A Database and Evaluation Methodology for Optical Flow

Baker, Simon; Scharstein, Daniel; Lewis, J. P.; Roth, Stefan; Black, Michael J.; Szeliski, Richard

doi:10.1109/iccv.2007.4408903

Cited by 1,013 publications

(1,450 citation statements)

References 53 publications

Supporting

Mentioning

1,442

Contrasting

Unclassified

Order By: Relevance

“…Table 2. Average Angular Error (AAE) comparison obtained from the Middlebury website [23]. The second column shows the average ranks and other columns on the right show AAEs around the motion discontinuities.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…Quantitative evaluation of the optical flow algorithm is conducted using the dataset in [23]. The overall rank of our method is high amongst all recorded optical flow algorithms on the Middlebury website based on the average angular error (AAE).…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…To visualize the dense flow, in this paper, we adopt the color coding in [23] where the chromaticity is used to distinguish the motion direction and the intensity corresponds to the motion magnitude. Fig.…”

Section: Our Approachmentioning

confidence: 99%

See 2 more Smart Citations

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

Liu

Chen

Jia

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Segmentation has gained in popularity in stereo matching. However, it is not trivial to incorporate it in optical flow estimation due to the possible non-rigid motion problem. In this paper, we describe a new optical flow scheme containing three phases. First, we partition the input images and integrate the segmentation information into a variational model where each of the segments is constrained by an affine motion. Then the errors brought in by segmentation are measured and stored in a confidence map. The final flow estimation is achieved through a global optimization phase that minimizes an energy function incorporating the confidence map. Extensive experiments show that the proposed method not only produces quantitatively accurate optical flow estimates but also preserves sharp motion boundaries, which makes the optical flow result usable in a number of computer vision applications, such as image/video segmentation and editing.

show abstract

Section: Quantitative Evaluationmentioning

confidence: 99%

Section: Quantitative Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

Liu

Chen

Jia

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Based on this brightness constancy equation, a traditional way to calculate the motion vector v is to minimize the following optical flow equation [7]: …”

Section: Refractive Flowmentioning

confidence: 99%

Refraction Wiggles for Measuring Fluid Depth and Velocity from Video

Xue¹,

Rubinstein

Wadhwa³

et al. 2014

Computer Vision – ECCV 2014

View full text Add to dashboard Cite

Abstract. We present principled algorithms for measuring the velocity and 3D location of refractive fluids, such as hot air or gas, from natural videos with textured backgrounds. Our main observation is that intensity variations related to movements of refractive fluid elements, as observed by one or more video cameras, are consistent over small space-time volumes. We call these intensity variations "refraction wiggles", and use them as features for tracking and stereo fusion to recover the fluid motion and depth from video sequences. We give algorithms for 1) measuring the (2D, projected) motion of refractive fluids in monocular videos, and 2) recovering the 3D position of points on the fluid from stereo cameras. Unlike pixel intensities, wiggles can be extremely subtle and cannot be known with the same level of confidence for all pixels, depending on factors such as background texture and physical properties of the fluid. We thus carefully model uncertainty in our algorithms for robust estimation of fluid motion and depth. We show results on controlled sequences, synthetic simulations, and natural videos. Different from previous approaches for measuring refractive flow, our methods operate directly on videos captured with ordinary cameras, do not require auxiliary sensors, light sources or designed backgrounds, and can correctly detect the motion and location of refractive fluids even when they are invisible to the naked eye.

show abstract

“…In the experimental results, we study the precision of our methods using synthetic sequences from the Middlebury benchmark database [6]. This provides complex sequences with ground truths.…”

Section: Introductionmentioning

confidence: 99%

Computing inverse optical flow

Sánchez

Salgado

Monzón

2015

Pattern Recognition Letters

View full text Add to dashboard Cite

We propose four algorithms for computing the inverse optical flow between two images. We assume that the forward optical flow has already been obtained and we need to estimate the flow in the backward direction. The forward and backward flows can be related through a warping formula, which allows us to propose very efficient algorithms. These are presented in increasing order of complexity. The proposed methods provide high accuracy with low memory requirements and low running times. In general, the processing reduces to one or two image passes. Typically, when objects move in a sequence, some regions may appear or disappear. Finding the inverse flows in these situations is difficult and, in some cases, it is not possible to obtain a correct solution. Our algorithms deal with occlusions very easy and reliably. On the other hand, disocclusions have to be overcome as a post-processing step. We propose three approaches for filling disocclusions. In the experimental results, we use standard synthetic sequences to study the performance of the proposed methods, and show that they yield very accurate solutions. We also analyze the performance of the filling strategies.

show abstract

A Database and Evaluation Methodology for Optical Flow

Cited by 1,013 publications

References 53 publications

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

Refraction Wiggles for Measuring Fluid Depth and Velocity from Video

Computing inverse optical flow

Contact Info

Product

Resources

About