• 
    

    
    

      99热精品在线国产_美女午夜性视频免费_国产精品国产高清国产av_av欧美777_自拍偷自拍亚洲精品老妇_亚洲熟女精品中文字幕_www日本黄色视频网_国产精品野战在线观看 ?

      基于RC-DBSCAN的車道線檢測(cè)研究

      2021-09-14 11:09:22鄧元望蒲宏韜華鑫斌孫彪
      關(guān)鍵詞:特征融合機(jī)器視覺(jué)卡爾曼濾波

      鄧元望 蒲宏韜 華鑫斌 孫彪

      摘? ?要:針對(duì)在復(fù)雜的工況下車道線檢測(cè)的魯棒性和實(shí)時(shí)性較差等問(wèn)題,本文通過(guò)融合邊緣檢測(cè)與多顏色空間閾值分割結(jié)果,進(jìn)行車道線特征點(diǎn)的提取. 結(jié)合車道線在鳥瞰圖中的位置特點(diǎn),提出了基于DBSCAN二次聚類(Reclustering based on Density-Based Spatial Clustering of Application with Noise,RC-DBSCAN)的特征點(diǎn)聚類算法. 并以簇點(diǎn)是否進(jìn)行二次聚類和Lab空間采樣簇點(diǎn)的平均灰度值為依據(jù),進(jìn)行車道線線型和顏色的識(shí)別. 使用最小二乘法對(duì)車道線進(jìn)行擬合,通過(guò)基于可信區(qū)域的卡爾曼濾波算法對(duì)擬合后的車道線進(jìn)行跟蹤. 最后在實(shí)際道路采集的視頻與公開(kāi)的數(shù)據(jù)集中進(jìn)行了實(shí)驗(yàn). 實(shí)驗(yàn)表明,本文算法在復(fù)雜路況下對(duì)車道線檢測(cè)的魯棒性優(yōu)于傳統(tǒng)聚類算法,實(shí)時(shí)性能夠滿足實(shí)際需求;在結(jié)構(gòu)化道路上,對(duì)車道線類型的識(shí)別也具有很高的準(zhǔn)確率.

      關(guān)鍵詞:機(jī)器視覺(jué);車道線檢測(cè);特征融合;密度聚類;車道線類型識(shí)別;卡爾曼濾波

      中圖分類號(hào):TP391.41;U463.6 ? ? ? ? ? ? ? 文獻(xiàn)標(biāo)志碼:A

      Research on Lane Detection Based On RC-DBSCAN

      DENG Yuanwang PU Hongtao HUA Xinbin SUN Biao

      (College of Mechanical and Vehicle Engineering,Hunan University,Changsha 410082,China)

      Absrtact:In view of the poor robustness and real-time performance of lane detection under complex working conditions,this paper extracts the feature points of lane line by fusing the results of edge detection and multi-color space threshold segmentation. Combined with the location characteristics of lane line in aerial view,a feature point reclustering algorithm based on RC-DBSCAN (Reclustering based on Density-Based Spatial Clustering of Application with Noise) is proposed. Based on whether the cluster points are clustered twice or not and the average gray value of the cluster points sampled in Lab space,the lane line shape and color are identified. The lane line is fitted by the least square method,and the fitted lane line is tracked by the Kalman filter algorithm based on the trusted region. Finally,the experiment is carried out in the real road video and public data set. Experimental results show that the robustness of the proposed algorithm is better than the traditional clustering algorithm in complex road conditions,and the real-time performance can meet the actual needs;on the structured road,the recognition of lane type also has? high accuracy.

      Key words:machine vision;lane detection;feature fusion;density clustering;lane type recognition;Kalman filter

      車道線檢測(cè)是輔助駕駛感知系統(tǒng)最重要的功能之一,提高車道線檢測(cè)的準(zhǔn)確性,將有利于保障智能汽車的安全行駛和駕駛員的人身安全[1].

      目前,常見(jiàn)的車道線檢測(cè)算法主要有基于特征檢測(cè)、基于模型的檢測(cè)和基于深度學(xué)習(xí)的檢測(cè). 基于特征的檢測(cè)主要的特征包括了邊緣、紋理特征和顏色特征等[2-3]. 王家恩等提出了基于車道線寬度和邊緣點(diǎn)數(shù)量統(tǒng)計(jì)的邊緣檢測(cè)算法,能有效抑制噪聲的產(chǎn)生[4]. Chen 等通過(guò)Sobel算子進(jìn)行邊緣檢測(cè),并將圖片轉(zhuǎn)換到HSV空間,進(jìn)行顏色特征的車道線特征提取[5]. 文獻(xiàn)[6]通過(guò)結(jié)合遠(yuǎn)視場(chǎng)LSD直線檢測(cè)和遠(yuǎn)視場(chǎng)的雙曲線模型匹配對(duì)車道線進(jìn)行擬合,取得了較好的效果. Wang等利用密度聚類DBSCAN算法動(dòng)態(tài)確定鄰域參數(shù)實(shí)現(xiàn)對(duì)車道線的提取,并使用拋物線模型對(duì)車道線進(jìn)行擬合[7]. Ajaykumar 等使用K-means聚類算法對(duì)概率霍夫變換后的線段進(jìn)行聚類,并利用輪廓系數(shù)確定最佳的聚類簇的數(shù)目,由于K-means算法的局限性,聚類效果容易受到影響[8]. He 等提出了基于點(diǎn)云卷積神經(jīng)網(wǎng)絡(luò)的車道線檢測(cè)算法,在光照變化等復(fù)雜情況下,大大提高了檢測(cè)精度[9]. Neven等將車道線檢測(cè)問(wèn)題轉(zhuǎn)化為實(shí)例分割問(wèn)題,利用LaneNet網(wǎng)絡(luò)獲取每條車道線的像素級(jí)分割,從而提高了檢測(cè)精度[10].

      在車道線的跟蹤領(lǐng)域,常見(jiàn)的跟蹤算法可以分為基于模型參數(shù)的跟蹤和基于感興趣區(qū)域的跟蹤.? Lee等通過(guò)上一幀圖像車道線的位置信息,動(dòng)態(tài)確定感興趣區(qū)域,在此區(qū)域內(nèi)對(duì)車道線進(jìn)行追蹤,具有很好的實(shí)時(shí)性[11]. Wu 等利用卡爾曼濾波器對(duì)直線兩端坐標(biāo)參數(shù)進(jìn)行跟蹤,從而實(shí)現(xiàn)了對(duì)車道線的跟蹤[12].

      針對(duì)相關(guān)文獻(xiàn)存在的魯棒性、準(zhǔn)確性與實(shí)時(shí)性無(wú)法有效兼顧的問(wèn)題,為了在滿足實(shí)時(shí)性的同時(shí),更準(zhǔn)確、全面地提取車道線信息,本文提出基于RC-DBSCAN的車道線檢測(cè)跟蹤與類型識(shí)別算法.

      1? ?算法流程

      本文在圖像預(yù)處理部分,通過(guò)逆透視變換和對(duì)應(yīng)點(diǎn)提取車道線感興趣區(qū)域(Region of Interest,ROI),將Sobel算子邊緣檢測(cè)結(jié)果和基于顏色空間HSL和Lab 的最大類間方差法(OTSU)二值化結(jié)果進(jìn)行數(shù)據(jù)融合,提取出車道線的邊緣特征點(diǎn);采用RC-DBSCAN算法對(duì)特征點(diǎn)進(jìn)行聚類;通過(guò)圖像直方圖峰值位置與簇點(diǎn)的質(zhì)心位置排除路面干擾,并使用最小二乘法對(duì)車道線進(jìn)行擬合;同時(shí)通過(guò)簇是否二次聚類和Lab顏色空間中的簇點(diǎn)的顏色值對(duì)車道線類別進(jìn)行判定;最后通過(guò)卡爾曼濾波對(duì)車道線進(jìn)行跟蹤,并劃定可信區(qū)域?qū)柭鼮V波的追蹤結(jié)果進(jìn)行判定和優(yōu)化. 總體算法流程如圖1所示.

      2? ?圖像預(yù)處理

      2.1? ?圖片初處理

      攝像頭采集到的圖片可分為三個(gè)區(qū)域:天空背景區(qū)域,車道線區(qū)域,車道線外背景區(qū)域. 為了排除背景干擾,根據(jù)R、G、B通道的值進(jìn)行灰度化處理,灰度Gray的計(jì)算式如下:

      Gray = 0.299×R + 0.587×G + 0.114×B? ? (1)

      根據(jù)自車道范圍,劃定圖片的感興趣區(qū)域,本文選取圖片下方2/5左右的區(qū)域中的自車道線附近區(qū)域作為感興趣區(qū)域. 對(duì)圖像進(jìn)行基于對(duì)應(yīng)點(diǎn)的逆透視變換處理[13],得到車道線的鳥瞰圖. 圖2(a)為攝像頭采集的某車道線原圖,(b)為ROI區(qū)域的逆透視變換圖.

      2.2? ?基于Sobel算子的車道線邊緣提取

      利用Sobel算子通過(guò)模板,在x(水平),y(垂直)方向?qū)D片進(jìn)行卷積操作,通過(guò)對(duì)遍歷點(diǎn)進(jìn)行領(lǐng)域處理,達(dá)到提取邊緣特征的效果,見(jiàn)圖3.

      2.3? ?基于HSL和Lab顏色空間的特征提取與融合

      3? ?基于RC-DBSCAN的車道線提取

      3.1? ?RC-DBSCAN算法

      3.2? ?RC-DBSCAN與DBSCAN的檢測(cè)效果對(duì)比

      3.3? ?車道線簇的提取與擬合

      4? ?結(jié)構(gòu)化道路的車道線類型識(shí)別

      5? ?基于卡爾曼濾波的車道線跟蹤

      6? ?實(shí)驗(yàn)與分析

      6.1? ?車道線檢測(cè)

      6.2? ?車道線類型識(shí)別

      7? ?結(jié)? ?論

      在車輛行駛的復(fù)雜工況下,車道線的提取存在魯棒性和實(shí)時(shí)性不高的問(wèn)題,本文在邊緣特征與顏色空間特征提取的基礎(chǔ)上,提出了RC-DBSCAN聚類算法和車道線類型識(shí)別算法,結(jié)合卡爾曼濾波,在彎道、路面干擾、隧道等復(fù)雜工況下進(jìn)行了實(shí)車實(shí)驗(yàn). 結(jié)果表明,RC-DBSCAN算法相比于傳統(tǒng)的聚類算法具有更好的魯棒性和實(shí)時(shí)性,在復(fù)雜工況下的車道線檢測(cè)準(zhǔn)確性可達(dá)95%,對(duì)于分辨率為1 920 ×1 080的圖片,每幀耗時(shí)平均約79 ms,具有較好的實(shí)時(shí)性,在結(jié)構(gòu)化道路上,車道線類型識(shí)別的準(zhǔn)確率達(dá)98%.

      參考文獻(xiàn)

      [1]? ? HU L,OU J,HUANG J,et al. A review of research on traffic conflicts based on intelligent vehicles[J]. IEEE Access,2020,8:24471—24483.

      [2]? ? YOO J H,LEE S W,PARK S K,et al. A robust lane detection method based on vanishing point estimation using the relevance of line segments[J]. IEEE Transactions on Intelligent Transportation Systems,2017,18(12):3254—3266.

      [3]? ? PIAO J,SHIN H. Robust hypothesis generation method using binary blob analysis for multi-lane detection[J]. IET Image Processing,2017,11(12):1210—1218.

      [4]? ? 王家恩,陳無(wú)畏,汪明磊,等. 車輛輔助駕駛系統(tǒng)中的三車道檢測(cè)算法[J]. 汽車工程,2014,36(11):1378—1385.? ?WANG J E,CHEN W W,WANG M L,et al.. A three-lane detection algorithm for vehicle assistant driving system[J]. Automotive Engineering,2014,36(11):1378—1385. (In Chinese)

      [5]? ? CHEN C,WANG J,CHANG H,et al. Lane detection of multi-visual-features fusion based on DS theory[C]//Proceedings of the 30th Chinese Control Conference. Yantai,China:IEEE,2011:3047—3052.

      [6]? ? 曲峰. 基于視覺(jué)的結(jié)構(gòu)化道路及障礙物檢測(cè)技術(shù)研究[D].長(zhǎng)春:吉林大學(xué),2019:24—33.QU F. Research on technologies of vision-based structured road and obstacle detection[D]. Changchun:Jilin University,2019:24—33.(In Chinese)

      [7]? ? WANG J T,HONG W,GONG L. Lane detection algorithm based? on density clustering and RANSAC[C]//2018 Chinese? Control? And Decision Conference (CCDC). Shenyang,China:IEEE,2018:919—924.

      [8]? ? AJAYKUMAR R,GUPTA A,MERCHANT P S N. Automated lane detection by K-means clustering:a machine learning approach[J]. Electronic Imaging,2016,2016(14):1—6.

      [9]? ? HE B,AI R,YAN Y,et al. Lane marking detection based on convolution neural network from point clouds[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). Rio de Janeiro,Brazil :IEEE,2016:2475—2480.

      [10]? NEVEN D,DE BRABANDERE B,GEORGOULIS S,et al. Towards end-to-end lane detection:an instance segmentation approach[C]//2018 IEEE intelligent vehicles symposium (IV). Changshu,China :IEEE,2018:286—291.

      [11]? LEE C,MOON J H. Robust lane detection and tracking for real-time applications[J]. IEEE Transactions on Intelligent Transportation Systems,2018,19(12):4043—4048.

      [12]? WU P C,CHANG C Y,LIN C H. Lane-mark extraction for automobiles under complex conditions[J]. Pattern Recognition,2014,47(8):2756—2767.

      [13]? ALY M. Real time detection of lane markers in urban streets[C]//2008 IEEE Intelligent Vehicles Symposium. Eindhoven,Netherlands :IEEE,2008:7—12.

      [14]? LIU D,WANG Y,CHEN T,et al. Application of color filter adjustment and K-means clustering method in lane detection for self-driving cars[C]//2019 Third IEEE International Conference on Robotic Computing (IRC). Naples,Italy:IEEE,2019:153—158.

      [15]? 覃雄臻,魯若宇,陳立明,等. 多場(chǎng)景車道線檢測(cè)與偏離預(yù)警方法研究[J]. 機(jī)械科學(xué)與技術(shù),2020,39(9):1439—1449.QIN X Z,LU R Y,CHEN L M,et al. Research on multi-scene lane line detection and deviation warning method[J]. Mechanical Science and Technology for Aerospace Engineering,2020,39(9):1439—1449.(In Chinese)

      [16]? KHAN K,REHMAN S U,AZIZ K,et al. DBSCAN:Past,present and future[C]//The fifth international conference on the applications of digital information and web technologies (ICADIWT 2014). Bangalore,India:IEEE,2014:232—238.

      [17]? LI W,QU F,WANG Y,et al. A robust lane detection method based on hyperbolic model[J]. Soft Computing,2019,23(19):9161—9174.

      [18]? MUTHALAGU R,BOLIMERA A,KALAICHELVI V. Lane detection technique based on perspective transformation and histogram analysis for self-driving cars[J]. Computers & Electrical Engineering,2020,85:106653.

      [19]? 劉媛. 基于機(jī)器視覺(jué)的車道偏離預(yù)警系統(tǒng)關(guān)鍵算法研究[D].長(zhǎng)沙:湖南大學(xué),2013:47—51.?LIU Y. Research on key algorithms for vehicle lane departure warning system based on machine vision[D],Changsha:Hunan University,2013:47—51.(In Chinese)

      [20]? 陳濤,張洪丹,陳東,等. 基于優(yōu)先像素與卡爾曼濾波追蹤的車道線檢測(cè)[J]. 汽車工程,2016,38(2):200—205.CHEN T,ZHANG H D,CHEN D,et al. Lane detection based on high priority pixels and tracking by Kalman filte[J].Automotive Engineering,2016,38(2):200—205.

      [21]? LEE D K,SHIN J S,JUNG J H,et al. Real-time lane detection and tracking system using simple filter and Kalman filter[C]//2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN). Milan :IEEE,2017:275—277.

      [22]? 朱鴻宇,楊帆,高曉倩,等. 基于級(jí)聯(lián)霍夫變換的車道線快速檢測(cè)算法[J]. 計(jì)算機(jī)技術(shù)與發(fā)展,2021,31(1):88—93.ZHU H Y,YANG F,GAO X Q,et al. A fast lane detection algorithm based on cascade hough transform.computer technology and development,2021,31(1):88—93. (In Chinese)

      猜你喜歡
      特征融合機(jī)器視覺(jué)卡爾曼濾波
      基于遞推更新卡爾曼濾波的磁偶極子目標(biāo)跟蹤
      基于移動(dòng)端的樹(shù)木葉片識(shí)別方法的研究
      科技資訊(2017年11期)2017-06-09 18:28:13
      基于SIFT特征的港口內(nèi)艦船檢測(cè)方法
      融合整體與局部特征的車輛型號(hào)識(shí)別方法
      大場(chǎng)景三維激光掃描儀在研究生實(shí)踐教學(xué)培養(yǎng)中的應(yīng)用
      基于機(jī)器視覺(jué)的工件鋸片缺陷檢測(cè)系統(tǒng)設(shè)計(jì)
      軟件工程(2016年8期)2016-10-25 15:55:22
      基于機(jī)器視覺(jué)技術(shù)的動(dòng)態(tài)“白帶”常規(guī)檢測(cè)系統(tǒng)的開(kāi)發(fā)
      科技視界(2016年20期)2016-09-29 11:11:40
      機(jī)器視覺(jué)技術(shù)在煙支鋼印檢測(cè)中的應(yīng)用
      基于MATLAB的道路交通標(biāo)志識(shí)別
      基于模糊卡爾曼濾波算法的動(dòng)力電池SOC估計(jì)
      和田县| 称多县| 渑池县| 塘沽区| 双流县| 阿拉善盟| 伊吾县| 盐城市| 芷江| 南雄市| 玉龙| 屯门区| 南漳县| 泰安市| 鹰潭市| 孙吴县| 鄂托克前旗| 金塔县| 余庆县| 昌乐县| 木兰县| 辽源市| 进贤县| 杭锦旗| 阿勒泰市| 宾阳县| 长海县| 若羌县| 梁山县| 昌都县| 霞浦县| 保亭| 建始县| 明星| 遂平县| 竹北市| 老河口市| 兴安县| 辽阳县| 高州市| 湟中县|