利用2-D射影變換實(shí)現(xiàn)多視圖下元素的預(yù)報(bào)
PREDICTING IMAGE ELEMENTS USING 2-D PROTECTIVE TRANSFORMATION FROM MULTIPLE VIEWS
-
摘要: 在描述多視圖的幾何元素對(duì)應(yīng)關(guān)系方面,2-D射影變換是一種有力工具。該文把求解2-D射影變換矩陣的方法從單純的四點(diǎn)對(duì)應(yīng)擴(kuò)展到多種組合形式的四元素對(duì)應(yīng)當(dāng)中,如:4點(diǎn)、4線、3點(diǎn)1線、3線1點(diǎn)和2點(diǎn)2線等。基于2-D射影對(duì)應(yīng)所描述的視圖關(guān)系,可以有效解決雙視圖和三視圖條件下的點(diǎn)元素或線元素的預(yù)報(bào)問題。由于沒有任何估計(jì)因素的介入,提高了預(yù)報(bào)結(jié)果的準(zhǔn)確性。靈活組合點(diǎn)線多種元素建立視圖關(guān)系使得預(yù)報(bào)環(huán)境適應(yīng)面廣泛。實(shí)驗(yàn)結(jié)果驗(yàn)證了方法的有效性。Abstract: 2-D projective collineation provides an ideal mathematical tool for describing planar element correspondence in multiple views. This paper extends the solution methods for 2-D projective transformation matrix from 4 points corresponding to variety combinations of points and lines corresponding, such as 4 points, 4 lines, 1 point and 3 lines, 3 lines and 1 point, and 2 points and 2 lines, etc. Based on the relationship between two views indicated as 2-D projective collineation, prediction problems about points or lines from two views or three views can be solved effectively. Without any estimating parameters involved, the prediction results accuracy is improved. Freely combining points and lines on describing relationship between views makes the application field wider. The methods proposed here have been verified by experimental results.
-
O.D. Faugeras, L. Robert, What can two images tell us about a third one?, International Journalof Computer Vision, 1996, 18(3), 5-19.[2]Zhengyou Zhang, Determining the epipolar geometry and its Uncertainty, A Review, InternationalJournal of Computer Vision, 1998, 27(2), 161-195.[3]E.B. Barrett et al., Linear resection, intersection, and perspective-independent model matchingin photogrammetry: Theory, SPIE, Vol 1567, 1991, Applications of Digital Image ProcessingXIV, 142-169.[4]龍澤斌編著,幾何變換,湖南科學(xué)技術(shù)出版社,1984年第一版,第三章.[5]L. Quan, Invariants of six points and projective reconstruction from three uncalibrated images,IEEE Trans. on Pattern Analysis and Machine Intelligence, 1995, 17(1), 34-46. -
計(jì)量
- 文章訪問數(shù): 1868
- HTML全文瀏覽量: 120
- PDF下載量: 1036
- 被引次數(shù): 0
下載:
