Journal ArticleDOI
Quantization analysis and enhancement of a VLSI gradient-based motion estimation architecture
TLDR
A useful framework for building bio-inspired systems in real-time environments, reducing computational complexity is presented, and a complete quantization study of neuromorphic robust optical flow architecture is performed, using properties found in the cortical motion pathway.About:
This article is published in Digital Signal Processing.The article was published on 2012-12-01. It has received 47 citations till now. The article focuses on the topics: Optical flow & Motion estimation.read more
Citations
More filters
Journal ArticleDOI
A weighted mean filter with spatial-bias elimination for impulse noise removal
TL;DR: Compared to the state-of-the-art impulse noise removal methods, UWMF provides superior performance, without requiring a fine-tuning for its parameters, in terms of both objective measurements and subjective assessments.
Journal ArticleDOI
An edge-weighted second order variational model for image decomposition
TL;DR: An edge-weighted second order variational model for image decomposition, which is able to eliminate staircase effects and preserve object edges is proposed and a fast split Bregman algorithm is developed, which uses the fast Fourier transform and analytical generalised soft thresholding equations to avoid directly calculating the high order nonlinear partial differential equations.
Journal ArticleDOI
Image contrast enhancement using fuzzy clustering with adaptive cluster parameter and sub-histogram equalization
TL;DR: A method is introduced for automatic determination of the number of sub-histograms and density based histogram division leading to appropriate output with no need for parameter setting and demonstrates not only clearer details along with a boost in contrast, but also noticeably more natural appearance in the images.
Journal ArticleDOI
Weighted local intensity fusion method for variational optical flow estimation
TL;DR: A local intensity fusion (LIF) method that fuse flow proposals which are obtained from different methods and from different parameter settings integrally under a unified LIF, and a corrected weighted median filter (CWMF) which applies the motion information to correct errors of the color distance weight to denoise the intermediate flow fields during optimization.
Journal ArticleDOI
A Single Image Dehazing Method Using Average Saturation Prior
TL;DR: An improved atmospheric scattering model is proposed to overcome this inherent limitation of the model and outperforms several state-of-the-art single image dehazing methods in terms of both robustness and effectiveness.
References
More filters
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
Determining Optical Flow
TL;DR: In this article, 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.
Journal ArticleDOI
Performance of optical flow techniques
TL;DR: These comparisons are primarily empirical, and concentrate on the accuracy, reliability, and density of the velocity measurements; they show that performance can differ significantly among the techniques the authors implemented.
Journal ArticleDOI
Lucas-Kanade 20 Years On: A Unifying Framework
Simon Baker,Iain Matthews +1 more
TL;DR: In this paper, a wide variety of extensions have been made to the original formulation of the Lucas-Kanade algorithm and their extensions can be used with the inverse compositional algorithm without any significant loss of efficiency.
Journal ArticleDOI
Neuromorphic electronic systems
TL;DR: It is shown that for many problems, particularly those in which the input data are ill-conditioned and the computation can be specified in a relative manner, biological solutions are many orders of magnitude more effective than those using digital methods.