Results 41 to 50 of about 341,318 (278)
, 2015 Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset.
Brox, Thomas +6 more
core +1 more source
Journal of Open Research Software, 2021 This paper describes OpenOpticalFlow_PIV, an open source Matlab program integrating the optical flow method with the cross-correlation method for extraction of high-resolution velocity fields from particle images with large displacements.
Tianshu Liu, David M. Salazar
doaj +1 more source
Research on traditional and deep learning strategies based on optical flow estimation - a review
Journal of King Saud University: Computer and Information SciencesOptical flow estimation captures the motion information of objects in a scene through analyzing the displacement of pixels in an image over time. This technology provides a powerful tool for vision systems, allowing them to understand and perceive ...
Yifan Wang +8 more
doaj +1 more source
Guided Filtering: Toward Edge-Preserving for Optical Flow
IEEE Access, 2018 Despite progress made in the accuracy and robustness of optical flow in past years, the problem of over-segmentation and the blurring of image edge and motion boundary caused by the illumination change, complex texture, large displacement, and motion ...
Congxuan Zhang +5 more
doaj +1 more source
FGBRSN: Flow-Guided Gated Bi-Directional Recurrent Separated Network for Video Super-Resolution
IEEE Access, 2023 Video Super-Resolution (VSR) is the task of reconstructing high-resolution (HR) video sequences from low-resolution (LR) video sequences. Apart from spatial information of reference frames, temporal information of neighboring frames is also important for
Weikang Xue +4 more
doaj +1 more source
Improved Discrete Optical Flow Estimation With Triple Image Matching Cost
IEEE Access, 2020 Approaches that use more than two consecutive video frames in the optical flow estimation have a long research history. However, almost all such methods utilize extra information for a pre-processing flow prediction or for a post-processing flow ...
Fei Yang +3 more
doaj +1 more source
A Motion Refinement Network With Local Compensation for Video Frame Interpolation
IEEE Access, 2023 Video frame interpolation (VFI) is a challenging yet promising task that involves synthesizing intermediate frames from two given frames. State-of-the-art approaches have made significant progress by directly synthesizing images using forward optical ...
Kaiqiao Wang, Peng Liu
doaj +1 more source
A Fusion Approach for Multi-Frame Optical Flow Estimation
, 2018 To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results.
Gallo, Orazio +5 more
core +2 more sources
Robust Optical Flow Estimation in Mpeg Sequences [PDF]
Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., 2006 Motion information is essential in many computer vision and video analysis tasks. Since MPEG is still one of the most prevalent formats for representing, transferring and storing video data, the analysis of its motion field is important for real time video indexing and segmentation, event analysis and surveillance applications.
Ζερβακης Μιχαλης(http://users.isc.tuc.gr/~mzervakis) +2 more
openaire +2 more sources
A Dense Optical Flow Field Estimation with Variational Refinement
Journal of Engineering Technology and Applied Physics, 2019 Optical flow has long been a focus of research study in computer vision community. Researchers have established extensive work to solve the optical flow estimation.
Wei Yong Eng +3 more
doaj +1 more source