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

Journal of Engineering and Applied Science

Table 2 Evaluation of B-MHAC against state-of-the-art methods on perfromance parameter mAP

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
B-1	0.6843	0.6952	0.6856	0.7125	0.7752	0.7856	0.8152	0.9214	0.9587
B-2	0.6239	0.6531	0.6598	0.6859	0.7431	0.7658	0.7895	0.8152	0.9025
B-3	0.6151	0.6194	0.6252	0.6657	0.6894	0.7252	0.7594	0.8047	0.8956
B-4	0.6547	0.6773	0.6654	0.6913	0.6973	0.7754	0.7973	0.8478	0.9385
B-5	0.5955	0.6115	0.6175	0.6323	0.6615	0.7025	0.7415	0.8523	0.9122
B-6	0.5759	0.5936	0.5948	0.6189	0.6436	0.6868	0.7236	0.7321	0.8473
Average mAP	0.6249	0.6416	0.6413	0.6677	0.7016	0.7402	0.7710	0.8289	0.9091