以動態視覺為基礎的前車停止啟動與俯瞰碰撞偵測

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：163

、訪客IP：13.59.87.145

姓名

藍易康(Lan-Yi Kang) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

以動態視覺為基礎的前車停止啟動與俯瞰碰撞偵測
(Stop-and-go and Top-view Obstacle Detection based on Dynamic Vision)

相關論文

★ 適用於大面積及場景轉換的視訊錯誤隱藏法	★ 虛擬觸覺系統中的力回饋修正與展現
★ 多頻譜衛星影像融合與紅外線影像合成	★ 腹腔鏡膽囊切除手術模擬系統
★ 飛行模擬系統中的動態載入式多重解析度地形模塑	★ 以凌波為基礎的多重解析度地形模塑與貼圖
★ 多重解析度光流分析與深度計算	★ 體積守恆的變形模塑應用於腹腔鏡手術模擬
★ 互動式多重解析度模型編輯技術	★ 以小波轉換為基礎的多重解析度邊線追蹤技術(Wavelet-based multiresolution edge tracking for edge detection)
★ 基於二次式誤差及屬性準則的多重解析度模塑	★ 以整數小波轉換及灰色理論為基礎的漸進式影像壓縮
★ 建立在動態載入多重解析度地形模塑的戰術模擬	★ 以多階分割的空間關係做人臉偵測與特徵擷取
★ 以小波轉換為基礎的影像浮水印與壓縮	★ 外觀守恆及視點相關的多重解析度模塑

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

在都市內行車有較多的不便與危險；在本研究中，我們針對以下兩種情況做安全偵測。第一種情況，在都市行駛車輛時會有不少的時間是在等待交通號誌的變換或是在走走停停的擁擠車陣中。在等待交通號誌或是塞車的這段時間，駕駛人可能會分心或做其他事情，若此時前方車輛已往前駛離或是停止，可能就會造成不便或碰撞。第二種情況則是車輛在都市中行駛有汽機車靠近，但車體的結構與後照鏡的角度會影響後視視野而導致有部份盲點且同時難以注意車輛週遭其餘區域的情況，使得駕駛無法全面顧及車輛週遭環境，如此就有可能發生擦撞。在本研究中，我們提出前車停止啟動偵測與俯瞰碰撞偵測的方法，可幫助駕駛者了解前車的動向及己車周遭移動物體之動向，在發生危險之前告知駕駛人，使駕駛更為方便及安全。在前車停止啟動偵測與俯瞰碰撞偵測的方法中，相同的部份都是先偵測角點，利用角點做光流向量的估計，得到動態資訊後，再各別做前車停止啟動偵測或俯瞰碰撞偵測。
在前車停止與啟動偵測方面，篩選光流向量並調整光流向量的大小，將同一物體之光流向量調整成為大小差不多的向量，接著利用此條件將向量分群得到移動區塊，再對移動區塊判斷前車是否啟動或停止，並能避免己車前方與側方各方向汽機車與行人之影響、夜間側後方來車大燈造成前方車亮度變化、夜間各種燈光造成的明暗變化、雨天之雨刷擺動、陰晴變化等因素所造成的誤判，給予駕駛人正確的警示。
在俯瞰碰撞偵測方面，我們先篩選適合的光流向量，再利用光流向量的方向、位置、及大小做分群，對分群得到的移動區塊分析其移動的軌跡及與己車碰撞的可能碰撞時間判斷是否要給予駕駛者警告。
前車停止啟動偵測與俯瞰碰撞偵測的方法在Intel? Pentium? Core2 Duo 1.86GHz及2GB RAM的個人電腦上執行，在前車停止啟動偵測可達每秒25至30張畫面，正確率可達99?；而在俯瞰碰撞偵測可達每秒25至30張畫面，正確率可達98?。

摘要(英)

It is inconvenience and danger while driving in urban areas. Drivers spend much time waiting for traffic signals and stuck in jams. Lack of concentration at such moments may lead to accidents. Due to the limitation of field of view, drivers are mostly unable to see all the area around the vehicle during driving. For the safety of drivers, the stop-and-go and top-view obstacle detection methods are proposed in this study. Corners are used as features to calculate optical flow. We perform stop-and-go and top-view obstacle detections based on the optical flow.
In the stop-and-go detection method, we first filter optical flow and adjust the length of optical flow. The length of optical flows of an object is almost the same. The adjusted length is used as the condition for clustering. Then, we use these moving objects to recognize whether the front vehicle is stopping or going. This detection method can also avoid the effects of vehicles in different direction, variant weather, and the light at nighttime.
In the top-view obstacle detection method, the direction, position, and length of optical flows are used as condition for clustering. By analyzing the trajectory of moving objects and computing the possible collision time, we can recognize whether the moving object is dangerous.
The proposed methods are evaluated in several variant environments. The detection rate of stop-and-go method is 99? and the frame rate is 25 frames per second. The detection rate of the top-view detection method is 98? and the frame rate is 30 frames per second.

關鍵字(中)

★ 前車啟動
★ 前車停止
★ 俯瞰碰撞偵測

關鍵字(英)

★ stop-and-go
★ Top-view

論文目次

摘要 ii
Abstract iii
誌謝 iv
目錄 v
圖目錄 vii
表目錄 xi
第一章緒論 1
1.1 研究動機 1
1.2 系統架構 2
1.3 論文架構 4
第二章相關研究 6
2.1 前車停止與啟動偵測 6
2.2 俯瞰偵測 9
2.3 角點偵測 12
2.4 光流向量估計 16
第三章特徵擷取與光流向量估計 21
3.1 角點偵測 21
3.2 計算光流向量 23
第四章前車停止啟動偵測 27
4.1 光流向量篩選與調整 27
4.1.1 光流向量篩選 28
4.1.2 光流向量調整 31
4.2 光流向量分群 36
4.2.1 以相鄰向量比較相似性為基礎的分群 36
4.2.2 簡單群聚搜尋方法分群 38
4.3 前車啟動停止判斷 39
4.3.1 以角度基礎的判斷方法 39
4.3.2 以調整後向量大小為基礎的判斷方法 41
第五章俯瞰碰撞偵測 43
5.1 光流向量篩選與分群 43
5.2 俯瞰碰撞偵測 44
5.2.1 固定範圍偵測 44
5.2.2 劃分區域偵測 45
第六章實驗結果 52
6.1 實驗環境 52
6.2 前車停止與啟動偵測結果 53
6.2.1 前車停止偵測 53
6.2.2 前車啟動偵測 61
6.2.3 分群方法結果比較 68
6.2.4 判斷準則方法結果比較 70
6.3俯瞰碰撞偵測結果 71
6.3.1 固定範圍偵測 71
6.3.2 劃分區域偵測 73
6.4實驗平台與效能 77
第七章結論與未來展望 79
7.1 結論 79
7.2 未來展望 80
參考文獻 81

參考文獻

[1] Bab-Hadiashar, A. and D. Suter, "Robust total least squares based optic flow computation," in Proc. Asian Conf. on Computer Vision, Hong Kong, China, Jan.8-10, 1998, pp.566-573.
[2] Batavia, P. H., D. A. Pomerleau, and C. E. Thorpe, "Overtaking vehicle detection using implicit optical flow," in Proc. IEEE Conf. on Intelligent Transportation System, Pittsburgh, PA, Nov.9-12, 1997, pp.729-734.
[3] Beaudet, P. R., "Rotationally invariant image operators," in Proc. 4th Int. Conf. on Pattern Recognition, Kyoto, Japan, Nov.7-10, 1978, pp.579-583.
[4] Bouguet, J. Y., Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of The Algorithm, Technique Report, Intel Corporation Microprocessor Research Labs., 2003.
[5] Deriche, R. and G. Giraudon, "Accurate corner detection: an analytical study," in Proc. 3rd Int. Conf. on Computer Vision, Osaka, Japan, Dec.4-7, 1990, pp.66-70.
[6] Duric, Z. and A. Rosenfeld, "Image sequence stabilization in real time," Real-time Imaging, vol.2, no.5, pp.271-284, 1996.
[7] Ehlgen, T. and T. Pajdla, “Monitoring surrounding areas of truck-trailer combinations,” in Proc. of 5th Int. Conf. on Computer Vision Systems, Bielefeld, Germany, Mar.21-24, 2007, CD-ROM.
[8] Ehlgen, T., M. Thorn, and M. Glaser, “Omnidirectional cameras as backing-up aid,” in Proc. of IEEE Int. Conf. on Computer Vision., Rio de Janeiro, Brazil, Oct.14-21, 2007, pp.1-5.
[9] Fernando, W. S. P., L. Udawatta, and P. Pathirana, "Identification of moving obstacles with pyramidal Lucas Kanade optical flow and k means clustering," in Proc. 3rd Int. Conf. on Information and Automation for Sustainability, Melbourne, Australia, Dec.4-6, 2007, pp.111-117.
[10] Gandhi, T. and M. M. Trivedi, “Parametric ego-motion estimation for vehicle surround analysis using an omnidirectional camera,” Machine Vision and Applications, vol.16, no.2, pp.85-95, 2005.
[11] Harris, C. and M. Stephens, "A combined corner and edge detector," in Proc. 4th Alvey Vision Conference, Manchester, UK, Aug.30-Sep.2, 1988, pp.147-152.
[12] Horn, B. K. P. and B. G. Schunck, "Determining optical flow," Artificial Intelligence, vol.17, pp.185-203, 1981.
[13] Inoue, O., A. Seonju, and S. Ozawa, "Following vehicle detection using multiple cameras," in Proc. Int. Conf. on Vehicular Electronics and Safety, Columbus, OH, Sep.22-24, 2008, pp.79-83.
[14] Jin, J.-S., Z. Zhu, and G. Xu, "A stable vision system for moving vehicles," IEEE Trans. on Intelligent Transportation Systems, vol.1, no.1, pp.32-39, 2000.
[15] Jones, W. D., "Keeping cars from crashing," IEEE Spectrum, vol.38, no.9, pp.40-45, 2001.
[16] Kim, S. Y., S. Y. Oh, J. K. Kang, Y. W. Ryu, and K. S. Kim, and S. C. Park, "Front and rear vehicle detection and tracking in the day and night times using vision and sonar sensor fusion," in Proc. IEEE/RSJ Int. Conf. on Intelligent Robot and System, Alberta, Canada, Aug.2-6, 2005, pp.2173-2178.
[17] Kitchen, L. and A. Rosenfeld, "Gray level corner detection," Pattern Recognition Letters, vol.1, no.2, pp.95-102, 1982.
[18] Ko, S.-J., S.-H. Lee, and K.-H. Lee, "Digital image stabilizing algorithm based on bit-plane matching," IEEE Trans. on Consumer Electronics, vol.44, no.3, pp.617-622, 1998.
[19] Liang, Y.-M., H.-R. Tyan, S.-L. Chang, H.-Y. M. Liao, and S.-W. Chen, "Video stabilization for a camcorder mounted on a moving vehicle," IEEE Trans. on Vehicular Technology, vol.53, no.6, pp.1636-1648, 2004.
[20] Liu, J.-F., Y.-F. Su, M.-K. Ko, and P.-N. Yu, "Development of a vision-based driver assistance system with lane departure warning and forward collision warning functions," in Proc. Digital Image Computing Techniques and Applications, Canberra, Australia, Dec.1-3, 2008, pp.480-485.
[21] Liu, Y. C., K. Y. Lin, and Y. S. Chen, “Bird’s-eye view vision system for vehicle surrounding monitoring,” in Proc. Conf. Robot Vision, Berlin, Germany, Feb. 20-22, 2008, pp.207-218.
[22] Lowe, G., "Distinctive image features from scale-invariant keypoints," Int. Journal of Computer Vision, vol.60, no.2, pp.91-110, 2004.
[23] Lucas, B. D. and T. Kanade, "An iterative image registration technique with an application to stereo vision," in Proc. Int. Joint Conf. on Artificial Intelligence, Vancouver, Canada, Aug.24-28, 1981, pp.674-679.
[24] Moravec, H., "Towards automatic visual obstacle avoidance," in Proc. Int. Joint Conf. on Artificial Intelligence, Cambridge, MA, Aug.22-25, 1977, pp.584.
[25] Ong, E. P. and M. Spann, "Robust optical flow computation based on least-median-of-squares regression," Int. Journal of Computer Vision, vol.31, no.1, pp.51-82, 1999.
[26] Paik, J. K., Y. C. Park, and D. W. Kim, "An adaptive motion decision system for digital image stabilizer based on edge pattern matching," IEEE Trans. on Consumer Electronics, vol.38, no.3, pp.607-616, 1992.
[27] Ratakonda, K., "Real-time digital video stabilization for multimedia applications," in Proc. IEEE Symposium on Circuits and Systems, Monterey, CA, May 31-Jun.3, 1998, pp.69-72.
[28] Shi, J. and C. Tomasi, "Good features to track," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Seattle, WA, Jun.21-23, 1994, pp.593-600.
[29] Trajkovic, M. and M. Hedley, "Fast corner detection," Image and Vision Computing, vol.16, no.2, pp.75-87, 1998.
[30] Uornori, K., A. Morimura, H. Ishii, T. Sakaguchi, and Y. Kitamura, "Automatic image stabilizing system by full-digital signal processing," IEEE Trans. on Consumer Electronics, vol.36, no.3, pp.510-519, 1990.
[31] Wang, H. and J. M. Brady, "Real-time corner detection algorithm for motion estimation," Image and Vision Computing, vol.13, no.9, pp.695-703, 1995.
[32] Wu, B.-F., C.-J. Chen, H.-H. Chiang, H.-Y. Peng, J.-W. Ma, and T.-T. Lee, "The design of an intelligent real-time autonomous vehicle, Taiwan iTS-1," Journal of the Chinese Institute of Engineerings, vol.30, no.5, pp.829-842, 2007.

指導教授

曾定章(Din-Chang Tseng)

審核日期

2010-7-27

推文