本文選題：箭頭檢測 + L-junction��； 參考：《華中師范大學》2015年碩士論文

【摘要】：隨著智能汽車的發(fā)展,自動駕駛技術受到廣泛的關注,其中感知周圍環(huán)境和路面信息是自動駕駛技術關鍵的部分。路面箭頭標記作為自動駕駛系統(tǒng)感知信息的重要部分,實現(xiàn)對它的智能檢測和識別具有重要的意義。由于箭頭檢測過程中經(jīng)常受到箭頭標記自身磨損、外界多種非箭頭標記等因素的干擾,對它的檢測和識別往往不能達到滿意的效果。本文針對箭頭路面標記的檢測和識別進行了有效的研究。本文基于L-junction結構將路面上的箭頭標記用多個L-junction構成的L-junction鏈描述,使干擾因素對檢測的影響轉化為L-junction偏差。然后提出了三種編碼方法將L-junction鏈編碼為字符串,將一定偏差范圍內的L-junction編碼為同一個字符碼,提高檢測模型對磨損箭頭標記的包容性；同時運用箭頭標記上L-junction的角度和拓撲關系對檢測標記設置條件,排除非箭頭標記的干擾。為了判斷檢測標記是否為箭頭標記,本文提出了權重編輯距離算法。該算法對檢測標記不同的偏差賦予不同的權重,實現(xiàn)檢測標記編碼字符串與標準箭頭標記編碼字符串之間的相似性的計算,提高檢測模型檢測準確率。為了測試該模型的檢測效果,在北京五環(huán)高速公路上收集了三個路面圖像集：清晰箭頭標記圖像集、磨損箭頭標記圖像集、視頻圖像集。采用本文的檢測模型分別檢測三個圖像集中的圖像,并統(tǒng)計檢測的準確率和召回率。為了更綜合地衡量本文模型的檢測效果,本文還運用了深度學習模型:Boosting Convolutional Deep Neural Network (CDNN)來對這三個圖像集進行檢測。大量的檢測結果顯示,本文的檢測模型性能較穩(wěn)定,取得較高的準確率和召回率。
[Abstract]:With the development of intelligent vehicles, self-driving technology has been paid more and more attention, in which sensing the surrounding environment and road information is the key part of autopilot technology. As an important part of the sensing information of autopilot system, road arrow marking is of great significance to its intelligent detection and recognition. The detection and recognition of arrowhead are often not satisfactory due to the wear and tear of arrowhead markers and many outside factors such as non-arrowhead markers in the process of arrow detection. In this paper, the detection and recognition of arrowhead road markings are studied effectively. Based on the L-junction structure, the arrowhead marks on the road surface are described with L-junction chains composed of multiple L-junction, so that the influence of the interference factors on the detection is transformed into the L-junction deviation. Then three coding methods are proposed to encode the L-junction chain as a string and the L-junction in a certain range of deviations as the same character code to improve the tolerance of the detection model to the frayed arrow marks. At the same time, the angle and topological relation of L-junction on arrow mark are used to set the condition of detection mark, and the interference of non-arrow mark is eliminated. In order to determine whether the detection marks are arrow marks, this paper proposes a weighted edit distance algorithm. The algorithm gives different weights to the different deviations of the detection marks, realizes the calculation of the similarity between the detection tag encoding strings and the standard arrow tag coding strings, and improves the detection accuracy of the detection model. In order to test the effectiveness of the model, three road image sets were collected on Beijing Wuhuan Expressway: clear arrow marking image set, wear arrow marking image set and video image set. The detection model of this paper is used to detect the images of three image sets, and the accuracy and recall rate of the detection are calculated. In order to measure the effectiveness of our model more synthetically, we also use the depth learning model: boosting Convolutional Deep Neural Network to detect these three image sets. A large number of test results show that the performance of the detection model is stable, and high accuracy and recall rate are obtained.
【學位授予單位】：華中師范大學
【學位級別】：碩士
【學位授予年份】：2015
【分類號】：U463.6;U495;TP391.41

【相似文獻】

相關期刊論文 前10條

1 王莉娟;詹峰;俞穎;朱巖;劉少卿;黃社松;倪海橋;牛智川;;Influence of window layer thickness on double layer antireflection coating for triple junction solar cells[J];半導體學報;2011年06期

2 代盼;陸書龍;季蓮;何巍;邊歷峰;楊輝;有持佑之;吉田浩;內田史朗;池田昌夫;;A GaAs/GaInP dual junction solar cell grown by molecular beam epitaxy[J];Journal of Semiconductors;2013年10期

3 ;Effect of junction potential on the EMF of bielectrolyte solid-state sensors[J];Journal of University of Science and Technology Beijing(English Edition);2005年01期

4 高欣;楊生勝;薛玉雄;李凱;李丹明;王瀊;王云飛;馮展祖;;Effects of electron radiation on shielded space triple-junction GaAs solar cells[J];Chinese Physics B;2009年11期

5 肖文波;何興道;高益慶;張志敏;劉江濤;;Far-infrared electroluminescence characteristics of an InGaP/InGaAs/Ge triple-junction solar cell under forward DC bias[J];半導體學報;2012年06期

6 YU ZhiBin;LI Lu;GAO HuiEr;PEI QiBing;;Polymer light-emitting electrochemical cells:Recent developments to stabilize the p-i-n junction and explore novel device applications[J];Science China(Chemistry);2013年08期

7 Li Xin;Wang Shaoping;;Flow field and pressure loss analysis of junction and its structure optimization of aircraft hydraulic pipe system[J];Chinese Journal of Aeronautics;2013年04期

8 XING YuPeng;HAN PeiDe;WANG Shuai;LIANG Peng;LOU ShiShu;ZHANG YuanBo;HU ShaoXu;ZHU HuiShi;MI YanHong;ZHAO ChunHua;;Analysis of effects of front and back surface dopants on silicon vertical multi-junction solar cell by 2D numerical simulation[J];Science China(Technological Sciences);2013年11期

9 屈曉聲;張思思;包鴻音;熊麗玲;;The effect of InAs quantum-dot size and interdot distance on GaInP/GaAs/GaInAs/Ge multi-junction tandem solar cells[J];Journal of Semiconductors;2013年06期

10 Yoshio Ohshita;Hidetoshi Suzuki;Kenichi Nishimura;Masafumi Yamaguchi;;Recent Advances in High Efficiency Solar Cells[J];復旦學報(自然科學版);2007年05期

相關會議論文 前10條

1 楊園靜;;Investigation on PL performace of InAs quantum dotsfor Multi-junction GaAs solar cell[A];戰(zhàn)略性新興產業(yè)的培育和發(fā)展——首屆云南省科協(xié)學術年會論文集[C];2011年

2 ;Ongoing gap junction currents selectively revealed by elimination of transmembrane ion and voltage gradients in single inspiratory tracheal preganglionic vagal motoneurons:characteristics and the modulation by substance P[A];Proceedings of the 7th Biennial Meeting and the 5th Congress of the Chinese Society for Neuroscience[C];2007年

3 Yang LIU;Jie YANG;Zhi-yuan YU;Min-jie XIE;Wei WANG;;Effects of astrocytes gap junction communication regulation on neurovascular unit damage and repair in rats after cerebral ischemia[A];中國神經(jīng)科學學會第十屆全國學術會議論文摘要集[C];2013年

4 ;Adaptive Chaotic Synchronization of Hindmarsh-Rose Network with Gap-junction[A];中國自動化學會控制理論專業(yè)委員會C卷[C];2011年

5 Yasufumi Shigeyoshi;Seiichi Hashimoto;Masa-aki Hattori;;FSH induces development of circadian clockwork in rat granulosa cells via a gap junction protein Cx43 dependent pathway[A];生態(tài)環(huán)境與畜牧業(yè)可持續(xù)發(fā)展學術研討會暨中國畜牧獸醫(yī)學會2012年學術年會和第七屆全國畜牧獸醫(yī)青年科技工作者學術研討會會議論文集——T03環(huán)境與動物健康專題[C];2012年

6 CHEN Fan;WEI Zhinong;;Zigbee Based Temperature Monitoring System for Electric Cable Junction[A];proceedings of 2010 3rd International Conference on Computer and Electrical Engineering (ICCEE 2010 no.1)[C];2012年

7 PengFei Wang;ZongJie Cui;;Neuro-acinus junction configured for ACh induction of cytosolic calcium oscillations in rat sublingual acini[A];第八屆全國光生物學學術會議論文摘要集[C];2013年

8 Tooru TANAKA;Mitsuhiro NISHIO;;Epitaxial Growth and Characterization of AlInN Layers for Multi-Junction Tandem Solar Cells[A];第十屆中國太陽能光伏會議論文集：迎接光伏發(fā)電新時代[C];2008年

9 ;Recent Progress in Polymer Solar Cells at UCLA[A];全國第八屆有機固體電子過程暨華人有機光電功能材料學術討論會摘要集[C];2010年

10 ;Chaotic Synchronization of Two Coupled Neurons via Nonlinear Control[A];第二十四屆中國控制會議論文集（下冊）[C];2005年

相關碩士學位論文 前1條

1 梁美燕;基于L-junction特征的路面箭頭標記檢測和識別[D];華中師范大學;2015年

，

本文編號：1934609