Physics-Based Vision Algorithms

Type | PhD project
Duration | -
Project leader Alberto Ortiz Rodriguez
Collaborators Gabriel Oliver Codina

FOCUS

Development of vision algorithms based on the physical laws of image formation. In this way, the image formation process is taken into account and optical effects such as shading, shadows, specularities, inter-reflections, etc. can be discounted/tolerated by the algorithm implementing the vision task. Main results of this research work include an edge detection algorithm (C3E), two segmentation algorithms (IS2R, C3S), a set of methods for estimating the lighting parameters and an algorithm for CCD-based radiometric camera calibration and intensity uncertainty estimation (R2CIU).

DESCRIPTION

IS2R segments an image by (partially) reconstructing the shape of the scene. As a result, at the end of the process the segmentation and a description of the scene shape are available. Unfortunately, the image formation model is limited by the shape reconstruction requirement of the algorithm, and only ambient illlumination and body reflection are allowed. C3 E and C3S are the result of a study about how colour channels are coupled in uniform reflectance image areas and achieve more ambituous segmentations. Both look for image pixels where the coupling is lost because of a reflectance transition arising there, leading to an edge map (C3E) from which a segmentation can be then obtained (C3S). All three algorithms make use of intensity uncertaintes estimated by R2CIU to find reflectance transitions in an adaptive way with respect to image noise.

PUBLICATIONS

A. Ortiz, G. Oliver. New Segmentation and Edge Detection Methods Using Physics-Based Models of Image Formation. Universitat de les Illes Balears, 2005.

A. Ortiz, G. Oliver. R2CIU: Robust Radiometric Calibration and Intensity Uncertainty estimation. In Technical Report A-01-2005, Dep. Mathematics and Computer Science (UIB), 2005.

A. Ortiz, G. Oliver. Scene Lighting Parameters Estimation and Radiometric Camera Calibration. In Technical Report A-02-2003, Dep. Mathematics and Computer Science (UIB), 2003.

A. Ortiz, G. Oliver. Segmentation of Images based on the Detection of Reflectance Transitions. In Technical Report A-03-2003, Dep. Mathematics and Computer Science (UIB), 2003.

A. Ortiz, G. Oliver. Albedo-based Segmentation prior to estimating Shape from Shading in multi-albedo scenes. In Technical Report A-01-2008, Dep. Mathematics and Computer Science (UIB), 2002.

A. Ortiz, G. Oliver. New Performance Measures Using the Overlapping Area Matrix for Image Segmentation Evaluation. In Technical Report A-04-2005, Dep. Mathematics and Computer Science (UIB), 2005.

A. Ortiz, M. Simó, G. Oliver. Image Sequence Analysis for Real-Time Underwater Cable Tracking. In Workshop on Applications of Computer Vision (WACV), Palm Springs-CA (USA), 2000.

M. Simó, A. Ortiz, G. Oliver. Optimized Image Sequence Analysis for Real-Time Underwater Cable Tracking. In MTS/IEEE Oceans, Providence-RI (USA), 2000.

A. Ortiz, G. Oliver. Shape from Shading for Multiple Albedo Images. In International Conference on Pattern Recognition (ICPR), Barcelona (Spain), 2000.

A. Ortiz, G. Oliver, J. Frau. A Vision System for Underwater Real-Time Control Tasks. In MTS/IEEE Oceans, Halifax (Canada), 1997.

G. Oliver, A. Ortiz, J. Frau. An Underwater Vision System for Real-Time Tracking Purposes. In Symposium on Intelligent Robotic Systems (SIRS), Stockholm (Sweden), 1997.

A. Ortiz, G. Oliver. Image Segmentation through Physics-based Quality Maps. In Technical Report A-02-2002, Dep. Mathematics and Computer Science (UIB), 2002.

A. Ortiz, G. Oliver. An Adaptation for SFS Algorithms to Deal with Multiple Albedo Images. In Technical Report A-01-2000, Dep. Mathematics and Computer Science (UIB), 2000.

A. Ortiz, M. Simó, G. Oliver. Real-Time Image Sequence Analysis for Tracking an Underwater Power Cable. In Technical Report A-02-2000, Dep. Mathematics and Computer Science (UIB), 2000.

A. Ortiz, G. Oliver. A Physics-Based Segmentation Technique For Lambertian Scenes. In Technical Report A-02-1999, Dep. Mathematics and Computer Science (UIB), 1999.

A. Ortiz. Aplicacion de técnicas de visión por computador a entornos submarinos. 1998.

A. Ortiz, G. Oliver. On the Use of the Overlapping Area Matrix for Image Segmentation Evaluation: a Survey and New Performance Measures. In Pattern Recognition Letters, vol. 27, no. 16, pp. 1916--1926, 2006.

A. Ortiz, G. Oliver. A Novel Segmentation Strategy Based on Colour Channels Coupling. In IAPR International Conference on Image Analysis and Processing (ICIAP, LNCS 3617), Cagliary (Italy), 2005.

A. Ortiz, G. Oliver. Estimation of Intensity Uncertainties for Computer Vision Applications. In IEEE Advanced Concepts for Intelligent Vision Systems (ACIVS, LNCS 3708), Antwerp (Belgium), 2005.

A. Ortiz, G. Oliver. Radiometric Calibration of CCD Sensors: Dark Current and Fixed Pattern Noise Estimation. In IEEE International Conference on Robotics and Automation (ICRA), New Orleans (USA), 2004.

A. Ortiz, G. Oliver. A Physics-Based Colour Edge Detector. In Catalan Conference on Artificial Intelligence (CCIA, Artificial Intelligence Research and Development, vol. 113 - IOS Press), Barcelona (Spain), 2004.

A. Ortiz, G. Oliver. Estimation of Directional and Ambient Illumination Parameters by means of a Calibration Object. In IAPR International Conference on Image Analysis and Recognition (ICIAR, LNCS 3211), Porto (Portugal), 2004.

A. Ortiz, G. Oliver. Detection of Colour Channels Uncoupling for Curvature-Insensitive Segmentation. In First Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA, LNCS 2652), Port d'Andratx (Spain), 2003.

A. Ortiz, G. Oliver. Estimation of Scene Lighting Parameters and Camera Dark Current. In Catalan Conference on Artificial Intelligence (CCIA, Artificial Intelligence Research and Development, vol. 100 - IOS Press), Palma de Mallorca (Spain), 2003.

A. Ortiz, G. Oliver. A method to discount ambient lighting and albedo variation before estimating shape from image shading. In Workshop on Advanced Concepts for Intelligent Vision Systems (ACIVS), Ghent (Belgium), 2002.

A. Ortiz, G. Oliver. A qualitative approach to physics-based image segmentation. In Workshop on Advanced Concepts for Intelligent Vision Systems (ACIVS), Ghent (Belgium), 2002.

A. Ortiz, M. Simó, G. Oliver. A Vision System for an Underwater Cable Tracker. In International Journal of Machine Vision and Applications, vol. 13, no. 3, pp. 129—140, 2002.

A. Ortiz, G. Oliver. Radiometric Calibration of Vision Cameras and Intensity Uncertainty Estimation. In Image and Vision Computing, vol. 24, no. 10, pp. 1137--1145, 2006.


Uso de cookies

Este sitio web utiliza cookies para que usted tenga la mejor experiencia de usuario. Si continúa navegando está dando su consentimiento para la aceptación de las mencionadas cookies y la aceptación de nuestra política de cookies, pinche el enlace para mayor información.

ACEPTAR
Aviso de cookies