A Duality Based Approach for Realtime TV-L 1 Optical Flow

Zach, Christopher; Pock, Thomas; Bischof, Horst

doi:10.1007/978-3-540-74936-3_22

Cited by 1,397 publications

(1,181 citation statements)

References 18 publications

Supporting

Mentioning

1,122

Contrasting

Unclassified

Order By: Relevance

“…For this reason, ways to significantly speedup such methods on commodity hardware are an important contribution as they enable more efficient research in fields that build upon motion features. Fast implementations of the KLT tracker and optical flow [2,3] are examples that have certainly pushed research.…”

Section: Introductionmentioning

confidence: 99%

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Sundaram

Brox

Keutzer

2010

Lecture Notes in Computer Science

370

349

View full text Add to dashboard Cite

Dense and accurate motion tracking is an important requirement for many video feature extraction algorithms. In this paper we provide a method for computing point trajectories based on a fast parallel implementation of a recent optical flow algorithm that tolerates fast motion. The parallel implementation of large displacement optical flow runs about 78× faster than the serial C++ version. This makes it practical to use in a variety of applications, among them point tracking. In the course of obtaining the fast implementation, we also prove that the fixed point matrix obtained in the optical flow technique is positive semi-definite. We compare the point tracking to the most commonly used motion tracker -the KLT tracker -on a number of sequences with ground truth motion. Our resulting technique tracks up to three orders of magnitude more points and is 46% more accurate than the KLT tracker. It also provides a tracking density of 48% and has an occlusion error of 3% compared to a density of 0.1% and occlusion error of 8% for the KLT tracker. Compared to the Particle Video tracker, we achieve 66% better accuracy while retaining the ability to handle large displacements while running an order of magnitude faster.

show abstract

Section: Introductionmentioning

confidence: 99%

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Sundaram

Brox

Keutzer

2010

Lecture Notes in Computer Science

370

349

View full text Add to dashboard Cite

show abstract

“…. , 0.1; and A with 6 optical flow algorithms: a fast sparseto-dense pyramidal Lucas-Kanade [2], Farnebäck [5], Dual TV-L 1 [21], SimpleFlow [18], DeepFlow [20], and DISFlow [8]. Their implementations have been found in the OpenCV 3.2 library 5 , and they are used with their default or recommended sets of parameters.…”

Section: Comparison Of Motion Detectors With or Without Memorymentioning

confidence: 99%

Is a Memoryless Motion Detection Truly Relevant for Background Generation with LaBGen?

Laugraud

Droogenbroeck

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The stationary background generation problem consists in generating a unique image representing the stationary background of a given video sequence. The LaBGen background generation method combines a pixel-wise median filter and a patch selection mechanism based on a motion detection performed by a background subtraction algorithm. In our previous works related to LaBGen, we have shown that, surprisingly, the frame difference algorithm provides the most effective motion detection on average. Compared to other background subtraction algorithms, it detects motion between two frames without relying on additional past frames, and is therefore memoryless. In this paper, we experimentally check whether the memoryless property is truly relevant for LaBGen, and whether the effective motion detection provided by the frame difference is not an isolated case. For this purpose, we introduce LaBGen-OF, a variant of LaBGen leverages memoryless dense optical flow algorithms for motion detection. Our experiments show that using a memoryless motion detector is an adequate choice for our background generation framework, and that LaBGen-OF outperforms LaBGen on the SBMnet dataset. We further provide an open-source C++ implementation of both methods at http://www.telecom.ulg.ac.be/labgen.

show abstract

“…rithms along with baseline results of the highly recognized work by Brox et al [2] (LDOF) and Zach et al [22] (DB-TV-L1). This list refers to the state on 10 October 2012.…”

Section: Large-scale Optical Flowmentioning

confidence: 99%

“…Currently the most successful optical flow algorithms use variational calculus to minimize a global error function. In order to handle large displacements, variational optical flow methods are embedded into hierarchical schemes, refining an optimal prior solution successively at subsequent levels, see for example Brox et al [1,2], Zach et al [22], and Werlberger et al [20].…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Scan-Line Dynamic Programming for Optical Flow Using Semi-Global Matching

Hermann

Klette

2013

Computer Vision - ACCV 2012 Workshops

View full text Add to dashboard Cite

Abstract. Dense and robust optical flow estimation is still a major challenge in low-level computer vision. In recent years, mainly variational methods contributed to the progress in this field. One reason for their success is their suitability to be embedded into hierarchical schemes, which makes them capable of handling large pixel displacements. Matching-based regularization techniques, like dynamic programming or belief propagation concepts, can also lead to accurate optical flow fields. However, results are limited to short-or mid-scale optical flow vectors, because these techniques are usually not coupled with coarse-to-fine strategies. This paper introduces fSGM, a novel algorithm that is based on scan-line dynamic programming. It uses the cost integration strategy of semi-global matching, a concept well known in the area of stereo matching. The major novelty of fSGM is that it embeds the scan-line dynamic programming approach into a hierarchical scheme, which allows it to handle large pixel displacements with an accuracy comparable to variational methods. We prove the exceptional performance of fSGM by comparing it to current state-of-the-art methods on the KITTI Vision Benchmark Suite.

show abstract

A Duality Based Approach for Realtime TV-L 1 Optical Flow

Cited by 1,397 publications

References 18 publications

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Is a Memoryless Motion Detection Truly Relevant for Background Generation with LaBGen?

Hierarchical Scan-Line Dynamic Programming for Optical Flow Using Semi-Global Matching

Contact Info

Product

Resources

About