跳到主要內容

臺灣博碩士論文加值系統

(3.236.110.106) 您好!臺灣時間:2021/07/25 07:57
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:許宴綱
研究生(外文):Yen-Kang Hsu
論文名稱:可程式化物件偵測快速演算法及其硬體實現
論文名稱(外文):Hardware Implementation of Programmable Fast Algorithm for Object Detection
指導教授:吳崇賓
口試委員:范志鵬陳春僥
口試日期:2015-07-22
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:中文
論文頁數:62
中文關鍵詞:物件偵測車輛偵測路牌偵測夜間
外文關鍵詞:Object DetectionVehcile DetectionRoad Sign DetectionNight time
相關次數:
  • 被引用被引用:0
  • 點閱點閱:80
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文整合車輛與路標號誌之偵測,同時利用前一畫面偵測結果之資訊以達減少運算量。在連續影像偵測時,本論文提出全畫面偵測(Full Detection)、部分範圍偵測(Partial Detection)及物件驗證(Object Verification)三種模式,全畫面偵模式針對整個畫面進行物件之偵測;部分範圍偵測模式則是根據前一張畫面之偵測結果座標重新設定偵測範圍,在該範圍內進行物件偵測;物件驗證模式是根據其他模式偵測結果,在偵測結果範圍內根據物件特徵進行驗證。整個演算法使用可程式化參數進行控制與限制,可依據車速等條件設定參數,使演算法具更高適應性及大幅降低物件偵測計算量約78%。
此外,針對夜間光線不足的環境,本論文亦提出夜間車輛偵測演算法。影像先透過亮度進行二值化後以顏色統計方塊作為特徵,利用車燈相似之特性偵測前方車輛,如此一來可補足演算法原本在夜間低亮度環境準確率較低的缺點。經過實驗在不同天氣環境中平均準確率約為89%。
為了達到即時系統之目的,本論文亦提出適用於FULL HD@30fps之硬體架構與實現。為移植至嵌入式平台,本論文將演算法設計硬體架構,完成並實現於Zynq-7000之FPGA上進行模擬,經合成後可在工作頻率為1.9MHz達到即時運算。


In this thesis, an algorithm integrated the vehicle and road sign detection is proposed. To further reduce the processing time, we proposed three different modes: full detection, partial detection and objet verification. For a series of input images, we detected all objects of the complete image in full detection mode. Based on the results of the previous frame, we set searching regions for detection in partial detection mode. No detection is applied in object verification that the objects are only verified based on the locations of detected objects in the previous frame. The algorithm is controlled by the programmable parameters that the detection condition can be easily changed. Overall, the proposed algorithm achieves 78% computation reduction.
To reduce the influence of low luminance, we proposed Night Time Vehicle Detection (NTVD). First, the input image is binarized by the threshold of brightness. The feature point of Color Count Block (CCB) is calculated to judge the similarity of rear lights for determining whether the objects are vehicles. NTVD improves the disadvantage of original detection algorithm and increases the accuracy at night. The experimental results show the average accuracy rate of object detection can exceed about 89% in different weather.
To reach the target of real-time processing, related hardware architecture is also presented for FULL HD@30fps by using algorithm design flow. Finally the proposed hardware is simulated at Zynq-7000 platform and work at 1.9 MHz to reach the real time requirement.


目錄 I
圖目錄 III
表目錄 V
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 3
1.3 論文架構 3
第二章 文獻探討 4
2.1 車輛偵測 4
2.1.1 日間情形 4
2.1.2 夜間情形 6
2.2 路標偵測 8
2.3 物件偵測 10
第三章 研究方法 11
3.1 演算法架構 11
3.2 物件偵測加速演算法(FAST ALGORITHM FOR OBJECT DETECTION) 13
3.2.1 車輛偵測 13
3.2.1.1 物件驗證(Object Verification, V) 14
3.2.1.2 部分範圍偵測(Partial Detection, P) 15
3.2.2 路牌號誌偵測 16
3.3 夜間車輛偵測(NIGHT TIME VEHICLE DETECTION) 18
3.3.1 顏色特徵擷取(Color Extraction) 19
3.3.2 特徵計數方塊化(Color Count Block) 20
3.3.3 後車燈匹配(Rear Light Matching) 22
3.4 參數設定 25
第四章 硬體架構設計與實作 28
4.1 演算法架構 28
4.2 顏色計數方塊(COLOR COUNT BLOCK, CCB) 29
4.2.1 系統硬體架構 29
4.2.2 處理程序 30
4.2.3 記憶體配置 30
4.3 後車燈匹配(REAR LIGHT MATCHING, RLM) 31
4.3.1 系統硬體架構 31
4.3.2 處理程序 32
第五章 實驗結果與討論 33
5.1 物件偵測快速演算法(FAOD ) 33
5.1.1 重設範圍特徵擷取 33
5.1.1.1 水平特徵擷取 33
5.1.1.2 顏色特徵擷取 35
5.1.1.3 路標號誌顏色擷取 36
5.1.2 重設範圍連續方塊決定 37
5.1.3 不同情形物件偵測結果 38
5.2 夜間車輛偵測(NTVD ) 44
5.2.1 後車燈選擇 44
5.2.2 夜間車輛偵測結果 46
5.3 演算法程式效能分析 50
5.3.1 日間物件偵測加速演算法運算量分析 50
5.3.1.1 車輛偵測運算量分析 50
5.3.1.2 路牌號誌偵測加速演算法運算量分析 51
5.3.2 準確率及效能分析 53
第六章 結論與未來工作 58
6.1 結論 58
6.2 未來工作 58
參考文獻 59


[1][Online]. Available:
http://www.npa.gov.tw/NPAGip/wSite/lp?ctNode=12595&nowPage=2&pagesize=15&mp=1
[2]T. Bucher, C. Curio, J. Edelbrunner, C. Igel, D. Kastrup, I. Leefken, G. Lorenz, A. Steinhage, and W. Vonseelen, “Image processing and behavior planning for intelligent vehicles,” IEEE Trans. Ind. Electron., vol. 50, no. 1, pp. 62-75, Feb. 2003.
[3]T. Schamm,; C. von Carlowitz, and J. M. Zoޠllner, “On-road vehicle detection during dusk and at night,” IEEE Intell. Veh. Symp., San Diego, CA, USA, pp. 418-423, 2010
[4]周許斌,“可程式化物件偵測與分類之硬體實現”,國立中興大學電機工程學系碩士論文,中華民國一百零三年七月
[5]R. O’Malley, E. Jones, and M. Glavin, “Rear-lamp vehicle detection and tracking in low-exposure color video for night conditions,” IEEE Trans. Intell. Transp. Syst., vol. 11, no. 2, pp. 453–462, Jun. 2010.
[6]Z. Sun, R. Miller, G. Bebis, and D. Dimeo,“A real-time precrash vehicle detection system,” in Proc. IEEE WACV, 2002, pp. 171-176.
[7]A. Bensrhair, M. Bertozzi, A. Broggi, P. Miche, S. Mousset, and G. Toulminet, “A cooperative approach to vision-based vehicle detection,” in Proc. IEEE ITS, Aug. 2001, pp. 207-212.
[8]A. Kuehnle, “Symmetry-based recognition of vehicle rears,” Pattern recognition letters, vol. 12, no. 4, pp. 249-258, Apr. 1991.
[9]T. Zielke, M. Brauckman, and W. Vonseelen, “Intensity and edge-based symmetry detection with an application to car-following,” CVGIP: Image Understanding, vol. 58, no. 2, pp. 177-190, Sep. 1993.
[10]W. Vonseelen, C. Curio, J. Gayko, U. Handmann, and T. Kalinke, “Scene analysis and organization of behavior in driver assistance systems,” in Proc. IEEE ICIP, vol. 3, Sep. 2000.
[11]S. D. Buluswar, and B. A. Draper, “Color machine vision for autonomous vehicles,” Eng. Appl. Artif. Intell., vol. 11, no. 2, pp. 245-256, Apr. 1998.
[12]D. Guo, T. Fraichard, X. Ming, and C. Laugier, “Color modeling by spherical influence field in sensing driving environment,” in Proc. IEEE IV, Oct. 2000, pp. 249-254.
[13]J. M. Collado, C. H. Hilario, A. de la Escalera, and J. M. Armingol, “Model based vehicle detection for intelligent vehicles,” in Proc. IEEE IV, Jun. 2004, pp. 572-577.
[14]V. Graefe, and E. Wolfgang, “A novel approach for the detection of vehicles on freeways by real-time vision,” in Proc. IEEE IV, Sep. 1996, pp.363-368
[15]C. Tzomakas, and W. VonSeelen, “Vehicle detection in traffic scenes using shadows,” in Proc. RUHR–UNIVERSITAT, 1998.
[16]S. Cheng, “Detection of Unstructured Road Boundary and Road Sign Recognition,” Master Thesis, Univ. of National Chung Cheng, Chiayi, Taiwan, 2003.
[17]T. Asakura, Y. Aoyagi, and O. K. Hirose,“ Real-time recognition of road traffic sign in moving scene image using new image filter,” in Proc. IEEE SICE, 2000, pp. 13-18.
[18]W. C. Huang, and C. H. Wu, “Adaptive color image processing and recognition for varying backgrounds and illumination conditions,” IEEE Trans. Ind. Electron., vol. 45, no. 2, pp. 351-357, Apr. 1998.
[19]L. Pacheco, J. Batlle, and X. Cufi, ”A new approach to real time traffic sign recognition based on colour information,” in Proc. IEEE IVS, Oct. 1994, pp. 339-344.
[20]S. Nagumo, H. Hasegawa, and N. Okamoto,“Extraction of forward vehicles by front-mounted camera using brightness information,”in Proc. IEEE CCECE, vol. 2, May. 2003, pp. 1243-1246.
[21]J. Miura, T. Kanda, and Y. Shirai, “An active vision system for real-Time traffic sign recognition,” in Proc. IEEE ITS, Oct. 2000, pp.52-57.
[22]S. Nagumo, H. Hasegawa, and N. Okamoto, “Extraction of forward vehicles by front-mounted camera using brightness information,” in Proc. IEEE CCECE, vol. 2, May. 2003, pp. 1243-1246.
[23]J. Miura, T. Kanda, and Y. Shirai, “An active vision system for real-Time traffic sign recognition,” in Proc. IEEE ITS, Oct. 2000, pp.52-57.
[24]G. Kim, and J.S. Cho, “Vision-based Vehicle Detection and Inter-Vehicle Distance Estimation,” in Proc. IEEE ICCAS, Oct. 2012, pp. 625-629.
[25]W.C. Chang, and C.W. Cho, “Online Boosting for vehicle detection,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 40, no. 3, pp. 892-902, Jun. 2010.
[26]W. K. Tsai, S. L. Wu, L. J. Lin, T. M. Chen, and M. H. Li, “Edge-based forward vehicle detection method for complex scenes,” ICCE-TW, 2014, pp. 173-174.
[27]Peixun, Liu, et al. “On-road multi-vehicle tracking algorithm based on an improved particle filter.” IET Intell. Transp. Sys., 2014, vol. 9. no.4, pp. 29-441.
[28][Online]. Available: http://www.cpubenchmark.net/cpu_list.php
[29]L. W. Tsai, J. W. Hsieh, C. H. Chuang, Y. J. Tseng, K. C. Fan, and C. C. Lee, “Road sign detection using eigen colour,” IET computer vision, vol. 2, no.3, pp. 164-177, Sep. 2012.
[30]R. Malik, S. Nazir and J. Khurshid, “Colour Based Road Sign Detection and Extraction from Still Images,” in Proc. IEEE CIS, Sep. 2010, pp. 1-6.
[31]W. Wu, X. Chen, J. Yang, “Detection of text on road signs from video,” IEEE Trans. Intell. Transp. Syst., vol. 6, no. 4, pp. 378-390, Dec. 2005.
[32]T. Moura, A. Tiago, et al. “Traffic Sign Recognition for Autonomous Driving Robot.” in Proc. IEEE ICARSC, 2014. pp. 303-308.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top