Filters








15,546 Hits in 4.6 sec

Motion Adaptive Spatio-Temporal Gaussian Noise Reduction Filter for Double-Shot Images

Shao-Yi Chien, Tse-Wei Chen
2007 Multimedia and Expo, 2007 IEEE International Conference on  
Temporal average and 2-D adaptive filter is applied for static regions, where spatio-temporal filter with motion compensation is only applied for dynamic regions.  ...  In this paper, a motion adaptive spatio-temporal filter is proposed for double-shot images to achieve high performance with low computing power requirement.  ...  Another example of spatio-temporal filter is the selective filter based on doubleshot pictures [8] .  ... 
doi:10.1109/icme.2007.4284986 dblp:conf/icmcs/ChienC07 fatcat:ys4dapyjg5dktk6tpuo4onws7m

Spatio-temporal correlation based fast motion estimation algorithm for MPEG-2

K. Ramkishor, S. Krishna
2001 Conference Record of Thirty-Fifth Asilomar Conference on Signals, Systems and Computers (Cat.No.01CH37256)  
The algorithm is based on spatial and temporal correlation of motion vectors. The algorithm yields good tradeoff between motion estimation distortion and number of computations.  ...  The number of bits required to code motion vectors is less as the algorithm is based on correlation of motion vectors.  ...  Conclusions A fast motion estimation algorithm with adaptive search range based on spatial and temporal correlation of motion vectors is presented.  ... 
doi:10.1109/acssc.2001.986909 fatcat:ei6x4eeenfdipaawx7abltxr2m

Noise Reduction in Video Sequences The State of Art and the Technique for Motion Detection

Reeja S.R, N. P. Kavya
2012 International Journal of Computer Applications  
The first level can be achieved through Motion Detection. This paper explained about the motion estimation and compensation techniques.  ...  The different video denoising techniques, motion detection techniques and the noises used are shown through the taxonomy.  ...  A pixel based spatio-temporal adaptive filter that calculates new pixel values adaptively using the weighted mean of pixels over motion compensated frames has been proposed in [5] .  ... 
doi:10.5120/9304-3526 fatcat:iihsvtty6jfeln5qwjwwn7vmxa

Temporal gradient-domain path tracing

Marco Manzi, Markus Kettunen, Frédo Durand, Matthias Zwicker, Jaakko Lehtinen
2016 ACM Transactions on Graphics  
We further extend our approach to include second order, mixed spatio-temporal differences, an improved technique to compute temporal differences exploiting motion vectors, and adaptive sampling.  ...  Building on previous gradient-domain rendering techniques that sample finite differences over the image plane, we introduce temporal finite differences and formulate a corresponding 3D spatio-temporal  ...  These properties contrast previous algorithms, including sample reprojection, spatio-temporal filtering, and the construction of smooth spatio-temporal function bases for the frames.  ... 
doi:10.1145/2980179.2980256 fatcat:kiv3fmwwhffl5au6xxe5caiam4

Wavelet-based denoising for 3D OCT images

Vladimir Zlokolica, Ljubomir Jovanov, Aleksandra Pižurica, Paul De Keyser, Frans Dhaenens, Wilfried Philips, Andrew G. Tescher
2007 Applications of Digital Image Processing XXX  
The temporal filtering scheme reduces the noise level and adapts the motion compensation on it.  ...  In the proposed method we first perform recursive temporal filtering through the estimated motion trajectory between the 2D slices using noise-robust motion estimation/compensation scheme previously proposed  ...  In the motion estimation, we make use of spatial image discontinuities, represented by wavelet coefficients, in combination with spatio-temporal correlations of the motion vectors, within a recursive scheme  ... 
doi:10.1117/12.734286 fatcat:lou4nyi6u5hm7bo77yzhnqukt4

Layered Estimation of Atmospheric Mesoscale Dynamics From Satellite Imagery

Patrick Heas, Etienne Memin, Nicolas Papadakis, AndrÉ Szantai
2007 IEEE Transactions on Geoscience and Remote Sensing  
This estimator is expressed as the minimization of a global function including data and spatio-temporal smoothness terms.  ...  This alternative approach relies on the combination of correlation and optical-flow observations in a variational context.  ...  This incremental motion estimate relies neither on correlation-based vectors nor on spatio-temporal constraints, which only apply at large scales.  ... 
doi:10.1109/tgrs.2007.906156 fatcat:mhsfir5kefh4nclgvzjvqnprlu

Efficient motion weighted spatio-temporal video SSIM index

Anush K. Moorthy, Alan C. Bovik, Bernice E. Rogowitz, Thrasyvoulos N. Pappas
2010 Human Vision and Electronic Imaging XV  
Spatio-temporal video SSIM utilizes motion information computed from a block-based motion-estimation algorithm and quality measures using a localized set of oriented spatio-temporal filters.  ...  In order to bridge the gap between the conceptual elegance of MOVIE and a practical VQA algorithm, we propose a new VQA algorithm -the spatio-temporal video SSIM based on the essence of MOVIE.  ...  Spatio-temporal quality assessment is undertaken using a modified version of SS-SSIM, which we shall consider in the next section.  ... 
doi:10.1117/12.844198 dblp:conf/hvei/MoorthyB10 fatcat:dksiomvzdrdgbjfk3r5h7wmxlm

Wavelet-Domain Video Denoising Based on Reliability Measures

V. Zlokolica, A. Pizurica, W. Philips
2006 IEEE transactions on circuits and systems for video technology (Print)  
In the proposed method, motion estimation and adaptive recursive temporal filtering are performed in a closed loop, followed by an intra-frame spatially adaptive filter.  ...  The temporal filtering is performed separately in each wavelet band along the estimated motion trajectory and the parameters of the temporal filter depend on the motion reliabilities per wavelet band.  ...  Based on the estimated MVs and the corresponding reliability per wavelet band, we perform adaptive temporal filtering within each wavelet band.  ... 
doi:10.1109/tcsvt.2006.879994 fatcat:hgwflu435jfbxclayrrdp6aysm

Denoising Algorithm for CFA Image Sensors Considering Inter-Channel Correlation

Min Lee, Sang Park, Moon Kang
2017 Sensors  
Second, a motion-compensated temporal filter that employs inter-channel correlated motion estimation and compensation is proposed to remove the noise in the temporal domain.  ...  Then, a motion adaptive detection value controls the ratio of the spatial filter and the temporal filter. The denoised CFA sequence can thus be obtained without motion artifacts.  ...  A motion-compensated temporal filter based on MCP using inter-channel correlated motion estimation was additionally proposed.  ... 
doi:10.3390/s17061236 pmid:28555044 pmcid:PMC5492375 fatcat:evgzvzbu2zdwzlcwl6gi3d7ava

Spatio-Temporal Video Object Segmentation via Scale-Adaptive 3D Structure Tensor

Hai-Yun Wang, Kai-Kuang Ma
2004 EURASIP Journal on Advances in Signal Processing  
the duality of image segmentation and motion estimation such that spatial and temporal information could assist each other to jointly yield much improved segmentation results.  ...  The key novelties of our method are (1) scale-adaptive tensor computation, (2) spatial-constrained motion mask generation without invoking dense motion-field computation, (3) rigidity analysis, (4) motion  ...  Therefore, it is highly desirable to have adaptive scale for the spatio-temporal filtering rather than using fixed scale.  ... 
doi:10.1155/s111086570440122x fatcat:xjfukf6k3zboxgi7zgqnlamsam

Progressive Dictionary Learning With Hierarchical Predictive Structure for Low Bit-Rate Scalable Video Coding

Wenrui Dai, Yangmei Shen, Hongkai Xiong, Xiaoqian Jiang, Junni Zou, David Taubman
2017 IEEE Transactions on Image Processing  
For pyramidal layers, sparse representation based on spatio-temporal dictionary is adopted to improve the coding efficiency of enhancement layers with a guarantee of reconstruction performance.  ...  The overcomplete dictionary is trained to adaptively capture local structures along motion trajectories as well as exploit the correlations between the neighboring layers of resolutions.  ...  Since the spatio-temporal consistency tends to be maintained in both BL and EL, the motion estimation and compensation in EL is performed based on the motion vector derived in BL.  ... 
doi:10.1109/tip.2017.2692882 pmid:28422683 pmcid:PMC5638692 fatcat:yrf6mgcpojezvjhmiuvmvqklne

Visual learning and recognition of a probabilistic spatio-temporal model of cyclic human locomotion

M. Peternel, A. Leonardis
2004 Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.  
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person.  ...  For recognition, we use maximum a posteriori estimate combined with linear data adaptation.  ...  We present a novel method for representation of articu-late cyclic motion based on a set of spatio-temporal trajectories of continuously tracked points on the surface of the observed object.  ... 
doi:10.1109/icpr.2004.1333725 dblp:conf/icpr/PeternelL04 fatcat:5vqfx5auqbhnncjihavoaw2ipm

Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation [article]

Jose Caballero, Christian Ledig, Andrew Aitken, Alejandro Acosta, Johannes Totz, Zehan Wang, Wenzhe Shi
2017 arXiv   pre-print
However, recent attempts to benefit from temporal correlations in video super-resolution have been limited to naive or inefficient architectures.  ...  We also propose a novel joint motion compensation and video super-resolution algorithm that is orders of magnitude more efficient than competing methods, relying on a fast multi-resolution spatial transformer  ...  Estimating and compensating motion is a powerful mechanism to further constrain the problem and expose temporal correlations.  ... 
arXiv:1611.05250v2 fatcat:yjz4767vfnd3tgiwy3ufkzwt2a

Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation

Jose Caballero, Christian Ledig, Andrew Aitken, Alejandro Acosta, Johannes Totz, Zehan Wang, Wenzhe Shi
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
However, recent attempts to benefit from temporal correlations in video superresolution have been limited to naive or inefficient architectures.  ...  We also propose a novel joint motion compensation and video super-resolution algorithm that is orders of magnitude more efficient than competing methods, relying on a fast multi-resolution spatial transformer  ...  Estimating and compensating motion is a powerful mechanism to further constrain the problem and expose temporal correlations.  ... 
doi:10.1109/cvpr.2017.304 dblp:conf/cvpr/CaballeroLAATWS17 fatcat:br7ijilclfew7lth54wh2lf6yy

Adaptive motion estimation and video vector quantization based on spatiotemporal non-linearities of human perception [chapter]

J. Malo, F. Ferri, J. Albert, J. M. Artigas
1997 Lecture Notes in Computer Science  
The two main tasks of a video coding system are motion estimation and vector quantization of the signal.  ...  In this work a new splitting criterion to control the adaptive decomposition for the nonuniform optical flow estimation is exposed.  ...  [4] proposed a splitting criterion for adaptive-block-size motion estimation based on minimizing the entropy of the corrections and displacement field.  ... 
doi:10.1007/3-540-63507-6_232 fatcat:yaqzbnhcxzc5zablwgiaklciwq
« Previous Showing results 1 — 15 out of 15,546 results