Aug 2026· International Conference on Computer Vision and Pattern Analysis· Vol 14296, pp. 142960T - 142960T-7· 0 citations· 18 references
Engineering
TL;DR
A YOLO11n-based traffic light detection algorithm, named YOLO11n-PRE, which replaces the original C3k2 module in the backbone network with the C3k2-RCB module, which enhances deep feature extraction capability while maintaining lightweight via efficient residual connection and feature recalibration mechanism.
Abstract
To address the challenges of high detection difficulty caused by small target size and complex background environments of traffic lights in urban road scenarios, this paper proposes a YOLO11n-based traffic light detection algorithm, named YOLO11n-PRE. Based on the baseline YOLO11n, the proposed algorithm first replaces the original C3k2 module in the backbone network with the C3k2-RCB module, which enhances deep feature extraction capability while maintaining lightweight via efficient residual connection and feature recalibration mechanism. Secondly, a P2 small object detection layer is introduced to fuse shallow high-resolution feature information, expanding the original 3-scale detection architecture to 4-scale detection, which significantly strengthens the network’s perception and positioning ability for micro-scale traffic lights. Finally, an ECA efficient channel attention module is embedded into the PANet feature fusion path, which enhances key feature response and suppresses redundant information via adaptive weight calibration in the channel dimension. Experimental results show that compared with the baseline YOLOv11n, YOLO11n-PRE achieves a 1.9 percentage point improvement in mAP@0.5, with precision and recall increased by 1.8 and 2.3 percentage points respectively, and the parameter count is only 2.8M, which fully meets the requirements of real-time and efficient detection.
Small object detection in industrial scenarios faces challenges including limited pixel coverage, weak feature representation, and background interference. To address these problems, this paper presents an improved YOLOv11 detection model. First, a dual-backbone network architecture is designed to simultaneously capture rich semantic information and spatial details through parallel feature extraction paths. Second, the SimAM parameter-free attention mechanism is integrated into top-level feature fusion to adaptively enhance features relevant to small objects. Finally, the Adaptive Spatial Feature Fusion (ASFF) module is improved with a dual attention mechanism to optimize multi-scale feature fusion and mitigate feature conflicts. On a self-constructed industrial tool dataset, the method achieves an mAP@0.5:0.95 of 0.920, improving upon the baseline YOLOv11n by 5.9 percentage points. For small object detection specifically, mAP_s reaches 0.898, representing a 7.9 percentage point improvement. Experiments on the public VisDrone dataset further validate the generalization capability of the approach. Results demonstrate that the proposed method significantly enhances small object detection performance, providing an effective solution for industrial vision applications.
Chengru Liu, Junqing Yang, Qi-Qi Guo et al.· 2026 8th International Confe...· 0 citations
To address the challenges of traffic sign detection in complex road environments, particularly the limited discriminability of small objects and localization errors caused by blur and occlusion, this paper proposes P2CL-YOLO, a lightweight detection framework built upon YOLOv11s. The proposed method introduces a unified P2CL design to enhance the representation of small and occluded traffic signs. First, a dedicated P2 detection layer is designed to preserve high-resolution shallow features for small-object perception. On this basis, a lightweight CBAM attention module is embedded to refine channel-spatial features, suppress background interference, and enhance target saliency. The refined features are further exploited through a dual-path strategy: they are fed back into the multi-scale feature fusion pathway to strengthen hierarchical representations, while simultaneously being delivered to the LSDECD detection head for accurate localization of occluded targets via dynamic feature calibration. In addition, the Wise-IoU loss is adopted to improve bounding box regression stability and convergence behavior. Experimental results on the TT100K dataset show that the proposed method achieves 88.3% mAP@0.5, outperforming YOLOv11s by 5.8%. The model contains 10.05 M parameters with 23.7 GFLOPs. Further evaluation on the German Traffic Sign Detection Benchmark dataset demonstrates strong cross-domain generalization ability. Overall, P2CL-YOLO achieves a favorable balance between detection accuracy and computational efficiency, making it suitable for real-time traffic sign detection in resource-constrained environments.
A novel 3D object detection algorithm based on the PointPillars framework based on a triple attention mechanism to enhance target features and suppress background noise is proposed and a multi-scale dual detection head is developed that performs predictions on feature maps of different resolutions, thereby improving the recall rate in complex scenarios.
S. Zhang, Yibing Zhao, Jian Liu et al.· Machine Vision and Applicati...· 0 citations
To address the challenges encountered in vehicle detection within complex traffic scenarios, such as diverse features, strong background interference, and deployment constraints on edge devices, a lightweight vehicle detection method based on YOLOv8 improved with the Coordinate Attention mechanism is proposed. In this method, the Coordinate Attention module is introduced into the YOLOv8s backbone network to reconstruct the C2f structure. By embedding positional information, the model enhances its capability to extract key features, suppressing complex background interference while maintaining its lightweight characteristics. Experiments conducted on a dataset comprising 17,428 images of 17 vehicle classes demonstrate that the improved model achieves a precision of 90.4% and an mAP@0.5 of 91.5%. For vehicle types with regular structures and large volumes, such as four-wheel small trucks and six-wheel medium trucks, the detection accuracy approaches 99%, and the detection confidence remains stable above 0.8 under complex lighting and background interference conditions. This method effectively controls model complexity while maintaining high detection accuracy, thereby satisfying the application requirements for real-time vehicle detection on edge devices such as intelligent driving recorders.
Zhihan Wang· The 2026 International Confe...· 0 citations
Small object detection is challenging due to insufficient feature information and strong background interference. This paper proposes an improved algorithm based on YOLOv12n, with a progressive and complementary design that sequentially performs detail enhancement, cross-layer fusion optimization, and final detection. First, a high‐pass multi‐dimensional collaborative attention (HPMCA) module embedded in the backbone uses discrete cosine transform high‐pass filtering and multi‐dimensional attention to extract edge and texture details, strengthening subtle features in shallow and middle layers to compensate for inherent scarcity. Second, a hierarchical channel attention fusion neck (HCAF‐Neck) takes HPMCA‐enhanced features as input, integrating channel attention and adaptive fusion to effectively suppress background clutter, eliminate semantic discrepancies among multi‐level features, and prevent deep semantic information from overwhelming small‐object cues, thus improving fused feature quality. Third, a P2 detection branch is added to exploit high‐resolution spatial information from shallow maps, leveraging the optimized features from HCAF‐Neck to enhance perception and localization. Extensive experiments on VisDrone2019‐DET, TinyPerson, and SeaDronesSee show that our method achieves 37.5% mAP@50 on VisDrone, outperforming YOLOv12n by 6 percentage points, and also delivers competitive performance on the other datasets, confirming its stability and efficiency for small‐object detection.
Bing-Bing Fu, Jiyang Qi· Measurement science and tech...· 0 citations
Multi-scale feature fusion and attention mechanisms are leveraged in this study to address the persistent challenge of small object detection in complex visual environments. To enhance the feature representation of small, low-contrast, and scale varying targets, the proposed detection framework is built on the YOLO framework and integrates a lightweight hybrid attention module and adaptive skip connections. By adopting selective channel-spatial attention and dynamic feature map alignment, the system retains key fine-grained details throughout the network, thus greatly reducing information loss during deep convolution processing. Experimental validation on the COCO small object subset and drone aerial images shows that the model achieves significant improvements in average precision and recall compared to established YOLO variants, especially for objects smaller than 32 x 32 pixels. The real-time inference speed and low memory usage are maintained, proving its effectiveness in embedded and resource-constrained applications. The effectiveness of combining advanced multi-scale fusion with attention mechanism to meet the needs of autonomous perception system is emphasized, and a robust and effective solution is provided for the scene where accurate small target detection is crucial.
Junnan Guo· The 2026 International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
