Dense Structure from a Dense Optical Flow Sequence

Xiong, Yalin; Shafer, Steven A.

doi:10.1006/cviu.1997.0601

Cited by 19 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second approach is the iconic depth estimator [18,25] in which all pixels contribute a depth estimate. This approach is more suitable for a navigating robot as it lends itself to small motions between viewpoints.…”

Section: Previous Workmentioning

confidence: 99%

“…Structure-from-motion can be defined as the process of inferring a mesh of interconnected points representing a three-dimensional surface from time-varying patterns of image change [3,16,20,25]. This problem is very difficult for several reasons [5,7,14]: the projected image intensity fails to provide an invertible encoding of surface characteristics under most conditions, the correspondence problem becomes increasingly difficult as the displacement between images increases, and the triangulation process becomes increasingly ill-conditioned as the motion between frames becomes small.…”

Section: Introductionmentioning

confidence: 99%

“…An additional constraint on the system is the restriction on the configuration space inherent to an autonomous navigator [9,13,19,25]. Most active vision algorithms assume full motion control is available to a viewer (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Active Surface Reconstruction Using the Gradient Strategy

Mitran

Ferrie

2002

Computer Vision — ECCV 2002

View full text Add to dashboard Cite

Abstract. This paper describes the design and implementation of an active surface reconstruction algorithm for two-frame image sequences using passive imaging. A novel strategy based on the statistical grouping of image gradient features is used. It is shown that the gradient of the intensity in an image can successfully be used to drive the direction of the viewer's motion. As such, an increased efficiency in the accumulation of information is demonstrated through a significant increase in the convergence rate of the depth estimator (3 to 4 times for the presented results) over traditional passive depth-from-motion. The viewer is considered to be restricted to a short baseline. A maximal-estimation framework is adopted to provide a simple approach for propagating information in a bottom-up fashion in the system. A Kalman filtering scheme is used for accumulating information temporally. The paper provides results for real-textured data to support the findings.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Active Surface Reconstruction Using the Gradient Strategy

Mitran

Ferrie

2002

Computer Vision — ECCV 2002

View full text Add to dashboard Cite

show abstract

“…A 5 th algorithm by Xiong and Shafter [11] is under implementation. All of these algorithms assume known camera translation and rotation (or can be made to have this assumption).…”

Section: The Algorithmsmentioning

confidence: 99%