Research on luminaire paint defect detection model based on improved YOLOv10

Aiming at the problems of low detection accuracy, low computational efficiency and poor detection ability of multi-scale targets in existing detection methods, an improved YOLOv10 algorithm was proposed to improve the accuracy and efficiency of multi-scale defect detection of luminaire paint. By introducing the LSKA attention mechanism to the SPPF module on the YOLOv10 feature extraction backbone network, the recognition ability of the complex form of paint defects of lamps is improved. At the same time, the lightweight design of C2f and detection head module makes the algorithm more suitable for real-time application scenarios. In terms of evaluation indexes, after ablation experiments, the improved algorithm has improved 2.6% compared with the original YOLOv10 in main performance indexes mAP@0.5. In addition, the lightweight design of the improved algorithm significantly reduces the number of parameters and the amount of computation required. Compared with the original YOLOv10, the number of parameters is reduced by 0.22×10 ⁶ and the amount of computation is reduced by 1.4GFLOPS, making it more suitable for deployment in resource-constrained environments. The improved YOLOv10 algorithm proposed in this paper achieves a balance of high accuracy and high efficiency in the multi-scale defect detection of luminaire paint surface, providing a reliable machine learning technical means for industrial production, and helping industrial equipment to carry out efficient monitoring and diagnosis under unattended conditions.