Select All | Select None
You can now keep track of new articles from Computer Vision and Image Understanding on your personalized homepage!
Highlights ► We improve sub-pixel matching for various vision problems merely through upsampling. ► It has been thoroughly discussed how scale changes affect data and regularization terms. ► We fuse results in different scales for effective error suppression. ► Effectiveness has been...
Highlights ► We propose a novel moving object detection algorithm. ► The algorithm is based on chromaticity difference model and brightness ratio model. ► Chromaticity difference model estimates the intensity difference of false foreground pixels. ► Brightness ratio model estimates the...
Highlights ► We present a graph matching method to solve the point-set correspondence problem. ► It is posed in a principled way and allows to detect outliers. ► We use relational geometrical information and soft assignments. ► We present image matching and shape retrieval experiments,...
Highlights ► We model irregular pupil boundary localization with orthogonal polynomials (OP). ► We examine local regularities using the point spread operators in the OP model. ► Edge map separates significant edge from the noise using statistical test. ► Pupil boundary points are...
Highlights ► We propose a context based system for detecting suspicious behaviour. ► We propose a context space model for distinguishing between different contexts. ► We propose the use of data stream clustering for updating and retrieving knowledge. ► We propose an inference algorithm...
Highlights ► Integrated framework for multimodal registration, sensor fusion, and tracking. ► Application in approximately far-range scene monitoring using uncalibrated cameras. ► Comprehensive survey of multimodal video surveillance state-of-the-art methods. ► Iterative feedback scheme...
Highlights ► We study the visual word incoherence, which is characterized by visually similar patches being hosted in different, not neighboring visual words. ► Visual synonyms, are linkages between visual words containing visually similar patches and present an algorithm for extracting...
Highlights ► We present two systems (CIS1 and CIS2) that allow external access to the aperture of an imaging lens. ► Neither CIS1 nor CIS2 requires the modification of the imaging lens to access aperture. ► CIS1 and CIS2 provide the external aperture plane in front of or behind the imaging...
Highlights ► It can handle total and partial occlusions, camera effects and deformable objects. ► To be the first to use the Image Foresting Transform for tracking purposes. ► Faster and more accurate than state-of-the-art tracking approaches. ► Creation of a new public dataset composed...
results per page
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.