改进的有雾图像中被遮挡车辆及行人识别算法

于天河,王文龙,刘镛,杨壮壮,侯善冲

Improved algorithm for identifying occluded vehicles and pedestrians in foggy images

Tianhe YU,Wenlong WANG,Yong LIU,Zhuangzhuang YANG,Shanchong HOU

表 3 基于CityPersons数据集的各目标检测模型在遮挡场景下的性能对比

Tab.3 Performance comparison of various object detection models based on CityPersons dataset under occlusion scenarios

模型 FPS/ (帧·s−1) F1 Pr Re mAP So Po Se SSD 15.38 0.8135 0.8305 0.7563 0.7757 0.5325 0.3883 Faster R-CNN 8.13 0.8413 0.8728 0.7823 0.8049 0.6926 0.5264 YOLOv10 55.56 0.8768 0.9102 0.8226 0.8336 0.7554 0.5727 MsF-SSD-Net 74.07 0.8545 0.8901 0.8189 0.9241 0.8136 0.5812 DCT- YOLO[26] — 0.8400 0.9160 0.7750 0.8870 — — improved YOLOv7[27] 252.00 0.7700 0.7820 0.7690 0.8220 — —