Feature Tracks are not Zero-Mean Gaussian

• URL: http://arxiv.org/abs/2303.14315v1
• Date: Sat, 25 Mar 2023 00:58:30 GMT
• Title: Feature Tracks are not Zero-Mean Gaussian
• Authors: Stephanie Tsuei, Wenjie Mo, Stefano Soatto
• Abstract summary: It is customary to assume that the errors in feature track positions are zero-mean Gaussian. Using a combination of calibrated camera intrinsics, ground-truth camera pose, and depth images, it is possible to compute ground-truth positions for feature tracks extracted using an image processing algorithm.
• Score: 63.51990384359593
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In state estimation algorithms that use feature tracks as input, it is customary to assume that the errors in feature track positions are zero-mean Gaussian. Using a combination of calibrated camera intrinsics, ground-truth camera pose, and depth images, it is possible to compute ground-truth positions for feature tracks extracted using an image processing algorithm. We find that feature track errors are not zero-mean Gaussian and that the distribution of errors is conditional on the type of motion, the speed of motion, and the image processing algorithm used to extract the tracks.

Related papers

• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum [56.37522020675243]
  We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. We show that due to their larger allowable stepsizes, our new normalized error feedback algorithms outperform their non-normalized counterparts on various tasks.
  arXiv  Detail & Related papers  (2024-10-22T10:19:27Z)
• Learning to Make Keypoints Sub-Pixel Accurate [80.55676599677824]
  This work addresses the challenge of sub-pixel accuracy in detecting 2D local features. We propose a novel network that enhances any detector with sub-pixel precision by learning an offset vector for detected features.
  arXiv  Detail & Related papers  (2024-07-16T12:39:56Z)
• Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes [1.3581810800092389]
  We propose a novel method called Random Walk on Pixel Manifolds (RWPM) RWPM utilizes random walks to reveal the intrinsic relationships among pixels to refine the pixel embeddings. Our experiments show that RWPM consistently improve the performance of the existing anomaly segmentation methods.
  arXiv  Detail & Related papers  (2024-04-27T17:16:45Z)
• Deep Dynamic Scene Deblurring from Optical Flow [53.625999196063574]
  Deblurring can provide visually more pleasant pictures and make photography more convenient. It is difficult to model the non-uniform blur mathematically. We develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features.
  arXiv  Detail & Related papers  (2023-01-18T06:37:21Z)
• Real-time AdaBoost cascade face tracker based on likelihood map and optical flow [59.17685450892182]
  The authors present a novel face tracking approach where optical flow information is incorporated into a modified version of the Viola Jones detection algorithm. In the original algorithm, detection is static, as information from previous frames is not considered. The proposed tracker preserves information about the number of classification stages passed by each window.
  arXiv  Detail & Related papers  (2022-10-25T10:15:07Z)
• Variational Bayes for robust radar single object tracking [5.390933335965428]
  We address object tracking by radar and the robustness of the current state-of-the-art methods to process outliers. We take the Gaussian Sum Filter as our baseline and propose a modification by modelling process noise with a distribution that has heavier tails than a Gaussian. Our simulations show that - in the presence of process outliers - the robust tracker outperforms the Gaussian Sum filter when tracking single objects.
  arXiv  Detail & Related papers  (2022-09-28T19:41:33Z)
• TomoSLAM: factor graph optimization for rotation angle refinement in microtomography [0.0]
  Relative trajectories of a sample, a detector, and a signal source are traditionally considered to be known. Due to mechanical backlashes, rotation sensor measurement errors, thermal deformations real trajectory differs from desired ones. The scientific novelty of this work is to consider the problem of trajectory refinement in microtomography as a SLAM problem.
  arXiv  Detail & Related papers  (2021-11-10T08:00:46Z)
• Occlusion-aware Visual Tracker using Spatial Structural Information and Dominant Features [0.19036571490366497]
  The proposed algorithm divides the object into discrete image patches according to the pixel distribution of the object by means of clustering. To avoid the drifting of the tracker to false targets, the proposed algorithm extracts the dominant features, such as color histogram or histogram of gradient orientation, from these image patches. The proposed algorithm incorporates these components into the particle filter framework, which results in a robust and precise tracker.
  arXiv  Detail & Related papers  (2021-04-16T09:01:45Z)
• Superaccurate Camera Calibration via Inverse Rendering [0.19336815376402716]
  We propose a new method for camera calibration using the principle of inverse rendering. Instead of relying solely on detected feature points, we use an estimate of the internal parameters and the pose of the calibration object to implicitly render a non-photorealistic equivalent of the optical features.
  arXiv  Detail & Related papers  (2020-03-20T10:26:16Z)

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.