ABSTRACT Illegal parking in fire lanes threatens safety, while manual patrols are inefficient and costly. Occlusion, motion blur and viewpoint changes further impede accurate detection. To address these challenges, this study proposes an improved model based on YOLOv11‐Seg, named YOLO‐FC, specifically designed for fire lane occupancy detection. The proposed model integrates a spatial‐channel synergistic attention (SCSA) mechanism, a universal inverted bottleneck (UIB) module and a content‐guided attention fusion (CGAFusion) module to enhance the model's robustness against complex environmental interferences. On this basis, an intersection‐over‐union (IoU)‐based method is further proposed for emergency lane occupancy identification. Experimental results show that the proposed model achieves a mean average precision (mAP) of 98.6% and 89.7% for fire lane and car detection, respectively, and mAP scores of 98.4% and 89.6% for segmentation tasks. Both ablation studies and comparative experiments demonstrate that the three proposed improvements significantly enhance the accuracy of detection and segmentation for fire lanes and cars. Moreover, the fire lane occupancy recognition results indicate that the YOLO‐FC model achieves an identification accuracy of 95.85%. This research provides an efficient and feasible technical solution for intelligent and real‐time supervision of fire lanes in urban community environments.
Huang et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: