Real-time quantized optical flow

Camus, T.

doi:10.1109/camp.1995.521028

Cited by 35 publications

(57 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Real-time optical flow techniques typically consider only the data fidelity term to generate displacement fields [12,25]. One of the first variational approaches to compute the optical flow in real-time was presented by Bruhn et al [10,11].…”

Section: Introductionmentioning

confidence: 99%

An Improved Algorithm for TV-L 1 Optical Flow

Wedel

Pock

Zach

et al. 2009

Lecture Notes in Computer Science

343

229

View full text Add to dashboard Cite

Fig. 1. Optical flow for the backyard and mini cooper scene of the Middlebury optical flow benchmark. Optical flow captures the dynamics of a scene by estimating the motion of every pixel between two frames of an image sequence. The displacement of every pixel is shown as displacement vectors on top of the commonly used flow color scheme (see Figure 5). Abstract.A look at the Middlebury optical flow benchmark [5] reveals that nowadays variational methods yield the most accurate optical flow fields between two image frames. In this work we propose an improvement variant of the original duality based TV-L 1 optical flow algorithm in [31] and provide implementation details. This formulation can preserve discontinuities in the flow field by employing total variation (TV) regularization. Furthermore, it offers robustness against outliers by applying the robust L 1 norm in the data fidelity term.Our contributions are as follows. First, we propose to perform a structure-texture decomposition of the input images to get rid of violations in the optical flow constraint due to illumination changes. Second, we propose to integrate a median filter into the numerical scheme to further increase the robustness to sampling artefacts in the image data. We experimentally show that very precise and robust estimation of optical flow can be achieved with a variational approach in realtime. The numerical scheme and the implementation are described in a detailed way, which enables reimplementation of this high-end method.

show abstract

Section: Introductionmentioning

confidence: 99%

An Improved Algorithm for TV-L 1 Optical Flow

Wedel

Pock

Zach

et al. 2009

Lecture Notes in Computer Science

343

229

View full text Add to dashboard Cite

show abstract

“…Refer to the cited references for full details. [2]: Applies region matching for spatial windows over n previous frames. The window size sets the maximum detectable flow magnitude.…”

Section: Overview and Theoretical Comparisonmentioning

confidence: 99%

“…We aim to provide insight and recommendations for the choice of flow techniques for robot navigation with continuous motion. Three gradient-based methods are included: Lucas and Kanade [8], Horn and Schunck [5], and Nagel [9], as well as Camus' correlation-based method [2]. Three temporal filters are also included: Gaussian filtering, Simoncelli's presmoothing and derivative filters [12], and Fleet and Langley's recursive temporal filter [3].…”

Section: Introductionmentioning

confidence: 99%

Performance of optical flow techniques for indoor navigation with a mobile robot

McCarthy

Bames²

2004

IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004

View full text Add to dashboard Cite

Abstract-We present a comparison of four optical flow methods and three spatio-temporal filters for mobile robot navigation in corridor-like environments. Previous comparisons of optical flow methods have evaluated performance only in terms of accuracy and/or efficiency, and typically in isolation. These comparisons are inadequate for addressing applicability to continuous, real-time operation as part of a robot control loop. We emphasise the need for comparisons that consider the context of a system, and that are confirmed by in-system results. To this end, we give results for on and off-board trials of two biologically inspired behaviours: corridor centring and visual odometry. Our results show the best in-system performances are achieved using Lucas and Kanade's gradient-based method in combination with a recursive temporal filter. Results for traditionally used Gaussian filters indicate that long latencies significantly impede performance for real-time tasks in the control loop.

show abstract

“…One of the characteristics of the Lucas-Kanade algorithm, compared to the method proposed by Camus [2], is that it does not yield a very high density of flow vectors. This means that the flow information fades out quickly across motion boundaries.…”

Section: Feature Tracking Algorithmmentioning

confidence: 99%