AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
The YOLOv12 network is adopted as the baseline model and the ADown module is introduced to improve downsampling efficiency while maintaining lightweight performance, and the BN-CGLU is incorporated into the A2C2f module to enhance the model’s nonlinear representation capability.
This study presents SEII-YOLO, a lightweight architecture optimized based on the YOLOv11n framework, which achieves notable performance gains—particularly in distinguishing similar-looking equipment—while reducing parameters by 8.96% and computational load by 3.17%.
The mixing stage of automotive battery production requires reliable monitoring of raw material types, personnel actions, and correct tool use. However, accurate multi-scale object detection in complex scenes remains challenging because of background interference and the requirements of embedded deployment and real-time operation. This study proposes an enhanced YOLOv5 framework for industrial multi-object detection. The method adopts a dual-stage feature-enhancement strategy designed to improve robustness while limiting parameter count and computational complexity. First, the Convolutional Block Attention Module (CBAM) is embedded in the Backbone and Neck of YOLOv5 to provide multi-granularity feature enhancement and improve the detection of small objects, such as tools. Second, the conventional CIOU loss is replaced with the Focal-EIOU loss function to optimize bounding-box regression, reduce false detections across multiple target scales, and accelerate model convergence. Finally, K-means clustering is applied to target geometric features to generate specialized anchor-box parameters better suited to industrial scenarios. Experimental results on an automotive battery production-site dataset show that the improved model's mAP@0.5 increased by 2.4 % compared with the original model, reaching 95.2 %, while mAP@0.5:0.95 improved by 3.6 %, reaching 78.5 %. The proposed framework provides a lightweight and reliable solution for multi-object detection in complex industrial environments and supports the development of intelligent visual monitoring systems for smart manufacturing.
A lightweight YOLOv11-based foreign object detector is designed, using StarNet to reconstruct the backbone, reducing redundant parameters and computational cost, and SDIoU is introduced for bounding box regression, which improves the localization of multi-scale targets.
A lightweight detection algorithm named GCW-YOLOv8, which improves detection accuracy by 1.4% while reducing parameter count by 34.4%, achieving a superior balance between accuracy and efficiency for smart construction site applications.
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.
Aircraft skin defect detection often suffers from low detection accuracy due to variations in lighting, shadows, and complex backgrounds. To address this, this study proposes a lightweight and enhanced YOLOv8n-based algorithm. Firstly, the original C2f structure is replaced by the new C2fGhost module to reduce the floating-point operation volume during the feature channel fusion process. Secondly, the AOM (Attention Occlusion Mechanism) is introduced to enhance feature extraction in complex environments. Finally, a regression loss function combining DFL and WIS-IoU is adopted to improve convergence. The experimental results demonstrate that the proposed algorithm achieves a Precision of 85.4% and an mailto:mAP@0.5 of 83.6%, representing improvements of 2.6% and 1.9% respectively over the baseline YOLOv8n model. Notably, this performance boost is achieved while maintaining a compact model size of merely 6.02 MB. These results signify a substantial advancement in balancing detection accuracy and model efficiency, offering a highly viable solution for real-time, embedded inspection systems in the aerospace industry.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.