国产欧美精品一区二区,中文字幕专区在线亚洲,国产精品美女网站在线观看,艾秋果冻传媒2021精品,在线免费一区二区,久久久久久青草大香综合精品,日韩美aaa特级毛片,欧美成人精品午夜免费影视

In response to the demand for automated detection of overloaded trucks in intelligent overload management scenarios, an improved method is proposed based on YOLOv5s to recognize truck type from three aspects: data, model, and algorithm. At the data level, the data augmentation used simulates complex scenarios such as facing severe bad weather conditions, image noise, and data damage in real life, which enriches the diversity of training data and improves the robustness of the model. In terms of the model, a new attention mechanism is proposed to consider the importance of different channels and the positional information of encoding features, which improves the recognition accuracy of the model. In order to overcome the shortcomings of existing algorithms, a more general standard for determining the subordinate relationship between trucks and axles is proposed to apply to more complex scenarios. The experimental results show that the proposed improved model achieves recognition accuracy of 99.34% and 99.22% for truck and axle, respectively, and 98.71% accuracy for truck type recognition. Compared with the classic YOLOv5s network, the average recognition accuracy of trucks and axles has increased by 2.39%, and the truck type recognition accuracy is increased by 2.22%. In summary, the proposed method achieves automatic and accurate recognition of truck type, which can provide theoretical support for truck type recognition in intelligent overload management scenarios.