基于圖像處理的車型識別,基于,圖像,圖象,處理,車型,識別,辨認 一、 畢業(yè)設(shè)計（論文）的目的與要求：1. 培養(yǎng)學生綜合運用所學基礎(chǔ)課、技術(shù)基礎(chǔ)和專業(yè)課的知識，分析和解決工程技術(shù)問題的工作能力。2. 鞏固、深化和擴大學生所學基本理論、基本知識和基本技能。3. 要求學生在熟練掌握計算機技術(shù)，圖像處理的前提下，了解不同類型汽車特征提取方法，已經(jīng)在此基礎(chǔ)上了解不同類型汽車自動識別方法。4. 本課題進行過程中能鍛煉學生的調(diào)查研究、查閱文獻和收集資料、理論分析、試驗測試的能力；并重點鍛煉了學生 Matlab 程序設(shè)計的能力、圖像處理與分析的能力；在學期結(jié)束時撰寫論文和設(shè)計說明書的能力進行鍛煉。5. 培養(yǎng)學生的創(chuàng)新能力和團隊精神，樹立良好的學術(shù)思想和工作作風。 2．畢業(yè)設(shè)計（論文）的內(nèi)容：掌握圖像處理與識別的基礎(chǔ)流程與方法，研究不同類型汽車的特征提取方法，并根據(jù)所提取的特征識別汽車的類型，在試驗測試中，要求至少對 4 種不同的車型進行識別。本課題主要采用理論與實驗測試相結(jié)合的研究方式，為多種不同類型汽車自動識別系統(tǒng)的設(shè)計與開發(fā)提供了一定的理論依據(jù)。三、畢業(yè)設(shè)計（論文）課題應完成的工作:1．開題報告；2．與課題有關(guān)的外文翻譯（一萬字符以上）；3．掌握不同類型汽車特征提取及自動識別方法；4．以 Matlab 為工具實現(xiàn)相關(guān)算法；5．進行實例測試與分析。四．畢業(yè)設(shè)計（論文）進程的安排：序 號 設(shè)計（論文）各階段名稱 日 期 備 注 1 調(diào)研報告準備和開題報告 2015 年 12 月 15 日 ~ 2016 年 1 月 15 日2 外文翻譯 2016 年 2 月 22 日~ 2016 年 2 月 28 日3 以 Matlab 為工具實現(xiàn)汽車類型特征提取及自動識別2016 年 3 月 1 日~ 2016 年 4 月 15 日4 實例測試與分析 2016 年 4 月 16 日~ 2016 年 4 月 30 日5 撰寫論文及答辯 2016 年 5 月 1 日 ~ 2016 年 5 月 31 日五．應收集的資料及主要參考文獻： [1] 李晉秀，趙建濤.一種圖像處理的汽車類型識別算法[J].西安工業(yè)大學學報， 2009,29(3):275-278.[2] 王振峰.圖像處理技術(shù)在汽車類型自動識別中的應用研究[D].中國農(nóng)業(yè)大學碩士學位論文，2000.[3] 馬寧.基于神經(jīng)網(wǎng)絡(luò)的汽車識別研究[D].哈爾濱工程大學碩士學位論文，2002.[4] 周偉.MATLAB 小波分析高級技術(shù)[M]，西安：西安電子科技大學出版社， 2006,1-130.[5] 梅麗鳳, 王艷秋.藍和惠一種新型車型自動識別系統(tǒng)[J],制造業(yè)自動化,2006, 28 (12):68-71.[6] 蔡智湘.車型自動分類技術(shù)的分析和前景展望[J],濰坊學院學報，2004.7,14(4):120-122.[7] 張鐵.基于視頻的車型識別系統(tǒng)的實現(xiàn)[D],四川；四川大學，2004.[8] 曹治錦，唐慧明.視頻圖像中的車型識別[J]，計算機工程與應用 2004,(24):226-228.六、任務執(zhí)行日期：自 20XX 年 12 月 15 日 起，至 20XXX 年 6 月 1 日 止。學 生（簽字） 指導教師（簽字） 系 主 任（簽字） 目錄1 課題背景 .21.1 研究背景 21.2 研究意義 22 文獻調(diào)研 .33 課題目標 .44 課題內(nèi)容 .44.1 課題內(nèi)容介紹 44.2 技術(shù)路線 54.3 可行性分析 64.4 關(guān)鍵技術(shù)分析 65 日程安排 .76 參考文獻 .821 課題背景1.1 研究背景智能交通系統(tǒng)( Intelligent TransportationSy stem , ITS)是未來交通系統(tǒng)的發(fā)展方向，是將先進的計算機技術(shù)、通訊技術(shù)、機器視覺等集成運用于交通管理系統(tǒng)而建立的一種實時 、準確、高效的綜合交通運輸管理系統(tǒng)。ITS在美國、日本和歐洲研發(fā)較早，實際應用程度也較高，我國也已于本世紀初開始大力進行 ITS 的研究工作。ITS 的發(fā)展應用大力增加了交通管理的智能化程度，如判別路面破損程度、識別車輛類型、檢測車流量等。數(shù)字圖像是 ITS 中重要的信息載體，圖像處理技術(shù)對 ITS 的效能有著重要的影響。汽車是交通系統(tǒng)中的主要對象，汽車類型的識別廣泛應用于公路管理及公路收費系統(tǒng)中。目前，采用傳統(tǒng)的電磁感應線圈識別車型在實際中較多，但由于其固有的對路面破壞、維護困難、獲取參數(shù)單一等原因，使其發(fā)展受到了很大的限制。此外，“車牌識別”也在逐步應用，但對一些違規(guī)遮擋、涂改、改掛車牌的現(xiàn)象卻無能為力，特別是對未來的無人值守收費系統(tǒng)，僅依靠車牌識別則不能完全解決這些問題。1.2 研究意義汽車識別的復雜性與挑戰(zhàn)性并沒有影響人們對這一課題的研究熱情,這與汽車識別的應用價值和重要理論的意義分不開的。從應用的角度講,汽車識別系統(tǒng)的研究和開發(fā)在道路收費、車輛監(jiān)測中具有很明顯的實用價值。32 文獻調(diào)研在我們的日常生活中，隨著計算機技術(shù)的快速發(fā)展,傳感器性能的不斷提高,以及各類系統(tǒng)軟件和應用軟件的大量開發(fā)和推廣,計算機己經(jīng)從先前單純的數(shù)值計算,應用到文字處理、圖形圖像處理、語音處理、人工智能及模式識別等各個領(lǐng)域。但計算機對聲音、圖像等外界信息的直接感知上的局限性,已越來越成為計算機進一步應用發(fā)展的障礙,也與其高超的運算能力形成鮮明的對比。因此著眼于拓寬計算機的應用領(lǐng)域,提高計算機感知外部信息能力的新學科—模式識別便應運產(chǎn)生。經(jīng)過幾代研究人員三十多年的不斷努力,這一學科正不斷發(fā)展成熟。在語音識別方面,藍色巨人 BIM 以及其他公司己經(jīng)有多種語言版本的語音識別產(chǎn)品問世,連續(xù)語音識別已相當成熟,并己開始走向了實用化、商品化。而在圖像處理與識別方面成果也豐富多彩,特別是在軍事、醫(yī)學、地質(zhì)、氣象等領(lǐng)域都取得了可喜的實用成果。汽車識別作為模式識別學科的一個分支,是模式識別領(lǐng)域中一個困難而又十分具有實際應用價值和廣闊應用前景的研究課題。近些年來隨著國家公路建設(shè)的飛速發(fā)展,為支持國家公路建設(shè)迅速回收資金而設(shè)立了大大小小的收費站,在收費的過程中產(chǎn)生了這樣或那樣的經(jīng)濟問題,如收人情費、私設(shè)小金庫、道路堵塞等,如何做到對收費的科學管理,堵塞工作人員的經(jīng)濟漏洞,并獲得各種車輛流量的科學數(shù)據(jù),為國家的道路規(guī)劃提供合理的理論依據(jù),這就成為當前一個急需解決的問題。隨著我國交通基礎(chǔ)設(shè)施建設(shè)的不斷投入和飛速發(fā)展,公路里程快速增長,橋梁數(shù)目不斷增多,路橋的交通流量變得越來越大。通暢的交通帶來了經(jīng)濟的快速4增長,許多地方為發(fā)展本地區(qū)經(jīng)濟,大力發(fā)展交通,修建了高等級公路。由于修建公路采用的是“借貸修路,滾動發(fā)展”的策略,為償還貸款,地方政府報經(jīng)省人民政府批準后,在公路、橋梁上設(shè)置收費站,對車輛收取通行費。無論采取哪種收費方式,都必須先對車輛進行分類,才能確定應當收取的通行費。當前,車輛類別的判定一般由人工來完成,其突出的優(yōu)點是誤判少、可靠性好,但也存在弊端。因此,對車輛進行自動分類識別,解決車輛在路上暢通行駛,實現(xiàn)路橋的現(xiàn)代化管理,并且杜絕人工收費所造成的收費款額流失成為魚待解決的問題。電子技術(shù)和計算機技術(shù)的發(fā)展,為解決這個問題提供了可靠的技術(shù)保障。路橋自動收費系統(tǒng)的誕生和應用,不僅能充份體現(xiàn)出公路路橋口現(xiàn)代化管理的先進水平,同時還會緩解目前路橋收費口造成的交通擁擠堵塞現(xiàn)象,堵塞人工收費造成收費款額流失的漏洞,從而產(chǎn)生較大的社會效益和經(jīng)濟效益。車輛自動識別分類技術(shù)是路橋自動收費系統(tǒng)的重要組成部分,是一門集模式識別、工業(yè)測控技術(shù)、電子技術(shù)、系統(tǒng)工程技術(shù)于一體的綜合技術(shù)。它對在特定地點和時間的車輛進行識別和分類,作為交通管理、收費、調(diào)度、統(tǒng)計的依據(jù)。國外由于公路建設(shè)起步早,對于車輛自動分類技術(shù)的研究開始的也早。國內(nèi)進入九十年代才。開始這方面的研究,如交通部科學研究院、西安公路所、上海交通大學、西安交通大學、北京理工大學等,部分系統(tǒng)已投入正式運營。3 課題目標(1). 培養(yǎng)學生綜合運用所學基礎(chǔ)課、技術(shù)基礎(chǔ)和專業(yè)課的知識，分析和解決工程技術(shù)問題的工作能力。(2). 要求學生在熟練掌握計算機技術(shù)，圖像處理的前提下，了解不同類型汽車特征提取方法，以及在此基礎(chǔ)上了解不同類型汽車自動識別方法。(3).本課題進行過程中能鍛煉學生的調(diào)查研究、查閱文獻和收集資料、理論分析、試驗測試的能力；并重點鍛煉了學生 matlab 程序設(shè)計的能力、圖像處理與分析的能力。(4).整理各類文檔，撰寫畢業(yè)論文。54 課題內(nèi)容4.1 課題內(nèi)容介紹掌握圖像處理與識別的基本流程與方法。研究不同類型汽車的特征提取方法，并根據(jù)所提取的特征識別汽車的類型，在試驗測試中，要求至少對 4 種不同的車型進行識別。4.11 圖像特征提取及車型分類汽車的相關(guān)參數(shù)較多,就外形而言，就有車長、車寬、車高、軸距、輪距、軸數(shù)等多個參數(shù)，不同的參數(shù)，其圖像處理算法和分類效果有很大的區(qū)別。在現(xiàn)如今的實際應用當中，用線圈測量軸距的方法最多，但不能有效防止有些違法用戶私自加長，加寬車箱等現(xiàn)象。本文選擇最典型的，無法以大改小的車長、車高兩大基礎(chǔ)幾何特征設(shè)計算法。4.12 圖像處理及算法圖像處理是為了某種目的對圖像的強度(灰度)分布做某些特殊的加工和分析,主要分為兩大類,一是光學處理,一是數(shù)字圖像處理。從數(shù)學的角度來講,圖像識別使一個從高維特征向量空間到一維空間的非線性映射,Kolmogorov 定理’理保證任一個連續(xù)函數(shù)或映射可由一個三層網(wǎng)絡(luò)來實現(xiàn)。BP 網(wǎng)絡(luò)是一個多層前饋網(wǎng)絡(luò),盡管存在一些問題,如局部極小值、學習速度較慢等,但是,由于網(wǎng)絡(luò)容易構(gòu)造,對輸入的數(shù)據(jù)沒有什么要求,理論研究的深入,在實踐中有廣泛的深入應用,不少研究學者用它來進行圖像識別。針對本課題深入研究的系統(tǒng)中特定幾種汽車的汽車識別問題,綜合考慮上面的因素,我們選用 BP 網(wǎng)絡(luò)模型來設(shè)計分類器。4.13 汽車識別的軟環(huán)境鑒于本算法軟件的實驗性與探索性,因此本軟件的全部在由 VC 開發(fā)的Matlab 系統(tǒng)軟件平臺上設(shè)計完成。Matlba 是 MathWorkS 公司的產(chǎn)品,它是一種交互式、面向?qū)ο蟮某绦蛟O(shè)計語言,廣泛應用于工業(yè)界與學術(shù)界,主要用于矩陣運算,同時在數(shù)值分析、自動控制模擬、數(shù)字信號處理、動態(tài)分析、繪圖等方面也具有強大的功能,他本身除了具有強大的圖形繪制和輸出功能,同時還發(fā)布了圖像、小波、神經(jīng)元網(wǎng)絡(luò)等大量的工具箱,大大的方便了我們的解決問題的工作。64.2 技術(shù)路線提出課題 緒論研究現(xiàn)狀圖像處理BP 網(wǎng)絡(luò)模型理論基礎(chǔ)研究分析車型識別Matlab 系統(tǒng)軟件汽車圖像的獲取及格式轉(zhuǎn)換系統(tǒng)算法程序確定圖像獲取及數(shù)字處理74.3 可行性分析自己查詢編寫 Matlab 軟件的編碼，經(jīng)過自己查閱資料、進行文獻調(diào)研，實現(xiàn)對至少 4 種車型的識別，已經(jīng)對這項課題有了大致了解。另外，在有導師的指導，完成這項課題是完全可行的。4.4 關(guān)鍵技術(shù)介紹4.41 數(shù)字圖像處理圖像處理是為了某種目的對圖像的強度(灰度)分布做某些特殊的加工和分析,主要分為兩大類,一是光學處理,一是數(shù)字圖像處理。本文主要設(shè)計數(shù)字圖像處理系統(tǒng)。所謂數(shù)字圖像處理,就是利用數(shù)字計算機或其他數(shù)字硬件,對圖像進行加工和分析,以期提高圖像的實用性,達到人們要求的某些預期效果。就其處理目的來講一般分為三大類,一類是增強有用信息,抑制無用信息,使圖像視覺質(zhì)量提高,以便于計算機對其做進一步的處理;一類是提取、描述、分析圖像所包含的某些特征或特殊的信息,以便計算機對圖像做進一步的分析和理解,經(jīng)常作為模式識別、計算機視覺等的預處理;另一類是圖像數(shù)據(jù)的壓縮,以便于圖象數(shù)據(jù)的存取和傳輸。4.42 Matlab 軟件MATLAB 將數(shù)值分析、矩陣運算、編程技術(shù)、圖形處理結(jié)合在一起，為用戶提供了一個強有力的科學及工程問題的分析計算和程序設(shè)計工具，它還提供了方案設(shè)計夾裝結(jié)構(gòu)特征提取車型的識別總結(jié)實例測試研究結(jié)果及后續(xù)改進測試結(jié)果分析8專業(yè)水平的文字處理、符號計算、實時控制和可視化建模仿真等功能，是具有多種語言功能和特征的新一代軟件開發(fā)平臺。 MATLAB 已發(fā)展成為適合多種工作平臺，眾多學科、功能強大的大型軟件。在歐美等國家的高校，MATLAB 已成為線性代數(shù)、數(shù)字信號處理、數(shù)理統(tǒng)計、時間序列分析、動態(tài)系統(tǒng)仿真等高級課程的基本教學工具。成為相關(guān)專業(yè)學生必須掌握的基本技能。在設(shè)計研究單位和工業(yè)開發(fā)部門，MATLAB 被廣泛的應用于研究和解決各種具體問題。在中國，MATLAB 也已開始日益受到重視，因為無論哪個學科或工程領(lǐng)域都可以從 MATLAB 中找到合適的功能。 Matlab 有以下優(yōu)點：（1）編程效率高，比 C 語言等更加接近我們思維習慣和書寫習慣；（2）方便使用，在編程和調(diào)試過程中它是一種比 VB 還要簡單的語言；（3）較強的擴充力，有豐富的庫函數(shù)，一些復雜的數(shù)學運算可以直接調(diào)用；（4）語言簡單，內(nèi)涵豐富，（5）高效方便的矩陣和數(shù)組運算。Matlab軟件有非常友好的編譯環(huán)境，并且進行編譯的語言也很簡單，容易應用，在數(shù)據(jù)和圖片這方面也有相當大的處理能力。由于 Matlab 軟件的簡單方便化，它在各個方面也有很多的應用，尤其是在模塊集合工具箱方面的應用更為廣泛。4.43 特征選取方法特征的提取方法要考慮到車輛特征的具體情況，不能只從理論角度思考，通過對車型圖像的參數(shù)提取或變換，得到一組能真正反映車輛信息的特征值。特征值有兩種提取方法，一種是根據(jù)某些原理進行特征提取，比如把同一識別對象在不同波段的攝像得到的灰度作為它的特征，這種應用在農(nóng)田估產(chǎn)、森林資源調(diào)查中廣泛應用。另一種就是要求對待識別的圖像的各種特征都充分理解，然后把這種特征轉(zhuǎn)化為文字或數(shù)值來識別。 對于車型的特征提取，從技術(shù)角度來說，所能提取的特征信息越多，就越能詳細準確的分類車型，但是從使用角度來說，為了能夠快速識別車型，特征參數(shù)就不能太多，而且一些冗余特征信息也會影響車型識別的準確度。為了能準確快速的識別車型，所提取的特征值必須具有代表性和較小的冗余度，同時還有滿足不同條件下，特征值的穩(wěn)定性?；谝陨弦?，特征值選取要滿足以下三個特點： 第一，區(qū)別性，不同的車型其特征值有較明顯的差異。 第二，相似性，對于相同的車型其特征值都會比較接近。第三，簡單性，特征值個數(shù)越多，車型識別系統(tǒng)就會越復雜，因此特征值的選取要盡可能少。 以上提出的三個特點，區(qū)別性是基本的特點，是特征值選取的關(guān)鍵，相似性則是為了保證識別的準確率，簡單性是為了保證車型識別的速度。95 日程安排序號 設(shè)計（論文）各階段名稱 日期 備注1 調(diào)研、開題報告準備及撰寫 12 月 22 日~1 月 15日2 外文翻譯 2 月 22 日~2 月 28日3 以 matlab 為工具實現(xiàn)汽車類型表情特征提取及自動識別3 月 1 日~4 月 15 日4 實例測試與分析 4 月 16 日~4 月 30日5 撰寫論文及答辯 5 月 1 日~5 月 31 日6 參考文獻10[1]Total Course Highway of Domastic Has Amounted to 45,400 Kilometers[N].Guangming Daily,2006-12-10:4.[2]Hontani H.Koga T.Character Extraction Method Without Prior Knowledge on Size and Position Information.Vehicle[C]//ElectronicsConference,2001.Proceedings of the IEEE International,2001:67.[3]Pun T.Entropic Thresholding.A New Approach[J].Computer Vision,Graphics Image Process,2001,16:210.[4]CUI Yi.Imagery Processing and Analysis-mathematics Morphology M ethod and Application[M].Beijing:The Science Press,2002.[5]CUI Jiang.Research on the Image Recognition Technique for MovingVehicles[D].Nanjing:Nanjing University of Aeronautics and Astronautics, 2003.[6]LI Jin-hui,Lou Wei,JIANG Shou-shan.A Study on Road Surface Defects Detecting Technology with CCDCamera[ J].Journal of Xi'an Institute of Technology,2002,22(2):95.[7]YU Hong-jun.Research on the Recognition of the Vehicle Style and Recognition of the Vehicle Plate [D] . Xi'an: Highway College of Chang' an University,2005.[8].李晉秀，趙建濤.一種圖像處理的汽車類型識別算法[J].西安工業(yè)大學學報，2009,29(3):275-278[9].王振峰.圖像處理技術(shù)在汽車類型自動識別中的應用研究[D].中國農(nóng)業(yè)大學碩士學位論文，2000.[10]. 馬寧.基于神經(jīng)網(wǎng)絡(luò)的汽車識別研究[D].哈爾濱工程大學碩士學位論文，2002.[11]李介谷、施鵬飛、劉重慶、謝式絢編著,圖像處理技術(shù),上海交通大學出版社,上海,1988.[12]章毓晉,圖像處理和分析,清華大學出版社,1997.[13]徐建華編著,圖像處理與分析,科學出版社,1992.[14]吳維從編著,計算機圖像處理,上?？茖W技術(shù)出版社,1989.11[15]吳敏金著,圖像形態(tài)學,上海科學技術(shù)文獻出版社,1991.[16]吳健康編著,數(shù)字圖象分析,人民郵電出版社,1989.[17]劉榴娣,劉明奇,黨長民編著,實用數(shù)字圖像處理,北京理工大學出版社,1998.[18]沈庭芝,方子文編著,數(shù)字圖像處理及模式識別,北京理工大學出版社,1998.[19]潘祖善,何紹雄,賈學堂編,濾波技術(shù),上海交通大學出版社,1997.[20]沈清,湯霖編著,模式識別導論,國防科技大學出版社,1991.[21]薛東輝、朱耀庭、朱光喜、熊艷,分形方法用于有噪聲圖像邊緣檢測的研究,通信學報,1996,17(1):7-11.[22]陳凌、陳云霞,改進 Hnogh 變換及并行計算,電子學報,19%,24(10):111-114[23]李文彪、潘士先,弱正則化邊緣檢測,自動化學報,1996,22(5),545-553.[24]舒昌獻,莫玉龍,基于軟化形態(tài)學的邊緣檢測,中國圖象圖形學報,1999,2(4,2):141-142.[25]葉衍,張凌,曹明明,何久保,基于特征分布的圖象信息抽取,中國圖象圖形學報,1998,3(3,3):189 一 192.[26]奕新,朱鐵一,二次濾波法提取邊緣信息方法及其應用,青島海洋大學學報,1999,l,(29,l):107 一 110.[27]高雁飛,幾種 CCD 圖像邊緣的高精度檢測方法分析,西安工業(yè)學院學報,1998,6,(18,2):92 一 98.[28]張啟忠,楊紀春,羅志增,模糊邊緣檢測技術(shù)在機器人觸覺圖象處理中的應用,傳感器技術(shù),1998,(17,l)6 一 7〔川李應,唐增銘,宋新科,計算機視覺在汽車噸位辨識中的應用,福州大學學報,1998,12,(26,6)25 一 27.An Efficient Vehicle Model Recognition MethodHuihuaYangGuangxi Experiment Center of Information Science, Guilin, China Email: yanghuihua@tsinghua.edu.cnLei Zhai, Lingqiao Li, Zhenbing Liu, Yichen Luo, Yong WangSchool of Electronic Engineering and Automation/Guilin University of Electronic Technology, Guilin, China Email: keylei203@gmail.com, zbliu@guet.edu.cn, 54pe@163.com, louisluo@guet.edu.cn, wang@guet.edu.cnHaiyan Lai, Ming GuanGuangxi Communications Investment Group CO., LTD, Guilin, China 13517810019@163.com, gm9099@sina.comAbstract—An efficient vehicle model recognition method based on Adaptive Harris corner detector is presented in this paper. First, the vehicle radiator grid is selected as ROI and Harris corner detection is used to detect corner as vehicle model features, to solve a problem of inconsistencies in the number of corner between different models or the same model in different environment. Second, an adaptive threshold function is constructed to control the number of corner replacing a fixed threshold, ensuring that the image is always able to produce a certain number of strong corners. Third, a parallel scheme is designed to accelerate the vehicle recognition algorithm via GPU/CPU heterogeneous computing model to meet real-time requirement, which includes parallelization of algorithm and parallelization of process. The experiments on 1096 big truck images of 12 vehicle models obtain the recognition accuracy rate of 99.5%, and achieve 58x speedup on average by a platform with Intel Core i5 2400 and NVIDIA C2075. The results show that our proposed method can meet the requirements of practical application.Index Terms—vehicle model recognition; ROI positioning; adaptive Harris Algorithm; GPU/CPU collaborative computingI. INTRODUCTIONVehicle model recognition is an interesting and difficult subject of intelligent transportation study. In [1] and [2], features of corner point are utilized to achieve the coarse classification of cars, buses, heavy goods vehicles (HGVs) etc. In [3], an interesting approach for vehicle model recognition from frontal view vehicle images is presented, whose recognition accuracy achieves 93%. The vehicle manufacture and model were treated as a single class and recognized simultaneously, but no results for recognition speed were reported. In [4] and [5], a comparative knowledge acquisition system were introduced, consisting of several object recognition modules which represent a car image viewed from the rear, such as a window, tail lights, and so on, based on color recognition. This approach has the drawback ofbeing sensitive to lighting condition. In [6], a vehicle model recognition method was presented which was extracted of textural features of the radiator grille using based gray level co-occurrence matrix (GLCM), but ROI positioning is difficult in an outdoor environment. In [7], scale invariant feature transform (SIFT) features is proved to be suitable for vehicle manufacturer and model recognition, but it does not have real-time performance.In summary, the above model identification methods still can’t be a good solution to the actual vehicle recognition task in an outdoor environment. There are two main reasons:1. ROI Positioning and feature extraction are difficult in the complex outdoor environment.2. Recognition algorithm can’t meet the real-time requirement for practical applications.In the same time, GPU/CPU collaborative computing has become more and more important in data processing of computing-intensive tasks, and attracts the attention of many application developers in recent years [9][11,12]. This is because GPU can offer extensive resources even for non-visual, general-purpose computations: massive parallelism, high memory bandwidth, and general purpose instruction sets. GPU/CPU collaborative computing uses CPU to process sequence recognition tasks and uses GPU to process a large number of repetitive repeatabilitycalculations to improve the key performance of applications. GPU/CPU collaborative computing is widely used in the field of image processing [10]. To the best of our knowledge, there is no report about the application of this accelerated technology in the vehicle model recognition fields.This paper present a new vehicle model recognition based adaptive Harris corner detector. This is a part of the “JT-G green channel inspection system”, which uses vehicle model recognition technology based on machine vision to achieve the cab’s automatic detection and safe avoidance. First, radiator grid is positioned as ROI based on logo. Then, using the adaptive Harris corner detector to detect ROI’s corner, an adaptive threshold function is? 2013 ACADEMY PUBLISHER doi:10.4304/jsw.8.8.1952-1959? 2013 ACADEMY PUBLISHERconstructed to control the number of corner replace a fixed threshold. This method can ensure the image always produce a certain number of strong corner, avoiding dramatic changes of corner number between the different models, or the same model in different environment, thus it can greatly improve the recognition accuracy and robustness of the recognition.Output: The binary image after coarse location.Step: a. Suppress horizontal texture using operator [1,-1].Dx (i, j) ? g(i, j) ? g(i ? 1, j)b. Suppress vertical texture using operator[1,-1]T.D(i, j) ? Dx (i, j) ? Dx (i, j+1)c. Suppress noise.(1)(2)Besides, a parallelization scheme for vehicle model recognition is designed, including the parallelization of adaptive Harris algorithm and the parallelization of?1f (i, j) ? ??0D(i, j) ? 0D(i, j) ? 0workflow, to ensure that the algorithm has a fast response time and meet real-time requirement.i ? r j ? r sum(i, j) ? ?? f (i, j)i ?r j ?r (3)II. ROI POSITIONINGSelection and robust positioning of ROI in complexity field environment is difficult. In [6], the vehicle radiator grid as ROI completes a good vehicle recognition effect.?255pixel (i, j) ? ?? 0T = r ? r / 2 ? 1sum(i, j) ? T sum(i, j) ≤ TThis paper also uses this method, but adds logo’s information in order to increase ROI’s distinguishing degree, as shown in Fig. 1.Figure 1. ROI selection of vehicle model recognitionThe ROI is positioned based on logo’s position. The position of the number plate region is steady-going and fixed in size. If the number plate can be fast and coarse detected, it can also be obtained the vehicle logo position in the vertical direction. The relationship between the number plate and the vehicle logo is as shown in Fig. 2. General logo is always at right above the license plate’ position, we only need to detect logo in the vertical direction or position and the large white rectangle image is as the input image.Figure 2. Through the license plate to determine the approximate location of logoTo position ROI, logo vertical position is needed to determine. Algorithm 1 describes the process of vertical position location for vehicle logo.Algorithm1: Location for logo’s vertical position.Input: Grayscale image of extracted based on plate.Where r is kernel’s size, T is adaptive threshold.d. The edge extraction: detect edge using Canny operator, the output is pixel*.e. Obtaining the row that its pixel values is maximum as the horizontal axis.ROI positioning for logo vertical position is shown in Fig. 3. Where h is plate’s height, w is plate’s width, y is vertical position of logo, n is an empirical parameter.(a) Coarse location based on plate(b) Location of logo vertical position(c) Location of ROI based on logo Figure 3. Location of ROI? 2013 ACADEMY PUBLISHERIII. ADAPTIVE HARRIS ALGORITHMA. HarrisCorner is known as interesting points in the image. They are discrete, reliable and meaningful. Feature-corner is shown to perform with good consistency on natural imagery, this paper selects corner as characteristic of vehicle’s model.There are many corner detectors, such as Harris, Fast, SIFT, SURF and so on. Fig. 4 is a corner-image detected by Harris, SURF and SIFT respectively.(a) Harris (b) SURF (c) SIFT Figure 4. Corner-image detected by three detectorsAs shown in Fig.4, Harris corner detector has the best results in the view of the positioning accuracy of corner. Since Harris corner detector is based on first order Hessian matrix, so it has higher detection accuracy. SIFT or SURF is based on High-dimensional scale space, and has higher dimensional feature vectors, robustness better than Harris. Because only information of corner’s position is used in the process of matching, we selected Harris corner detector as this paper’s detector.B. Harris corner detectorHarris corner detection is a classic corner detection algorithm proposed by Harris C and Davis L S.A in 1988. It is a signal-based feature-corner extraction operator, assuming window W as processed image, the minute displacement (u, v) moving in any direction, then the gradation change amount can be defined as (4):E(u, v) ? ? w(x, y)[I (x ? u, y ? v) ? I (x, y)]2x, y? Au2 ? 2Cuv ? Bv2C. Defects of classic Harris for vehicle model recognitionThe corner response value of R, R is more than a fixed threshold value T. It is considered that point is the corner point, otherwise it is not. Fixed threshold will have some problems in the model recognition.1. The differences of corner points’ counts between different vehicle model lead to mismatch. As shown in Fig. 6, vehicle A has little corner points, vehicle B has many corner points, A and C with the same models, A and B with the different models. The counts of corner points matched between A and B successfully more than those between A and C in this case, so we concluded that A and B have the same model, vehicle model recognition for A is failure.(a) A and B have 22 similar corner points(b) A and C have 20 similar corner points? A M ? ?? ?uC??v?M ?u v?T (4) Figure 6. Differences of corner points between different vehicle model lead to mismatchWhere ?C B? is a symmetrical autocorrelation matrix,A ? X 2 ? w , function.B ? Y 2 ? w , C ? ( XY ) ? w , w(x,y) is window 2. The differences of corner points’ counts in differentillumination condition lead to mismatch. As shown in Fig. 7, vehicle D and F have the same models in different illumination condition, vehicle D and E have differentHarris’s feature is defined as the maximum value of the local, and its response function is:CRF ? ?M ? K (traceM )2models in well-lighting condition. Because Harris corner detector’s adaptive character toward lighting is not well, the corner points’ count in well-lighting condition is large?M ? ?1?2tr(M ) ? ?1 ? ?2(5) more than that in poor lighting condition. The counts of corner points matched between D and E is successfully more than those between D and F in this case. So weAs is a constant set by experience, K is generallybetween 0.04-0.06. If a point’s CRF is more threshold T, is a corner. Harris corner detection operator need to set the parameters K and T. The parameter selection arbitrariness will affect the final test results significantly. Algorithm process is as shown in Fig. 5.concluded that D and E have the same model, vehicle model recognition for D is failure.Figure 5. Processing steps for Harris corner detector? 2013 ACADEMY PUBLISHERw h0?(a) D and E have 14 similar corner points(b) D and F have 11 similar corner pointsFigure 7. The differences of corner points in different illumination condition model lead to mismatchAs shown in Fig.6 and 7, the classic Harris corner detector algorithm for vehicle model recognition effect is not good. The key reason is that the number of corner points is difficult to control. There is a large gap of the number of corner points between detected in the different models or in different environments, so it often leads a mismatch.D. Adaptive Harris AlgorithmCorner points’ count caused by the fixed threshold number of inconsistencies affect the recognition accuracy of the models. Corner threshold should be related to the overall distribution of the response value and the change range. So we take the mean of responses and the variation range weighted sum as a final adaptive threshold, Specific (6):threshold ? 1 (?? f (x, y)) ? ? *[max( f (x, y)) ? min( f (x, y))]w ? h x?1 y ?1(a) 60 corner points by hand(b) Fixed threshold(c) Adaptive thresholdFigure 8. Comparison-image using fixed threshold and adaptive thresholdAfter the calculation of the (6), corner points’ count in different models tends to be consistent in different environment, but not entirely. Sorting corner’s response value is executed in order to improve accuracy:1. Sorting corner by their response value. Strong-corner front, weak-corner behind.2. Setting a fixed parameter n, it indicates the desired output number of corner points . It is usually less than the expected minimum number of corner.Adaptive Harris algorithm process is shown in Fig. 9.f (x, y) ? ?r(x, y) r(x, y) ? t? r(x, y) ?? tr(x, y) ? ?(M )tr(M )2 (6)Where r(x, y) represents coordinate (x, y)’s response values. tpresets a small empirical threshold.The adaptive threshold is decided by mean value and change range of candidate corner, which reflects variation in the intensity of the image as a whole. If a certain vehicle model has single texture detail or in poor lighting conditions, the gradient of the image is small, the relatively response value is low, the adaptive threshold is also reduced, and still be able to ensure that the angle of the output of a certain number of points. In contrast, the adaptive threshold is also high, and it can limited excessive corner.As shown in Fig.8, figure corner points’ count is 60 points. Fig. 8(b) is corner-image using fixed threshold and Fig.8(c) is corner-image using (3). We can see that adaptive Harris threshold has a higher accuracy. The adaptive threshold can avoid the setting of the threshold value, ensure the detection accuracy at the same time.Adaptive Harris algorithm avoids models and differences between model or environment affect recognition accuracy. As shown in Fig. 10 ( the same vehicles as Fig. 6 ), vehicle A, B and C all have 15 corner, vehicle A and B have 5 corner points and A and C have 13 corner points, we conclude A with C are more similar than A with B.Figure 9. Processing steps of Adaptive Harris? 2013 ACADEMY PUBLISHER(a) D and E have 14 similar corner points(b) D and F have 11 similar corner points Figure 10. Model recognition for vehicle DAdaptive threshold can be guaranteed a certain amount of corner points to some extent by setting t and ? . The number of corner points impacts on the recognition accuracy of vehicle model. Few feature-corner generates a false match easily, more feature-corner increases amount of calculation. The perfect quantity is sufficient to reflect the characteristics of the models, but also to avoid the “false corner”. Fig. 11 is statistical analysis about vehicle model accuracy under different number of corner points detected by Harris, SURF and SIFT algorithm respectly. The results show that when the number of corner points in the range of 100-150 (t = 15, ? = 0.05) the recognition accuracy is relatively stable. When the corner points to 130, the Harris algorithm models achieve the highest recognition accuracy rate up to 99%.As shown in Fig. 12, using database matching to calculate the similarity of models’ image and the advantage is that the method is simple, maintain and upgrade easily. Its disadvantage is that the calculation is extraordinarily time consumption in the case of big database and can’t meet the real-time requirements.Figure 12. Processes of vehicle model recognition algorithmA. Parallelization of algorithmParallelization of algorithm includes parallel adaptive Harris algorithm and Max-correlation algorithm. These two algorithms are both compute-intensive, very suitable for parallel acceleration. Table I analysis of the processing flow of these two algorithms carefully, irrelevant loop and matrix operations are transmitted to GPU processing, transmission of signals and logic processing by CPU.Sample images are compressed to the size of 200? 200 in this paper. Every calculation of corner detectionand corner matching volume is not too large. In addition, the communication between the GPU and CPU overhead is large, and the speedup of parallel algorithm is not very high.TABLE I. PARALLELIZATION OF ADAPTIVE HARRIS11001050Harris SIFT SURF100095090085080050 100 150 200 250Feature-corner amoutFigure 11. Effect of the number of corner points on vehicle recognition accuracyIV. GPU/CPU COLLABORATIVE COMPUTINGThe proposed method for vehicle model recognition includes ROI positioning, corner detection and corner matching. The corner detection uses adaptive Harris algorithm, and corner matching uses the maximum correlation algorithm (Max-correlation).B. Parallelization of workflowFor the entire vehicle recognition method, due to corner detection in the whole process is called only once, the contribution of the acceleration to the entire model recognition is limited. Max-correlation algorithm is called every matching process, but the amount of calculation of the algorithm itself is small. So it is not the bottleneck of the whole method efficiency. Most of the recognition time consuming in the processing of data transmission, acceleration efficiency is not very high.Algorithm Step Parallelizable (Y/N)Adaptive Harris1.Grayscale Y2.Gradient Y3.Gaussian blur Y4 Correlation matrix Y5.Response Y6.Non-maximum suppression Y7.Adaptive threshold N9.Sorting corner NMax-correlation8. Calculating a correlation matrix Y9.Search match corner Y10. Calculating number of match corner Y1091/1096 Thecorrect amount? 2013 ACADEMY PUBLISHERImage of current vehicleDetect corner using Adaptive HarrisSince every corner matching process is independent, the matching of the different vehicle models can be parallelized. We select NVIDIA CUDA platform, used optimization techniques are as follows:1. Loading all features of datasets first, some constant as Gauss coefficients were loaded to constant registers of GPU.2. Setting the number of feature database as thread blocks, setting the number of corner as the number of threads in a thread block.Parallelization of workflow is realized in Fig. 13.Figure 13. Frame of parallel model for vehicle model recognitionV. EXPERIMENT RESULTS AND ANALYSISA. Data set description and experimental environmentThe datasets come from “JT-G green channel inspection system” on Guangxi “Quan-Yellow” high-speed toll station. Datasets include 6 categories logo, 12 vehicle models and 1096 front and side images with the speed of 3-20 km/h speed passing the equipment. Affected by the sensitivity of the sensor and the vehicle’s uniform speed, vehicle distance and angle may have a slight deviation. The samples also contain different lighting conditions such as sunny, cloudy, and evening. Experimental environment as following:1. PC: Intel Core i5-2400@3.10GHz x4, 4GB memory, win7 sp1 x64 operating system.2. GPU: NVIDIA Tesla C2075, CUDA v4.2.Figure 14. Green channel inspection system on the freewayB. Recognition AccuracyThe classic image “Lena” for corner detection is selected in order to verify the accuracy of the adaptive Harris algorithm based on GPU/CPU collaborative computing. The comparative results are shown in Fig. 15.We can see that the two corner-image are almost the same, which proves the accuracy of the algorithm. It is noteworthy that, these two corner-images are not same completely. That is because the inconsistencies of the floating calculation accuracy between CPU and GPU. It leads to the result of the calculation having a small deviation.(a) corner-image of CPU-Version algorithm(b) corner-image of GPU/CPU-Version algorithmFigure 15. Effect comparison of CPU-Version and GPU/CPU-version of the algorithmVehicle model recognition has many feature-extraction methods, this paper compared GLCM, PHash, DCT, SURF, SIFT and Harris, the results are shown in Table II.………………Matching Matching Matching ……… Matching corner N1 corner N2