本文關(guān)鍵詞： 裂縫圖像 裂縫檢測 簡化脈沖耦合神經(jīng)網(wǎng)絡(luò) 特征提取　出處：《鄭州大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：我國公路的發(fā)展一日千里。道路質(zhì)量的及時檢測在延長道路使用壽命的同時,也可以避免路面病害給行車安全方面帶來的隱患�？紤]到人工檢測方法存在效率低、精度低、危險系數(shù)較高等缺陷,路面裂縫的自動檢測系統(tǒng)成為道路養(yǎng)護(hù)方向的熱點研究問題,而裂縫自動檢測算法則為自動檢測系統(tǒng)的核心內(nèi)容。依據(jù)國內(nèi)外已有的道路裂縫檢測相關(guān)算法,本文對裂縫檢測算法進(jìn)行了研究與設(shè)計。首先,單純地從對裂縫圖像進(jìn)行裂縫檢測的角度出發(fā),需要對傳統(tǒng)的脈沖耦合神經(jīng)網(wǎng)絡(luò)(PCNN)模型進(jìn)行簡化改進(jìn),這不僅可以降低傳統(tǒng)PCNN在模擬過程中的計算復(fù)雜度,而且保留了其原有的神經(jīng)元運行特征,使其可以應(yīng)用于裂縫圖像的目標(biāo)檢測。針對PCNN無法確定裂縫圖像的最優(yōu)檢測以及脈沖門限具有非線性因子的問題,提出了一種基于遺傳算法(GA)和簡化PCNN的裂縫圖像檢測方法—GA-PCNN。該方法采用改進(jìn)后的最小誤差準(zhǔn)則作為遺傳算法的適應(yīng)度函數(shù),并且根據(jù)遺傳算法具有全局最優(yōu)解的特點確定簡化PCNN中各因子的值,實現(xiàn)了簡化PCNN的裂縫圖像自動分割。在使用GA-PCNN算法對裂縫圖像進(jìn)行處理后,通過一種形態(tài)學(xué)的抗噪多結(jié)構(gòu)元素邊緣提取算子對其裂縫邊緣進(jìn)行提取,然后使用一種基于生長的連接方法對斷裂的裂縫塊進(jìn)行邊緣連接。基于MATLAB R2009a平臺對本文算法進(jìn)行實驗仿真,通過與不同的檢測方法進(jìn)行比較,以區(qū)域?qū)Ρ榷�、ROC曲線這些客觀指標(biāo)為基準(zhǔn)對其性能進(jìn)行分析。分析結(jié)果表明,該方法對裂縫圖像檢測具有較好的有效性與通用性。最后,對利用上述方法得到的裂縫目標(biāo)圖像,進(jìn)行裂縫特征信息的提取、分類及計算。經(jīng)過對檢測后的圖像設(shè)置一系列判定條件,提取圖像中連通域信息;同時通過觀察裂縫在坐標(biāo)軸投影所呈現(xiàn)的特點,對目標(biāo)裂縫進(jìn)行分類;通過細(xì)化的方法提取裂縫骨架,并對目標(biāo)裂縫的面積及長度、寬度信息進(jìn)行計算。
[Abstract]:With the rapid development of highway in our country, the timely detection of road quality can not only prolong the service life of the road, but also avoid the hidden danger brought by the road surface diseases to the driving safety. Considering the low efficiency and low precision of the manual detection method, Because of the defects such as high risk coefficient, the automatic detection system of pavement cracks has become a hot research issue in the direction of road maintenance. The automatic crack detection algorithm is the core of the automatic detection system. According to the existing road crack detection algorithms, this paper studies and designs the crack detection algorithm. It is necessary to simplify and improve the traditional pulse coupled neural network (PCNN) model from the point of view of crack detection in fracture images, which can not only reduce the computational complexity of traditional PCNN in the process of simulation. Moreover, it preserves its original neuronal characteristics, which can be applied to target detection of crack image. In view of the problem that PCNN can not determine the optimal detection of crack image and the pulse threshold has nonlinear factor, A crack detection method named -GA-PCNN based on genetic algorithm (GA) and simplified PCNN is proposed. The improved minimum error criterion is used as the fitness function of genetic algorithm. According to the characteristics of global optimal solution of genetic algorithm (GA), the value of each factor in simplified PCNN is determined, and the crack image of simplified PCNN is segmented automatically. After using GA-PCNN algorithm to process the crack image, The edge of crack is extracted by a morphological edge detection operator with anti-noise and multi-structure elements. Then a growth-based connection method is used to connect the fracture blocks. The algorithm is simulated based on the MATLAB R2009a platform, and compared with different detection methods. The performance of the method is analyzed based on the objective index of regional contrast and ROC curve. The analysis results show that the method is effective and universal for crack image detection. Finally, the fracture target image obtained by the above method is analyzed. After setting a series of judgment conditions to detect the image, extract the information of the connected region in the image, and observe the characteristics of the crack projection on the axis, the paper carries out the extraction, classification and calculation of the feature information of the crack, and sets a series of judgment conditions to the detected image. The target crack is classified and the crack skeleton is extracted by thinning method, and the information of the area, length and width of the target crack is calculated.
【學(xué)位授予單位】：鄭州大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 顧曉東,余道衡;PCNN的原理及其應(yīng)用[J];電路與系統(tǒng)學(xué)報;2001年03期

2 鄒文潔;;基于PCNN神經(jīng)網(wǎng)絡(luò)的圖像去噪算法研究[J];計算機(jī)仿真;2008年08期

3 齊永鋒;火元蓮;張家樹;;基于簡化的PCNN與類內(nèi)最小離散度的圖像自動分割方法[J];光電子.激光;2008年09期

4 王念一;馬義德;綻琨;;PCNN理論研究進(jìn)展及其語音識別中的應(yīng)用[J];自動化與儀器儀表;2013年01期

5 鐘亞平;;基于PCNN的手腕骨圖像自動分割方法研究[J];軟件導(dǎo)刊;2013年07期

6 顧曉東,郭仕德,余道衡;一種基于PCNN的圖像去噪新方法[J];電子與信息學(xué)報;2002年10期

7 趙峙江;趙春暉;張志宏;;一種新的PCNN模型參數(shù)估算方法[J];電子學(xué)報;2007年05期

8 火元蓮;;一種基于PCNN的圖像自動分割方法[J];自動化與儀器儀表;2008年06期

9 李敏;蔡騁;談?wù)?;基于修正PCNN的多傳感器圖像融合方法[J];中國圖象圖形學(xué)報;2008年02期

10 劉R，

本文編號：1536121