Detection of Building Façade Damage Based on Improved YOLOv8

With the continuous acceleration of urban modernization, the number of houses in the city continues to increase, and the population becomes more and more densely populated. Once a building collapses or the facade falls off, it will cause immeasurable losses of life and property. However, traditional building facade inspection has problems such as slow inspection speed and high cost. In response to the above problems, this paper proposes an improved building facade detection method based on the YOLOv8 algorithm. In order to detect building facades in real time, the Ghost module is designed for the backbone network, which greatly reduces the number of parameters in the model and improves the detection speed. By adding the SE attention mechanism, problems such as complex background images and insufficiently obvious features in the building facade data set are solved. Finally, the Focal-EIoU loss function is used to improve the detection accuracy of the model. Experimental results show that compared with the original model, the detection accuracy of the model proposed in this article is improved by 1.9%, and the number of parameters of the model is reduced by 11.6%, which can better meet the application scenarios of building facade detection.