Robust Feature Tracking in DVS Event Stream using Bézier Mapping

Seok, Hochang; Lim, Jongwoo

doi:10.1109/wacv45572.2020.9093607

Cited by 31 publications

(22 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In principle, we can optimize a continuous B-spline trajectory by optimizing all knots on the spline and taking all events into account, but this is expensive and inefficient. Inspired by [10], we make use of a History patch H which compresses the information of previous knots and events in order to speed up the algorithm. The History patch H is built in recurrent relation.…”

Section: Methodsmentioning

confidence: 99%

“…Since there is no public implementation of [10] available, and we are using different initial positions, we can only compare our result qualitatively. In Fig.…”

Section: Methodsmentioning

confidence: 99%

“…The optical flow is computed as an expectation over all associations and the patch can undergo affine deformations during tracking. The work by Seok et al [10] is the first approach to formulate event tracking in continuous time. However, adding more knots to the existing Bézier curve changes all previous knots, so the feature trajectory has to be formed by concatenating many short Bézier curves and is only zero order continuous.…”

Section: Related Workmentioning

confidence: 99%

“…This approach is known as motion-compensation [4]. It is applied to a variety of event-based vision tasks, such as feature tracking [5], [10], ego-motion estimation [16], [14] or motion segmentation [12].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization

Chui,

Klenk,

Cremers

2021

Preprint

View full text Add to dashboard Cite

We propose a novel method for continuous-time feature tracking in event cameras. To this end, we track features by aligning events along an estimated trajectory in space-time such that the projection on the image plane results in maximally sharp event patch images. The trajectory is parameterized by n th order B-splines, which are continuous up to (n − 2) th derivative. In contrast to previous work, we optimize the curve parameters in a sliding window fashion. On a public dataset we experimentally confirm that the proposed sliding-window B-spline optimization leads to longer and more accurate feature tracks than in previous work.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Since there is no public implementation of [10] available, and we are using different initial positions, we can only compare our result qualitatively. In Fig.…”

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization

Chui,

Klenk,

Cremers

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The parameter δt is set by making a trade-off between the two considerations. A better way to resolve this limitation is to apply nonlinear motion models, such as a Bézier spline [32], which is able to describe complex motion within a relatively longer temporal window. We leave these to future work.…”

Section: E Limitationsmentioning

confidence: 99%

Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting

Lu¹,

Zhou²,

Shen³

2021

Preprint

View full text Add to dashboard Cite

Among prerequisites for a synthetic agent to interact with dynamic scenes, the ability to identify independently moving objects is specifically important. From an application perspective, nevertheless, standard cameras may deteriorate remarkably under aggressive motion and challenging illumination conditions. In contrast, event-based cameras, as a category of novel biologically inspired sensors, deliver advantages to deal with these challenges. Its rapid response and asynchronous nature enables it to capture visual stimuli at exactly the same rate of the scene dynamics. In this paper, we present a cascaded two-level multi-model fitting method for identifying independently moving objects (i.e., the motion segmentation problem) with a monocular event camera. The first level leverages tracking of event features and solves the feature clustering problem under a progressive multi-model fitting scheme. Initialized with the resulting motion model instances, the second level further addresses the event clustering problem using a spatio-temporal graph-cut method. This combination leads to efficient and accurate event-wise motion segmentation that cannot be achieved by any of them alone. Experiments demonstrate the effectiveness and versatility of our method in real-world scenes with different motion patterns and an unknown number of independently moving objects.

show abstract

Multi‐Event‐Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

Ghosh

Gallego

2022

Advanced Intelligent Systems

View full text Add to dashboard Cite

Event cameras are bio‐inspired sensors that offer advantages over traditional cameras. They operate asynchronously, sampling the scene at microsecond resolution and producing a stream of brightness changes. This unconventional output has sparked novel computer vision methods to unlock the camera's potential. Here, the problem of event‐based stereo 3D reconstruction for SLAM is considered. Most event‐based stereo methods attempt to exploit the high temporal resolution of the camera and the simultaneity of events across cameras to establish matches and estimate depth. By contrast, this work investigates how to estimate depth without explicit data association by fusing disparity space images (DSIs) originated in efficient monocular methods. Fusion theory is developed and applied to design multi‐camera 3D reconstruction algorithms that produce state‐of‐the‐art results, as confirmed by comparisons with four baseline methods and tests on a variety of available datasets.

show abstract

Robust Feature Tracking in DVS Event Stream using Bézier Mapping

Cited by 31 publications

References 25 publications

Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization

Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization

Event-based Motion Segmentation by Cascaded Two-Level Multi-Model Fitting

Multi‐Event‐Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

Contact Info

Product

Resources

About