Month: November 2012

Constancy and inconstancy in categorical colour perception

Place: Large Lecture Room Affiliation: Computer Vision Centre and Dep. of Computer Science, UAB.   To recognise objects is perhaps the most important task an autonomous system, either biological or artificial needs to perform. In the context of human vision, this is

Posted in Phd

The contribution of color for edge detection in natural scenes

Place: Large Lecture Room Affiliation: Department of General and Experimental Psychology Justus Liebig University Giessen. Germany   In a statistical analysis of over 700 natural scenes from the McGill calibrated color image database we found that luminance and chromatic edges are statistically

Posted in Seminars

Multimodal Stereo from Thermal Infrared and Visible Spectrum

Place: Large Lecture Room Affiliation: Computer Vision Centre and Dep. of Computer Science, UAB   Recent advances in thermal infrared imaging (LWIR) has allowed its use in applications beyond of the military domain. Nowadays, this new family of  sensors is included in

Posted in Phd

Kernel signal-to-noise ratio for machine learning

Place: Large Lecture Room Affiliation: Image and Signal Processing Group (ISP), Universitat de València, Spain   In this talk I will introduce a powerful kernel function for machine learning and signal processing. The proposed kernel signal to noise ratio (KSNR) maximizes the

Posted in Seminars

Contributions to the Diagnosis of Intestinal Motility by Automatic Image Analysis

Place: Large Lecture Room – CVC Affiliation: Universitat de Barcelona and Computer Vision Centre   In the early twenty first century Given Imaging Ltd. presented wireless capsule endoscopy (WCE) as a new technological breakthrough that allowed the visualization of the intestine by

Posted in Phd

Towards Deep Image Understanding: From pixels to semantics

Place: Large Lecture Room Affiliation: Computer Vision Centre and Dep. of Computer Science, UAB.   Understanding the content of the images is one of the greatest challenges of computer vision. Recognition of objects appearing in images, identifying and interpreting their actions are

Posted in Phd

Differential Evolution: Properties and Applications

Place: Large Lecture Room Affiliation: Department of Computer Science, West University of Timisoara, Romania   Differential Evolution (DE) is currently one of the most used population based stochastic metaheuristic for solving multi-modal, multi-objective, dynamic or constrained optimization problems. Despite its simplicity in

Posted in Seminars

3D Motion Data aided Human Action Recognition and Pose Estimation

Place: Large Lecture Room Affiliation: Computer Vision Centre and Dep. of Computer Science, UAB.   In this work, we explore human action recognition and pose estimation problems. Different from traditional works of learning from 2D images or video sequences and their annotated output,

Posted in Phd

Ground Truth for Correspondence Problems: What we need to know

Place: Large Lecture Room Affiliation: HCI Lasb. Heidelberg, Germany   Creating ground truth for e.g. optical flow in natural outdoor environments seems almost impossible. In this talk, I will propose several possible approaches, some of which we are currently investigating. One approach

Posted in Seminars