| M. W. Maimone and S. A. Shafer. A taxonomy for stereo computer vision experiments. In H. I. Christensen, W. Forstner, and C. B. Madsen, editors, Performance Characteristics of Vision Algorithms, pages 59--80, 1996. 7 |
....is matching two views of a single point in the scene. This correspondence problem has as its output, disparity, the o#set required to align the projections of the two points. Given a disparity map and camera parameters the depth and hence three dimensional strcuture of the scene can be inferred [4]. In the sparse stereo approach, features that are projectively invariant, such as corners, are identified in each image. Provided care is taken with the numerical analysis [5] it is possible to solve for the position of the corners and the camera parameters simultaneously. Often, however, a ....
M. Maimone and S. Shafer, "A taxonomy for stereo computer vision experiments," in ECCV Workshop on Performance Characteristics of Vision Algorithms, pp. 59 -- 79, April 1996.
....series of tests, each of which will have a specific objective. It is important to carefully define the objective of each task, since even small differences will make it change the form of the test and make it hard to compare similar tests. 2.2. Test Data. A typology of test data has been proposed [10] and includes: ffl Simulations using data without noise, allowing verifications of performance. This corresponds to the study in [7] which revealed the stability conditions. 4 P. COURTNEY AND N.A. THACKER ffl Simulations using data with noise: perhaps the most common form ffl Empirical testing ....
W.M. Maimone and S.A. Shafer, A Taxonomy for Stereo Computer Vision Experiments, Proceedings of ECCV Workshop on Performance Characteristics of Vision Algorithms, Cambridge, UK, April 1996.
No context found.
M. W. Maimone and S. A. Shafer. A taxonomy for stereo computer vision experiments. In H. I. Christensen, W. Forstner, and C. B. Madsen, editors, Performance Characteristics of Vision Algorithms, pages 59--80, 1996. 7
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC