A New Image-Based Model For Predicting Cracks In Sewer Pipes
A New Image-Based Model For Predicting Cracks In Sewer Pipes
复制标题
DOI：
10.14569/ijacsa.2013.041210
复制
发表时间：
2013
影响因子：
0.9
通讯作者：
I. Khalifa;A. Aboutabl;G. Barakat
中科院分区：
文献类型：
--
作者：
I. Khalifa;A. Aboutabl;G. Barakat
到目前为止，人工操作员的视觉检查主要用于检测下水道管道中的裂缝。在本文中，我们解决的问题，这种裂纹的自动检测。我们提出了一个模型，检测裂纹断裂，可能会发生在薄弱地区的管网。该模型还预测了五个裂纹水平之间的检测到的裂纹的粗糙度的水平。我们评估我们的结果进行比较，通过使用Canny算法得到的结果。该模型的准确率超过90%，优于其他方法。
Visual inspection by a human operator has been mostly used up till now to detect cracks in sewer pipes. In this paper, we address the problem of automated detection of such cracks. We propose a model which detects crack fractures that may occur in weak areas of a network of pipes. The model also predicts the level of dangerousness of the detected cracks among five crack levels. We evaluate our results by comparing them with those obtained by using the Canny algorithm. The accuracy percentage of this model exceeds 90% and outperforms other approaches.