Results 1 - 10
of
45
Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization
"... Abstract. The sparse representation has been widely used in many areas and utilized for visual tracking. Tracking with sparse representation is formulated as searching for samples with minimal reconstruction errors from learned template subspace. However, the computational cost makes it unsuitable t ..."
Abstract
-
Cited by 23 (2 self)
- Add to MetaCart
Abstract. The sparse representation has been widely used in many areas and utilized for visual tracking. Tracking with sparse representation is formulated as searching for samples with minimal reconstruction errors from learned template subspace. However, the computational cost makes it unsuitable
Robust Visual Tracking Via Consistent Low-Rank Sparse Learning
- INT J COMPUT VIS
, 2014
"... Object tracking is the process of determining the states of a target in consecutive video frames based on properties of motion and appearance consistency. In this paper, we propose a consistent low-rank sparse tracker (CLRST) that builds upon the particle filter framework for tracking. By exploiting ..."
Abstract
- Add to MetaCart
Object tracking is the process of determining the states of a target in consecutive video frames based on properties of motion and appearance consistency. In this paper, we propose a consistent low-rank sparse tracker (CLRST) that builds upon the particle filter framework for tracking
VIDEO DENOISING BY SPARSE 3D TRANSFORM-DOMAIN COLLABORATIVE FILTERING
"... We propose an e¤ective video denoising method based on highly sparse signal representation in local 3D transform domain. A noisy video is processed in blockwise manner and for each processed block we form a 3D data array that we call “group ” by stacking together blocks found similar to the currentl ..."
Abstract
-
Cited by 42 (6 self)
- Add to MetaCart
grouped blocks. This …ltering— that we term “collaborative …ltering” — exploits the correlation between grouped blocks and the corresponding highly sparse representation of the true signal in the transform domain. Since, in general, the obtained block estimates are mutually overlapping, we aggregate them
CONDENSATION-Conditional Density Propagation for Visual Tracking
, 1998
"... Abstract. The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent simultaneous alternative hypotheses. The Condensation algorithm uses "factored sampling", previ ..."
Abstract
- Add to MetaCart
Abstract. The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot represent simultaneous alternative hypotheses. The Condensation algorithm uses "factored sampling
Journal of Scientific Computing manuscript No. (will be inserted by the editor) Data-driven Multi-scale Non-local Wavelet Frame Construction and Image Recovery
"... Abstract By assuming that images of interest can be sparsely modelled by some transform, the sparsity-based regularization has been one promising approach for solving many ill-posed inverse problems in image recovery. One often-used type of systems for sparsifying images is wavelet tight frames, whi ..."
Abstract
- Add to MetaCart
Abstract By assuming that images of interest can be sparsely modelled by some transform, the sparsity-based regularization has been one promising approach for solving many ill-posed inverse problems in image recovery. One often-used type of systems for sparsifying images is wavelet tight frames
3D Human Pose Recovery from Monocular Images via Efficient Visual Feature Selection
"... In this paper we propose a new examplar-based approach to recover 3D human poses from monocular images. Given the visual feature of each frame, pose retrieval is first conducted in the examplar database to find relevant pose candidates. Then, dynamic programming is applied on the weighted set of can ..."
Abstract
- Add to MetaCart
In this paper we propose a new examplar-based approach to recover 3D human poses from monocular images. Given the visual feature of each frame, pose retrieval is first conducted in the examplar database to find relevant pose candidates. Then, dynamic programming is applied on the weighted set
SIMULATION, DEVELOPMENT AND DEPLOYMENT OF MOBILE WIRELESS SENSOR NETWORKS FOR MIGRATORY BIRD TRACKING
, 2012
"... This thesis presents CraneTracker, a multi-modal sensing and communication system for monitoring migratory species at the continental level. By exploiting the robust and extensive cellular infrastructure across the continent, traditional mobile wireless sensor networks can be extended to enable reli ..."
Abstract
- Add to MetaCart
reliable, low-cost monitoring of migratory species. The developed multi-tier architecture yields ecologists with unconventional behavior in-formation not furnished by alternative tracking systems at such a large scale and for a low-cost. The simulation, development and implementation of the Crane
DETC2004-57731 CRITICAL CAPABILITIES FOR SUCCESSFUL DISTRIBUTED COLLABORATIVE PRODUCT DEVELOPMENT
"... ABSTRACT Discrete manufacturing companies practicing distributed product development encounter challenges creating digital products, collaborating cross functionally in an organization and throughout the value chain, and controlling and managing product information and product development processes ..."
Abstract
- Add to MetaCart
ABSTRACT Discrete manufacturing companies practicing distributed product development encounter challenges creating digital products, collaborating cross functionally in an organization and throughout the value chain, and controlling and managing product information and product development
unknown title
"... nv c, neti me 8, U Sparse representation Non-convex optimization s si the ng W proposed. It has better performance in preserving image edges than conventional sparsifying transforms. are presented in the smooth region when the data are highly undersampled. In RI) is ical str ..."
Abstract
- Add to MetaCart
nv c, neti me 8, U Sparse representation Non-convex optimization s si the ng W proposed. It has better performance in preserving image edges than conventional sparsifying transforms. are presented in the smooth region when the data are highly undersampled. In RI) is ical str
1On the Identifiability of Overcomplete Dictionaries via the Minimisation Principle Underlying K-SVD
, 2013
"... This article gives theoretical insights into the performance of K-SVD, a dictionary learning algorithm that has gained significant popularity in practical applications. The particular question studied here is when a dictionary Φ ∈ Rd×K can be recovered as local minimum of the minimisation criterion ..."
Abstract
- Add to MetaCart
size, sampling complexity, dictionary identification, minimisation criterion, sparse representation 1
Results 1 - 10
of
45