Results 71 to 80 of about 1,277,276 (186)
IEEE Access, 2020 Human action recognition is an important research topic in the field of computer vision due to its application values. Recently, a variety of approaches based on deep learning features have been proposed due to the effectiveness of deep neural networks ...
Yanqin Wan +3 more
doaj +1 more source
Decomposition of optical flow on the sphere [PDF]
GEM - International Journal on Geomathematics, 2014 The final publication is available at link.springer ...
Kirisits, Clemens +2 more
openaire +3 more sources
Selectivity to approaching motion in retinal inputs to the dorsal visual pathway
eLife, 2020 To efficiently navigate through the environment and avoid potential threats, an animal must quickly detect the motion of approaching objects. Current models of primate vision place the origins of this complex computation in the visual cortex.
Todd R Appleby, Michael B Manookin
doaj +1 more source
Inviscid Flow Field Effects: Experimental results [PDF]
, 1980 The aero-optical distortions due to invisid flow effects over airborne laser turrets is investigated. Optical path differences across laser turret apertures are estimated from two data sources.
Gilbert, K. G., Otten, L. J., III
core +1 more source
Morphing a Stereogram into Hologram
Journal of Imaging, 2020 We developed a method to transform stereoscopic two-dimensional (2D) images into holograms via unsupervised morphing deformations between left (L) and right (R) input images.
Enrique Canessa, Livio Tenze
doaj +1 more source
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes
, 2022 Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance degrades at regions
Dai, Yuchao +4 more
core
Influence of phosphorus doping on hydrogen content and optical losses in PECVD silicon oxynitride [PDF]
, 2005 PECVD Phosphorus-doped silicon oxynitride layers (n=1.5) were deposited from N2O, 2%SiH4/N2, NH3 and 5%PH3/Ar gaseous mixtures. Chemical bonds were determined by Fourier transform infrared spectroscopy. N–H bond concentration of the layers decreased from
Driessen, A. +3 more
core +1 more source
Self-Supervised Pre-Training for Optical Flow Estimation via Contrastive Learning
IEEE AccessTo address the issues of dataset dependency and correlation volume redundancy in optical flow estimation, contrastive learning is introduced to build a self supervised optical flow framework.
Feng An, Wenyin Tao
doaj +1 more source
Drone SLAM using TDOA-RSS signal with applied EKF on PF data [PDF]
FME Transactions, 2019 This paper describes the integration of Particle filter data earlier recorded in simulation and tested in real-time scenario. Those data are parsed from beacon listener using TDOA-RSS inverse method.
Šoštarić Damir, Mester Gyula
doaj
Horn-Schunck Optical Flow with a Multi-Scale Strategy
Image Processing On Line, 2013 The seminal work of Horn and Schunck is the first variational method for optical flow estimation. It introduced a novel framework where the optical flow is computed as the solution of a minimization problem.
Enric Meinhardt-Llopis +2 more
doaj