Proceedings ArticleDOI
Robust local optical flow: Dense motion vector field interpolation
Jonas Geistert,Tobias Senst,Thomas Sikora +2 more
- pp 1-5
TLDR
Compared to state-of-the-art methods the proposed approach is significantly faster while retaining competitive accuracy on Middlebury, KITTI 2015 and MPI-Sintel data-set.Abstract:
Optical flow methods integrating sparse point correspondences have made significant contribution in the field of optical flow estimation. Especially for the goal of estimating motion accurately and efficiently, sparse-to-dense interpolation schemes for feature point matches have shown outstanding performances. Concurrently, local optical flow methods have been significantly improved with respect to long-range motion estimation in environments with varying illumination. This motivates us to propose a sparse-to-dense approach based on the Robust Local Optical Flow method. Compared to state-of-the-art methods the proposed approach is significantly faster while retaining competitive accuracy on Middlebury, KITTI 2015 and MPI-Sintel data-set.read more
Citations
More filters
Proceedings ArticleDOI
Optical Flow Dataset and Benchmark for Visual Crowd Analysis
TL;DR: In this paper, the authors introduce a new optical flow dataset exploiting the possibilities of a recent video engine to generate sequences with ground-truth optical flow for large crowds in different scenarios and evaluate different optical flow algorithms.
Journal ArticleDOI
Whole-pixel registration of non-rigid images using correspondences interpolation on sparse feature seeds
TL;DR: This work detects and match two types of feature seeds to improve the accuracy of the later dense CVF interpolation and realizes the whole-pixel registration of non-rigid images to yield the image alignment.
Posted Content
Optical Flow Dataset and Benchmark for Visual Crowd Analysis
TL;DR: A new optical flow dataset is introduced exploiting the possibilities of a recent video engine to generate sequences with ground-truth optical flow for large crowds in different scenarios, breaking with the development of the last decade of introducing ever increasing displacements to pose new difficulties.
Proceedings ArticleDOI
Degraf-Flow: Extending Degraf Features for Accurate and Efficient Sparse-To-Dense Optical Flow Estimation
TL;DR: Evaluation on established real-world benchmark datasets show test performance in an autonomous vehicle setting where DeGraF-Flow shows promising results in terms of accuracy with competitive computational efficiency among non-GPU based methods, including a marked increase in speed over the conceptually similar EpicFlow approach.
Posted Content
DeGraF-Flow: Extending DeGraF Features for accurate and efficient sparse-to-dense optical flow estimation
TL;DR: DeGraF-Flow as mentioned in this paper uses dense gradient-based features as the input to a sparse-to-dense optical flow estimation method for real-time optical flow recovery.
References
More filters
Proceedings Article
An iterative image registration technique with an application to stereo vision
Bruce D. Lucas,Takeo Kanade +1 more
TL;DR: In this paper, the spatial intensity gradient of the images is used to find a good match using a type of Newton-Raphson iteration, which can be generalized to handle rotation, scaling and shearing.
Journal ArticleDOI
Determining optical flow
TL;DR: In this paper, a method for finding the optical flow pattern is presented which assumes that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image, and an iterative implementation is shown which successfully computes the Optical Flow for a number of synthetic image sequences.
Proceedings ArticleDOI
Good features to track
Jianbo Shi,Tomasi +1 more
TL;DR: A feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world are proposed.
Book ChapterDOI
Machine learning for high-speed corner detection
Edward Rosten,Tom Drummond +1 more
TL;DR: It is shown that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time.
Journal Article
Machine Learning for High-Speed Corner Detection
Edward Rosten,Tom Drummond +1 more
TL;DR: In this paper, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations, and a comparison of corner detectors based on this criterion applied to 3D scenes is made.