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

• URL: http://arxiv.org/abs/2107.04536v1
• Date: Fri, 9 Jul 2021 16:41:20 GMT
• Title: Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization
• Authors: Jason Chui, Simon Klenk, Daniel Cremers
• Abstract summary: We propose a novel method for continuous-time feature tracking in event cameras. We track features by aligning events along an estimated trajectory in space-time. We experimentally confirm that the proposed sliding-window B-spline optimization leads to longer and more accurate feature tracks.
• Score: 55.11913183006984
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• A Distributional View of High Dimensional Optimization [0.0]
  We motivate this view with an investigation of the failure point of classical optimization.<n>We consider the optimization of a randomly drawn objective function.<n>It further turns out that this distributional view provides insights into optimal step size control of gradient descent.
  arXiv  Detail & Related papers  (2025-07-22T07:56:01Z)
• Online Dense Point Tracking with Streaming Memory [54.22820729477756]
  Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video.<n>Recent point tracking algorithms usually depend on sliding windows for indirect information propagation from the first frame to the current one.<n>We present a lightweight and fast model with textbfStreaming memory for dense textbfPOint textbfTracking and online video processing.
  arXiv  Detail & Related papers  (2025-03-09T06:16:49Z)
• ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking [41.889032460337226]
  ProTracker is a novel framework for accurate and robust long-term dense tracking of arbitrary points in videos. This design effectively combines global semantic information with temporally aware low-level features. Experiments demonstrate that ProTracker attains state-of-the-art performance among optimization-based approaches.
  arXiv  Detail & Related papers  (2025-01-06T18:55:52Z)
• Event-ECC: Asynchronous Tracking of Events with Continuous Optimization [1.9446776999250501]
  We propose a tracking algorithm that computes a 2D motion warp per single event, called event-ECC (eECC) The computational burden of event-wise processing is alleviated through a lightweight version that benefits from incremental processing and updating scheme. We report improvements in tracking accuracy and feature age over state-of-the-art event-based asynchronous trackers.
  arXiv  Detail & Related papers  (2024-09-22T19:03:19Z)
• Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm [132.9949120482274]
  This paper focuses on the selection of samples for annotation in the pretraining-finetuning paradigm. We propose a novel method called ActiveFT for active finetuning task to select a subset of data distributing similarly with the entire unlabeled pool. Extensive experiments show the leading performance and high efficiency of ActiveFT superior to baselines on both image classification and semantic segmentation.
  arXiv  Detail & Related papers  (2023-03-25T07:17:03Z)
• DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment [41.27664827586102]
  Direct methods have shown excellent performance in the applications of visual odometry and SLAM. We propose a framework that effectively combines direct image alignment for the short-term tracking and sliding-window photometric bundle adjustment for 3D object detection.
  arXiv  Detail & Related papers  (2022-09-29T17:40:22Z)
• Asynchronous Optimisation for Event-based Visual Odometry [53.59879499700895]
  Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range. We focus on event-based visual odometry (VO) We propose an asynchronous structure-from-motion optimisation back-end.
  arXiv  Detail & Related papers  (2022-03-02T11:28:47Z)
• Jacobian Computation for Cumulative B-splines on SE(3) and Application to Continuous-Time Object Tracking [13.249453757295086]
  We propose a method that estimates the $SE(3)$ continuous trajectories (orientation and translation) of the dynamic rigid objects present in a scene, from multiple RGB-D views. We fit the object trajectories to cumulative B-Splines curves, which allow us to interpolate, at any intermediate time stamp, not only their poses but also their linear and angular velocities and accelerations.
  arXiv  Detail & Related papers  (2022-01-25T19:53:33Z)
• Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering [53.523517926927894]
  We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics. We prove that our model-based procedure converges in noisy gradient setting. This is an interesting step for constructing self-tuning quadratics.
  arXiv  Detail & Related papers  (2020-11-09T22:07:30Z)
• Faster object tracking pipeline for real time tracking [0.0]
  Multi-object tracking (MOT) is a challenging practical problem for vision based applications. This paper showcases a generic pipeline which can be used to speed up detection based object tracking methods.
  arXiv  Detail & Related papers  (2020-11-08T06:33:48Z)
• Stochastic Optimization with Laggard Data Pipelines [65.20044914532221]
  We show that "dataechoed" extensions of common optimization methods exhibit provable improvements over their synchronous counterparts. Specifically, we show that in convex optimization with minibatches, data echoing affords speedups on the curvature-dominated part of the convergence rate, while maintaining the optimal statistical rate.
  arXiv  Detail & Related papers  (2020-10-26T14:55:31Z)
• PnPNet: End-to-End Perception and Prediction with Tracking in the Loop [82.97006521937101]
  We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles. We propose Net, an end-to-end model that takes as input sensor data, and outputs at each time step object tracks and their future level.
  arXiv  Detail & Related papers  (2020-05-29T17:57:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.