In response to the challenges of false positives and misses caused by dense occlusions and small targets in complex road environments, this paper proposes an enhanced YOLOv8-based network named YOLO-RC for advanced road traffic object detection. YOLO-RC utilizes MBConv modules to enhance feature extraction in the backbone network, improving the accurate localization capability for densely occluded targets. Additionally, a novel C3FB structure (Efficient Fusion of C3 modules and FocalNextBlock structure) is introduced to replace the C2f module in the neck network of YOLOv8, aiming to reduce the parameter count while enhancing model accuracy. Combining the weighted Bi-directional Feature Pyramid Network (BCFPN) for feature fusion incorporates deep, shallow, and original features, reinforces feature integration, minimizes information loss during convolution processes, and enhances target detection accuracy. Finally, introducing the CBAM module further enhances the algorithm’s ability to capture target features, directing more attention to relevant information within the images. Experimental results demonstrate that the proposed algorithm achieves a mAP50 of 91.1\(\%\) on the roadside target detection dataset DAIR-V2X-I, representing a 4.5\(\%\) improvement compared to the originalalgorithm, with a recall rate of 81.8\(\%\). The generalization experiments are conducted on the challenging dataset UA-DETRAC. The experimental results show that mAP50 reaches 94.8\(\%\), and MAP50-95 reaches 77.9\(\%\). The algorithm exhibits outstanding detection accuracy performance. Comparative analysis against some mainstream target detection algorithms also reveals the superiority of the proposed approach.

Aiming at the phenomena of missing detection and false detection caused by multiple instances of small and medium-sized targets, occlusion between targets and rotation deviation of target positions, an improved YOLO11(You Only Look Once 11) based small target detection algorithm for UAV images is proposed. Firstly, the C3DC module is proposed by DynamicConv and C3k2 to enhance the expression ability of different features. Secondly, C2PDA is introduced into the neck by combining Dynamic Position Bias (DPB) module to reduce the sensitivity of the model to the target position deviation. Finally, SCO module is proposed to improve the feature pyramid structure to improve the detection ability of small targets. Through the experimental verification on the VisDrone2019 dataset, the experimental results show that compared with the original YOLO11 model, the mAP50 of the improved model is increased by 3.2% to 42.2%, and the MAP50:95 is increased by 2.2% to 25.6%.It achieves 33.7% mAP50 on the UAVDT dataset, which is also better than other SOTA models.Compared with the existing YOLO model and its improved version, the proposed model maintains high detection accuracy in complex scenarios. The research results show that the algorithm has significantly improved the detection ability of UAV images in complex scenes, and its comprehensive performance comprehensively exceeds that of YOLO11 model.

This methodological diagnostic tests whether broad building descriptors support retrofit-class shortlists beyond popularity. We mapped 2623 New York City Local Law 87 audit rows to six classes with five decision states, trained on 2019–2022, validated on 2023, and tested on unseen 2024 property groups. Under natural recorded-label visibility, state-aware and equal-information global policies both achieved an observed-positive Recall@3 of 0.832. The state model returned the same Top-3 set for 99.7% of test rows; all evaluated natural-condition neural models missed every recorded insulation and window-upgrade positive. Light-emitting diode (LED) lighting and heating, ventilation, and air conditioning (HVAC) controls comprised 277 of 394 test positives, explaining why high recall did not demonstrate personalization. In a secondary synthetic 10% visibility stress test, excluding unlabelled entries from negative supervision improved recall over naive binary cross-entropy by 0.279; the natural state–naive difference was 0.002 (95% confidence interval (CI) [−0.007, 0.012]). Post hoc capacity, ontology, status-precedence, and stopping sensitivities did not establish reliable superiority over popularity. The benchmark diagnoses label misspecification and nearly constant shortlists.