Table 3 Performance Comparison of Object Detection Methods (China Dataset).

From: A Large-Scale Image Repository for Automated Pavement Distress Analysis and Degradation Trend Prediction

Method

P

R

mAP@50

GFLOPS

Faster-RCNN

0.372

0.501

0.472

248.5

YOLOv5

0.502

0.491

0.502

134.7

YOLOv8

0.529

0.505

0.543

165.2

YOLOX

0.546

0.502

0.520

154.3

YOLOv11

0.536

0.585

0.569

87.2

RT-DETRv2

0.668

0.498

0.583

108.2

Back to article page