本文選題：管道探傷　切入點(diǎn)：管道機(jī)器人　出處：《化工自動(dòng)化及儀表》2016年11期 　論文類型：期刊論文

【摘要】：設(shè)計(jì)了針對(duì)小型管道內(nèi)部缺陷檢測的螺旋管道機(jī)器人系統(tǒng),基于該機(jī)器人系統(tǒng)提出了圖像處理的改進(jìn)算法。首先采用結(jié)合中值濾波思想的雙邊濾波器,解決了雙邊濾波無法去除孤立噪聲點(diǎn)的問題;其次采用了二維最大熵的閾值分割方法進(jìn)行圖像分割;最后根據(jù)管道缺陷的特點(diǎn)提取適合分類器分類的代表特征點(diǎn)進(jìn)行分類。仿真研究表明:所提算法能夠更加完整地提取缺陷信息。
[Abstract]:A spiral pipeline robot system is designed to detect the internal defects of small pipelines. Based on the robot system, an improved image processing algorithm is proposed. Firstly, a two-sided filter based on median filter is used. The problem that bilateral filtering can not remove isolated noise points is solved. Secondly, the threshold segmentation method based on 2-D maximum entropy is used for image segmentation. Finally, the representative feature points suitable for classifier classification are extracted according to the characteristics of pipeline defects. The simulation results show that the proposed algorithm can extract defect information more completely.
【作者單位】： 天津理工大學(xué)天津市復(fù)雜系統(tǒng)控制理論及應(yīng)用重點(diǎn)實(shí)驗(yàn)室;
【基金】：天津市科技重大專項(xiàng)與工程項(xiàng)目(15ZXZNGX00140) 天津市應(yīng)用基礎(chǔ)與前沿技術(shù)研究計(jì)劃項(xiàng)目(16JCTPJC49400)
【分類號(hào)】：TP391.41
，

本文編號(hào)：1627864