本文選題：計(jì)算機(jī)視覺　切入點(diǎn)：指數(shù)矩　出處：《北京郵電大學(xué)》2017年博士論文

【摘要】：計(jì)算機(jī)視覺,正在從根本上改變我們的世界,以及我們每個(gè)人的生活方式。讓機(jī)器之眼代替人眼,看懂我們的世界,實(shí)現(xiàn)智能化控制,解放人類的雙手,是無數(shù)科學(xué)家夢寐以求的理想。視覺智能的潛在應(yīng)用是無限的,人工智能幾乎觸及人類生活的各個(gè)方面,本文主要針對(duì)計(jì)算機(jī)視覺在智慧交通領(lǐng)域的應(yīng)用展開研究,將指數(shù)矩的多畸變不變性運(yùn)用到車輛追蹤、車牌定位、以及車牌字符識(shí)別中,形成一套基于指數(shù)矩的車輛識(shí)別算法。指數(shù)矩的相關(guān)理論,是計(jì)算機(jī)視覺領(lǐng)域一個(gè)新的研究方向,不僅可以用于車牌識(shí)別,還可應(yīng)用于常規(guī)的物體識(shí)別、場景識(shí)別等,因?yàn)橹笖?shù)矩的平移、縮放、和旋轉(zhuǎn)不變性,對(duì)于目標(biāo)物體的傾斜,遠(yuǎn)近變化,光照不足,天氣惡劣等情況有很強(qiáng)的抗干擾能力,在不佳環(huán)境下依然具有很高的識(shí)別效率和準(zhǔn)確度�；谥笖�(shù)矩的相關(guān)研究,對(duì)于未來智慧交通、智慧城市的建設(shè)有一定的價(jià)值。本文將指數(shù)矩作為圖像的特征參數(shù),對(duì)車輛追蹤、車牌定位、及車牌字符識(shí)別展開了一系列研究,主要的研究工作和創(chuàng)新點(diǎn)有下列幾個(gè)方面:(1)提出了基于指數(shù)矩的車輛跟蹤算法。在反復(fù)的實(shí)驗(yàn)中,作者發(fā)現(xiàn),在收費(fèi)站和交通關(guān)卡,車輛相對(duì)嚴(yán)格的直線行駛,從某一固定點(diǎn)觀察,車輛向遠(yuǎn)向近行駛可以視為連續(xù)的縮放變化,利用這一特征,作者將指數(shù)矩的縮放不變性運(yùn)用到車輛跟蹤中,提出了一種新的車輛跟蹤算法。首先利用幀間差分法確定目標(biāo)車輛,然后提取目標(biāo)車輛的指數(shù)矩作為跟蹤參數(shù),通過不斷調(diào)整搜索窗口的位置,實(shí)現(xiàn)多車輛的自動(dòng)跟蹤。較傳統(tǒng)車輛跟蹤算法,本文算法利用了指數(shù)矩的縮放不變性,降低了光照和天氣對(duì)識(shí)別的影響,提高了跟蹤的魯棒性。車輛自動(dòng)跟蹤算法在收費(fèi)站、交通關(guān)卡等有著廣泛的應(yīng)用前景。(2)提出了基于指數(shù)矩的車牌定位算法。本文提出了一種全新的車牌定位方法:基于指數(shù)矩特征的車牌定位方法。車牌定位是后續(xù)車牌字符識(shí)別的前提和基礎(chǔ),在車牌識(shí)別過程中具有至關(guān)重要的作用。本文將指數(shù)矩運(yùn)用到車牌定位中,利用指數(shù)矩的平移、縮放、和旋轉(zhuǎn)不變性,在車牌傾斜、車輛遠(yuǎn)/近變化、天氣變化、光照不足等環(huán)境信息變化的情況下,依然具有良好的識(shí)別效果。本方法在不必進(jìn)行傾斜校正、不必進(jìn)行中心點(diǎn)調(diào)整以及比例調(diào)整的情況下,即可定位車牌,縮短了定位時(shí)間,具有良好的實(shí)際應(yīng)用價(jià)值。(3)提出了基于指數(shù)矩和網(wǎng)格計(jì)算的車牌字符識(shí)別算法。作者根據(jù)車牌的字符形態(tài)學(xué)特征,對(duì)將車牌的所有字符分為12組:第1組是漢字組;第2-11組為形近的數(shù)字和字符組;第12組為模值無關(guān)組。將12個(gè)分組對(duì)應(yīng)12個(gè)神經(jīng)網(wǎng)絡(luò)分類器,進(jìn)行指數(shù)矩和網(wǎng)格特征訓(xùn)練,待處理的字符依次進(jìn)入相應(yīng)分類器,用指數(shù)矩特征進(jìn)行初級(jí)分類,再利用網(wǎng)格特征進(jìn)行第二次判定,確定最終的識(shí)別結(jié)果。該方法有效利用了指數(shù)矩的識(shí)別優(yōu)勢,同時(shí),利用網(wǎng)格特征,彌補(bǔ)了指數(shù)矩由于旋轉(zhuǎn)不變性在形似字符的判定中產(chǎn)生的誤差。
[Abstract]:Computer vision, is changing our world radically, and the life of each of us. Let the eye machine to replace eyes, we understand the world, the realization of intelligent control, liberation of human hands, is a dream of many scientists. The potential application of visual intelligence is infinite, almost all aspects of artificial intelligence touch of human life, this paper focuses on the application of computer vision in the field of intelligent transportation research, the index of moment distortion invariance applied to vehicle tracking, vehicle positioning, and license plate character recognition, a vehicle recognition algorithm based on moment theory index. The index of moment, is a new research direction the field of computer vision, not only can be used for license plate recognition, can also be used in conventional object recognition, scene recognition, because the moment index translation, scaling, and rotation invariance, To tilt, the object distance changes, insufficient light, bad weather conditions and have strong anti-interference capability, in the poor environment still has high recognition efficiency and accuracy. The related research index based on moment, for the future of intelligent transportation, smart city construction has a certain value. This paper will index moments as the feature parameters of the image, the vehicle tracking, vehicle license plate location, license plate character recognition and launched a series of research, the main research works and innovations are as follows: (1) tracking algorithm is proposed based on the exponential moment. The author found the vehicle in repeated experiments, and at the toll station and crossing traffic the vehicle, relatively tight straight, from a fixed point observation, the vehicle to travel away from the past can be regarded as the continuous change of the zoom, using this feature, the author will use the zoom invariant moment index to vehicle tracking, Put forward a new vehicle tracking algorithm. Firstly using frame difference method to determine the target vehicle, then the exponential moment is extracted as the target vehicle tracking parameters, by adjusting the position of the search window, automatic tracking of multiple vehicles. Compared with the traditional vehicle tracking algorithm, this algorithm uses zoom invariance moment index, reduce the effects of light and weather on the recognition, improve the robustness of tracking algorithm. In the toll station, automatic vehicle tracking, traffic levels and has a wide application prospect. (2) proposed a license plate location algorithm based on the exponential moment. This paper proposes a new method of license plate location: license plate location method of exponential moments based on the characteristics. License plate location is the premise and basis of the license plate character recognition, has a crucial role in the process of license plate recognition. In this paper, the exponential moment applied to license plate location, using the exponential moment Pan, zoom, tilt and rotation invariance in the vehicle, far / near changes, changes in the weather, illumination changes such as lack of environmental information, it still has a good recognition effect. This method needn't tilt correction, without center adjustment and ratio adjustment, can be license plate positioning, shorten the positioning time and has good practical value. (3) proposed character recognition algorithm based on Grid Computing and the exponential moment. According to the morphological features of license plate characters, all the characters are divided into 12 groups: the first group is the 2-11 group is the group Chinese characters; and digital form the character group of nearly twelfth groups; independent group value model. The 12 groups corresponding to the 12 neural network classifier, exponential moments and mesh character training, the character in order to enter the corresponding classifier, the primary classification index of moment features, and then The second decision is made by grid feature to determine the final recognition result. This method takes advantage of the identification of exponential moment effectively, and makes use of grid characteristics to compensate for the error caused by the rotation invariance of the exponential moment in the determination of the similar character.

【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 平子良;任海萍;盛云龍;午日亙;;一種廣義正交不變圖像矩:雅可比-傅立葉矩[J];光電子.激光;2008年03期

2 任海萍,平子良,博午日亙,盛云龍;基于雅可比-傅里葉矩的細(xì)胞模式識(shí)別[J];中國生物醫(yī)學(xué)工程學(xué)報(bào);2005年05期

3 博午fE,平子良,任海萍,盛云龍;切比雪夫-傅立葉矩用于多畸變不變模式識(shí)別(英文)[J];光電子·激光;2003年08期

相關(guān)博士學(xué)位論文 前3條

1 姜永靜;指數(shù)矩及其在模式識(shí)別中的應(yīng)用[D];北京郵電大學(xué);2011年

2 胡海濤;基于矩特征的鱗癌細(xì)胞識(shí)別[D];北京郵電大學(xué);2010年

3 高俊祥;智能視頻監(jiān)控中目標(biāo)的檢測與跟蹤[D];北京郵電大學(xué);2010年

，

本文編號(hào)：1688587