AI helps you reading Science
AI generates interpretation videos
AI extracts and analyses the key points of the paper to generate videos automatically
AI parses the academic lineage of this thesis
AI extracts a summary of this paper
In this paper we have developed a new methodology to acquire highly precise and reliable ground truth disparity measurements accurately aligned with stereo image pairs
High-accuracy stereo depth maps using structured light
CVPR, (2003): 195-202
Recent progress in stereo algorithm performance is quickly outpacing the ability of existing stereo data sets to discriminate among the best-performing algorithms, motivating the need for more challenging scenes with accurate ground truth information. This paper describes a method for acquiring high-complexity stereo image pairs with pixe...More
PPT (Upload PPT)
- The last few years have seen a resurgence of interest in the development of highly accurate stereo correspondence algorithms.
- Part of this interest has been spurred by fundamental breakthroughs in matching strategies and optimization algorithms, and part of the interest is due to the existence of image databases that can be used to test and compare such algorithms.
- Synthetic images have been suggested for testing stereo algorithm performance [12, 9], but they typically are either too easy to solve if noise, aliasing, etc. are not modeled, or too difficult, e.g., due to complete lack of texture in parts of the scene
- The last few years have seen a resurgence of interest in the development of highly accurate stereo correspondence algorithms
- In this paper we have developed a new methodology to acquire highly precise and reliable ground truth disparity measurements accurately aligned with stereo image pairs
- Such high-quality data is essential to evaluate the performance of stereo correspondence algorithms, which in turn spurs the development of even more accurate algorithms
- Our new high-quality disparity maps and the original input images are available on our web site at http://www.middlebury.edu/stereo/
- We plan to add these new data sets to those already in use to benchmark the performance of stereo correspondence algorithms 
- Our novel approach is based on taking stereo image pairs illuminated with active lighting from one or more projectors
- Using the method described in the previous sections, the authors have acquired two different scenes, Cones and Teddy.
- Figure 5 shows views L and R of each scene taken under ambient lighting.
- L and R are views 3 and 7 out of a total of 9 images the authors have taken from -spaced viewpoints, which can be used for prediction-error evaluation .
- The Cones scene was constructed such that most scene points visible from either view L and R can be illuminated with a single light source from above.
- Due to the complex scene, several small areas are shadowed under both illuminations
- In this paper the authors have developed a new methodology to acquire highly precise and reliable ground truth disparity measurements accurately aligned with stereo image pairs.
- Such high-quality data is essential to evaluate the performance of stereo correspondence algorithms, which in turn spurs the development of even more accurate algorithms.
- The encoded positions enable the recovery of camera-projector disparities, which can be used as an auxiliary source of information to increase the reliability of correspondences and to fill in missing data
- Table1: Performance of SSD, dynamic programming, and graph cut stereo methods on our data sets. The table shows the percentage of pixels whose disparity error is greater than threshold t for t = 1, 2
- Describes a method for acquiring high-complexity stereo image pairs with pixel-accurate correspondence information using structured light
- Presents new stereo data sets acquired with our method and demonstrate their suitability for stereo algorithm evaluation
- Distinguishes between views – the images taken by the cameras – and illuminations – the structured light patterns projected onto the scene. models both processes using planar perspective projection and use coordinates for views and for illuminations
- Has found that the only reliable way of thresholding pixels into on/off is to project both the code pattern and its inverse
- G. J. Agin and T. O. Binford. Computer description of curved objects. IEEE Trans. Comp., C-25(4):439–449, 1976.
- J. Batlle, E. Mouaddib, and J. Salvi. Recent progress in coded structured light as a technique to solve the correspondence problem: a survey. Pat. Recog., 31(7):963–982, 1998.
- P. Besl. Active optical range imaging sensors. In Jorge L.C. Sanz, editor, Advances in Machine Vision, pp. 1–63, 1989.
- J.-Y. Bouguet and P. Perona. 3D photography on your desk. In ICCV’98, pp. 43–50, 1998.
- C. Chen, Y. Hung, C. Chiang, and J. Wu. Range data acquisition using color structured lighting and stereo vision. Image and Vision Computing, 15(6):445–456, 1997.
- Y.-Y. Chuang et al. Environment matting extensions: towards higher accuracy and real-time capture. In SIGGRAPH 2000, pp. 121–130, 2000.
- B. Curless and M. Levoy. Better optical triangulation through spacetime analysis. In ICCV’95, pp. 987–994, 1995.
- J. Davis, R. Ramamoorthi, and S. Rusinkiewicz. Spacetime stereo: a unifying framework for depth from triangulation. In CVPR 2003, 2003.
- T. Frohlinghaus and J. M. Buhmann. Regularizing phasebased stereo. In ICPR’96, vol. A, pp. 451–455, 1996.
- G. Golub and C. F. Van Loan. Matrix Computation, third edition. The John Hopkins University Press, 1996.
- G. Hausler and D. Ritter. Parallel three-dimensional sensing by color-coded triangulation. Applied Optics, 32(35):7164– 7169, 1993.
- W. Hoff and N. Ahuja. Surfaces from stereo: integrating feature matching, disparity estimation, and contour detection. IEEE Trans. Pat. Anal. Mach. Int., 11(2):121–136, 1989.
- E. Horn and N. Kiryati. Toward optimal structured light patterns. In Intl. Conf. Recent Advances in 3D Digital Imaging and Modeling, pp. 28–35, 1997.
- S. B. Kang, J. Webb, L. Zitnick, and T. Kanade. A multibaseline stereo system with active illumination and real-time image acquisition. In ICCV’95, pp. 88–93, 1995.
- C. Loop and Z. Zhang. Computing rectifying homographies for stereo vision. In CVPR’99, volume I, pp. 125–131, 1999.
- J. Mulligan, V. Isler, and K. Daniilidis. Performance evaluation of stereo for tele-presence. In ICCV 2001, vol. II, pp. 558–565, 2001.
- Y. Nakamura, T. Matsuura, K. Satoh, and Y. Ohta. Occlusion detectable stereo - occlusion patterns in camera matrix. In CVPR’96, pp. 371–378, 1996.
- M. Proesmans, L. Van Gool, and F. Defoort. Reading between the lines - a method for extracting dynamic 3D with texture. In ICCV’98, pp. 1081–1086, 1998.
- K. Pulli et al. Acquisition and visualization of colored 3D objects. In ICPR’98, pp. 11-15, 1998.
- K. Sato and S. Inokuchi. Three-dimensional surface measurement by space encoding range imaging. J. Robotic Systems, 2:27–39, 1985.
- D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Intl. J. Comp. Vis., 47(1):7–42, 2002.
- E. Schubert. Fast 3D object recognition using multiple color coded illumination. In Proc. IEEE Conf. Acoustics, Speech, and Signal Processing, pp. 3057–3060, 1997.
- P. Vuylsteke and A. Oosterlinck. Range image acquisition with a single binary-encoded light pattern. IEEE Trans. Pat. Anal. Mach. Int., 12(2):148–164, 1990.
- L. Zhang, B. Curless, and S. M. Seitz. Spacetime stereo: shape recovery for dynamic scenes. In CVPR 2003, 2003.
- T. Zickler, P. N. Belhumeur, and D. J. Kriegman. Helmholtz stereopsis: exploiting reciprocity for surface reconstruction. In ECCV 2002, v. III, pp. 869–884, 2002.