5125	0.4569	0.4236	0.3896	0.3456	0.3179	0.1856	0.1243
D-2	0.5936	0.5469	0.4856	0.4598	0.4189	0.3823	0.3495	0.2658	0.1975
D-3	0.6044	0.6093	0.5908	0.5815	0.5517	0.5355	0.5231	0.3856	0.2235
D-4	0.5459	0.4781	0.4282	0.3874	0.3603	0.3089	0.2863	0.1925	0.1385
D-5	0.5017	0.5037	0.4895	0.4312	0.3931	0.3622	0.3147	0.2489	0.1596
D-6	0.6271	0.6149	0.6121	0.6088	0.5924	0.5894	0.5515	0.4023	0.2578
Average mNI	0.5715	0.5442	0.5105	0.482	0.451	0.42	0.39	0.2801	0.1835