Abstract
Automating the current bridge visual inspection practices using drones and image processing techniques is a prominent way to make these inspections more effective, robust, and less expensive. In this paper, we investigate the development of a novel deep-learning method for the detection of fatigue cracks in high-resolution images of steel bridges. First, we present a novel and challenging dataset comprising of images of cracks in steel bridges. Secondly, we integrate the ConvNext neural network with a previous state- of-the-art encoder-decoder network for crack segmentation. We study and report, the effects of the use of background patches on the network performance when applied to high-resolution images of cracks in steel bridges. Finally, we introduce a loss function that allows the use of more background patches for the training process, which yields a significant reduction in false positive rates.
Abstract (translated)
使用无人机和图像处理技术自动化当前的桥梁视觉检查做法是一种有效、稳健且成本较低的方法。在本文中，我们研究了用于检测钢桥高分辨率图像中疲劳裂纹的新颖深度学习方法的发展。首先，我们提出了一个由钢桥裂纹图像组成的全新有挑战性的数据集。其次，我们将ConvNext神经网络与之前的最先进的编码器-解码器网络相结合进行裂纹分割。我们研究并报道了将背景补丁应用于高分辨率裂纹钢桥图像时对网络性能的影响。最后，我们引入了一种允许在训练过程中使用更多背景补丁的损失函数，从而显著降低 false positive 率。
URL
https://arxiv.org/abs/2403.17725
