大型建筑表层墙体裂痕自动监测仿真

Automatic Monitoring Simulation of Cracks In Large Building Surface Wall

针对当前方法进行大型建筑表层墙体裂痕监测时,普遍存在着监测响应时间过长,准确率较低,能源消耗较大等问题。提出基于人工智能视觉的墙体裂痕监测方法。利用k-means算法将含有裂痕的表层墙体进行分类,引入概率松弛算法求出含有裂痕表层墙体像素点之间的空间结构特点,对含有裂痕信息的墙体进行特征提取,采用MeanShift序列算法,对墙体裂痕目标进行判别,引入核函数采集墙体裂痕图像集合间差异,以此完成监测。实验结果表明,所提出方法在进行大型建筑表层墙体裂痕监测时,监测响应时间较短、准确率较高、能源消耗较小。

Due to low accuracy and large energy consumption of current method in monitoring the cracks in the surface wall of large building,this article puts forward a method for monitoring wall cracks based on artificial intelli-gence vision.Firstly,k-means algorithm was used to classify the surface wall with cracks.Secondly,the probabilis-tic relaxation was introduced to find spatial structure characteristics between the pixels of surface walls with cracks.Moreover,the feature of wall with crack information was extracted,and MeanShift sequence algorithm was used to distinguish the wall crack target.Finally,the kernel function was used to collect the difference between the sets of wall crack image.Thus,the monitoring was completed.Simulation results show that the proposed method has shorter monitoring response time,higher accuracy and less energy consumption in monitoring the wall cracks in surface layer of large building.