本文中以YOLOv4深度学习目标检测算法为基础算法框架，建立轻量化目标

本文中以YOLOv4深度学习目标检测算法为基础算法框架，建立轻量化目标检测算法Lightweight YOLO（LYOLO）检测算法。制作工厂车间环境目标数据集，对数据进行标注，并对数据进行高斯噪声处理，做到多样化扩充来增强网络的泛化性能及鲁棒性。YOLOv4目标检测算法检测性能较好但是复杂的主干网络结构导致模型整体体积过大，实际应用时较难达到预期效果。

In this paper, based on the algorithm framework of yolov4 deep learning target detection algorithm, a lightweight Yolo (lyolo) detection algorithm is established. Make the factory workshop environment target data set, label the data, and process the data with Gaussian noise to achieve diversified expansion to enhance the generalization performance and robustness of the network. Yolov4 target detection algorithm has good detection performance, but the complex backbone network structure leads to the overall volume of the model is too large, which is difficult to achieve the expected effect in practical application.

In this paper, based on the algorithm framework of YOLOv4 deep learning target detection algorithm, a lightweight target detection algorithm, Lightweight YOLO(LYOLO) detection algorithm, is established. Make the factory workshop environmental target data set, label the data, and process the data with Gaussian noise, so as to achieve diversified expansion to enhance the generalization performance and robustness of the network. YOLOv4 target detection algorithm has good detection performance, but the complex backbone network structure leads to the overall volume of the model being too large, which makes it difficult to achieve the expected results in practical application.