| 研究生: |
王幰彰 Wang, Hsien-Chang |
|---|---|
| 論文名稱: |
滅點偵測之研究-基於θ-直方圖統計分析法 A Study of Vanishing Point Detection -Based on θ-Histogram Analysis |
| 指導教授: |
廖揚清
Liao, Yang-Cheng |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 測量及空間資訊學系 Department of Geomatics |
| 論文出版年: | 2004 |
| 畢業學年度: | 92 |
| 語文別: | 中文 |
| 論文頁數: | 85 |
| 中文關鍵詞: | 滅點偵測 、近景 |
| 外文關鍵詞: | vanishing point detection, close-range |
| 相關次數: | 點閱:38 下載:1 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
利用影像中的滅點(vanishing point)解算攝影時的方位元素(orientation parameter),不需要另外佈設控制點(control point)。可以應用在建物重建、機器人和自動車的方位導引、攝影機的率定、測量車系統的物空間長度推算等場合。
本文研究滅點解算攝影時方位元素的方式,提出基於θ-直方圖(θ-histogram)統計分析的滅點偵測(vanishing point detection)。上述方法可適用於攝影時任一旋轉角不為零度或接近零度所拍攝的近景(close-range)建物影像滅點位置偵測,不需要另外的已知條件及人工介入。
以單張影像,已知方位元素推算物空間長度的RMSE,作為評估所得成果好壞的依據。經實驗證明,六幅室內模型影像利用本文之基於θ-直方圖統計分析方法偵測滅點位置推算出的物空間長度RMSE值平均為±0.0041 m,相對精度約達1/48~1/21;室外實際建物影像推算的物空間長度RMSE值為±0.161 m,相對精度約達1/64~1/27。
上述方法在加入以驗後方差估計原理導出的選擇權迭代法後,即使用來計算滅點位置的直線有約13%不正確,所得的物空間長度推算RMSE值也能達到±0.166 m,相對精度約為1/62~1/28,相當程度地確保了此法滅點偵測成果的可靠度。
Using vanishing point to estimate orientation parameters does not need control point’s information. It is applied for the object reconstruction, navigation of autonomous vehicles or robots, camera calibration and length measurement.
This research present a method of vanishing point detection based on θ-histogram analysis. It is suitable for close-range building image and without manual interference.
If orientation parameters have known can infer object length on single image. For criterion of experimentation result, we compare inferential length with real length and compute RMSE. Average RMSE of using our method in the six model images is ±0.0041 m ( relative accuracy is 1/48~1/21 ).
RMSE of using our method in a real building image is ±0.0161 m ( relative accuracy is 1/64~1/27 ). Even if in the set of lines for vanishing point detection has 13% error, RMSE still can achieve ±0.166 m ( relative accuracy is 1/62~1/28 ). This result shows that our vanishing point detection method is robust.
參考文獻
王正忠,「以近景攝影測量進行模型式建物重建」,國立成功大學測量工程學研究所碩士論文,台南,2002。
李德仁,「誤差處理和可靠性理論-攝影測量平差的近代發展-」,測繪出版社,武漢,第200至201頁,1992。
陳連晃,「近景攝影測量中以物空間三軸條件取代控制測量之研究」,國立成功大學航空測量研究所碩士論文,台南,1986。
陳順宇,「統計學」,華泰書局,台北,第A7頁,1997。
張祖勛、張劍清、張世興,「單像房屋三維重建」, 2001年兩岸自動化數字工程測量研討會論文集,第112頁至118頁,2001。
傅俊淇,「多重影像中線形特徵物與物空間直線進行匹配之研究」,國立成功大學測量工程學研究所碩士論文,台南,2003。
劉冠佑,「透視校正用於田間環境之辨識與自動車之導引」,國立台灣大學生物產業機電工程學研究所碩士論文,台北,2001。
Stephen T. Barnard, Interpreting Perspective Images, Artificial intelligence, Vol. 21 pp.435-462 (1983)
F. A. van den Heuvel, Vanishing Point Detection for Architectural Photogrammetry, International archives of photogrammetry and remote sensing, Vol. 32 part 5, pp. 652-659 (1998)
R. Klette, K. Schlüns & A. Koschan, Computer Vision: Three Dimensional Data from Images, Springer press, pp. 53-57 (2001)
L. L. Lapin, Modern Engineering Statistics, Duxbury press, pp. 552 (1996)
N. OTSU, A Threshold Selection Method from Gray-Level Histograms, IEEE transaction on systems, man, and cybernetics, Vol. SMC-9, No. 1, pp. 62-66 (1979)
Carsten Rother, A new Approach to Vanishing Point Detection in Architectural Environments, Image and vision computing, Vol. 20 Issues 9-10, pp.647-655 (2002)
Ling-Ling Wang & Wen-Hsiang Tsai, Computing Camera Parameters using Vanishing-Line Information from a Rectangular Parallelepiped, Machine vision and applications, Vol. 3, pp.129-141 (1990)
A. M. G. Tommaselli, Orientation and reconstruction of close-range images using lines, International Archives of photogrammetry and remote sensing. Vol. 33, Part B5. Amsterdam (2000)
C. V. Tao, Visual Inference Techniques and Their Applications to Single-image-based Object Measurement, Surveying and land information system, Vol. 61, No. 2, 2001, pp.123-128 (2001)