Anisotropic Huber-L1 Optical Flow

Werlberger, Manuel; Trobin, Werner; Pock, Thomas; Wedel, Andreas; Cremers, Daniel; Bischof, Horst

doi:10.5244/c.23.108

Cited by 309 publications

(233 citation statements)

References 3 publications

Supporting

Mentioning

230

Contrasting

Unclassified

Order By: Relevance

“…A multi-grid redblack relaxation has been suggested in a parallel implementation of the linear CLG method [12]. Very efficient GPU implementations of other variational optical flow models have been proposed in [3,13,14].…”

Section: Related Workmentioning

confidence: 99%

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Sundaram

Brox

Keutzer

2010

Computer Vision – ECCV 2010

360

340

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: Related Workmentioning

confidence: 99%

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Sundaram

Brox

Keutzer

2010

Computer Vision – ECCV 2010

360

340

View full text Add to dashboard Cite

show abstract

“…Another common criterion used for this purpose is the 1 norm of the residual, which is non-trivial to minimize since it is non-smooth. Bruhn et al (2005) and Brox et al (2004) use Charbonnier's penalty that is a differentiable approximation of the 1 norm; others (Wedel et al 2008, Werlberger et al 2009) solved the non-smooth problem with primal-dual methods decoupling the matching and regularization terms. However, none of these robust flow estimation methods focus on the detection of occlusions.…”

Section: Prior Related Workmentioning

confidence: 99%

Sparse Occlusion Detection with Optical Flow

2011

View full text Add to dashboard Cite

We tackle the problem of detecting occluded regions in a video stream. Under assumptions of Lambertian reflection and static illumination, the task can be posed as a variational optimization problem, and its solution approximated using convex minimization. We describe efficient numerical schemes that reach the global optimum of the relaxed cost functional, for any number of independently moving objects, and any number of occlusion layers. We test the proposed algorithm on benchmark datasets, expanded to enable evaluation of occlusion detection performance, in addition to optical flow.

show abstract

“…This function has been identified [9] to be very descriptive and robust, especially under strong illumination variations. Since this is a crucial feature for real-world applications the function is increasingly applied for both, stereo [16] and optical flow estimation methods [20].…”

Section: Algorithm Configurationmentioning

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

Anisotropic Huber-L1 Optical Flow

Cited by 309 publications

References 3 publications

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow

Sparse Occlusion Detection with Optical Flow

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

Contact Info

Product

Resources

About