A selective feature scanning and context-aware decoupling framework for construction scene object detection

Construction-scene object detection is complicated by background clutter, occlusion, large scale variation, and visually similar categories. We developed SFMDet, a YOLOv12-based detector that combines Selective Feature Scanning (SFS), Multi-level Cross-Attention (MCAM), Directional Partial Convolution (DPConv), and Context-Aware Decoupling (CADM). SFS models long-range spatial dependencies, whereas MCAM exchanges information across feature levels after spatial and channel alignment. DPConv limits the computational cost of neck fusion, and CADM supplies task-specific features for classification and localization. The Hybrid Adaptive Loss uses Varifocal Loss, WIoU-v1 with distribution focal loss, feature alignment, and epoch-dependent objective weights. On a construction-scene dataset containing 5,000 images, 49 categories, and 21,988 instances, SFMDet achieved 72.6% [email protected], 4.3 points above YOLOv12s. Network-only TensorRT FP16 inference reached 287 FPS on an RTX 4090 at $$640\times640$$ resolution and batch size 1. Evaluation on three public UAV and remote-sensing datasets showed gains over the same baselines. Code and dataset materials are available at https://github.com/XiaoxiaLuo/SFMDet .