Within the last year
Within the past 3 years
1 - 10 of 14 articles
Highlights ► Heavy computational load in visual tracking. ► Global and local view of natural motion. ► Coarse-to-fine tracking strategy. ► Adaptation to motion change. ► Significant reduction in computational load.
Research highlights ► Mixtures of uniform distributions and multivariate Gaussians with full covariance matrices are proposed for background modelling. ► A learning algorithm is derived from the stochastic approximation framework, which has a reduced computational complexity. ► Real time...
Highlights ► We propose a general algorithm for automating interactive segmentation evaluation. ► We suggest four methods for simulating user interactions. ► We compare results from each method to real user interactions. ► A validation study shows that automated evaluation is feasible and...
Research highlights ► Image segmentation algorithms versus their continuous models. ► Model (asymptotic) equivalence of image segmentation algorithms. ► Model equivalence of some fuzzy connectedness and level set segmentation algorithms.
Research highlights ► We propose a Markov random field based sign ambiguity resolution method in interferometry (MSRAI). ► MSARI outperforms traditional path following phase demodulation methods. ► We propose the use of Multilevel Quadratic Pseudo-Boolean Optimization method. ► It better...
Research highlights ► Novel iris representations based on binary features from the multi-scale Taylor expansion. ► Enhancement of the local extrema-based approach with efficient matching. ► Combination of the above two performs with highest recognition rates. ► Evaluation results provided...
Highlights ► Novel idea to analyze corneal reflections of screen illumination in the human eye. ► Novel method for calibrating the geometric relation in display-camera setups. ► Method does not require any user interaction or awareness and special hardware. ► Optimization framework leads...
Research highlights ► Region labeling is successfully faced as OVA multiclass classification. ► We study the benefits offered by OVA classification to region labeling. ► Introduce model that refines the output of a classifier by using co-occurrences. ► Our method is easier to implement...
Highlights ►Video-rate camera tracking and scene mapping extended to multiple maps and cameras. ► Augmented reality established in localized maps with automated switching between. ► Uses portable computer, wearable and hand-held cameras, and i/o via touchscreen. ► Operation demonstrated...
Save this article to read later. You can see your Read Later on your DeepDyve homepage.
To save an article, log in first, or sign up for a DeepDyve account if you don't already have one.
Sign Up Log In
To subscribe to email alerts, please log in first, or sign up for a DeepDyve account if you don't already have one.
Read and print from thousands of top scholarly journals.
Sign up with Facebook
Sign up with Google
Already have an account? Log in
To get new article updates from a journal on your personalized homepage, please log in first, or sign up for a DeepDyve account if you don't already have one.