Skip to main content

Table 6 B-MHAC vs similar models on mAP

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

Baseline methods/datasets

Block matching [1]

Active contours [2]

Shape prior active contours [3]

Shape invariance active contours [4]

Region-based active contours [5]

Unified active contour model [6]

Yolo v2 bifold skip

B-MHAC

B-1

0.8258

0.8525

0.8965

0.9145

0.9369

0.9522

0.9214

0.9627

B-2

0.7963

0.8256

0.8698

0.8963

0.9245

0.9289

0.8547

0.8963

B-3

0.7058

0.7256

0.7485

0.7458

0.7698

0.7852

0.7523

0.8425

B-4

0.8025

0.8266

0.8785

0.8989

0.9299

0.9369

0.9078

0.9457

B-5

0.7989

0.8158

0.8698

0.8858

0.9158

0.9195

0.8752

0.9025

B-6

0.6854

0.7125

0.7258

0.7458

0.7698

0.7896

0.7321

0.8147