Title :
Ray Projection for Recovering Projective Transformations and Illumination Changes
Author :
Zhang, Yun ; Chu, Chee Hung Henry
Author_Institution :
Center for Adv. Comput. Studies, Univ. of Louisiana at Lafayette, Lafayette, LA, USA
fDate :
3/1/2011 12:00:00 AM
Abstract :
The ray projection and its application to recovering a projective geometric transformation and an affine lighting change between two objects are mathematically studied. A novel technique, viz., variable contour, is proposed for accurately evaluating the ray projection. Moreover, a novel flexible framework of the ray projection is devised for the joint recovery of the eight parameters for the projective transformation and the two parameters for the lighting change. Finally, the framework is experimentally evaluated by recovering a variety of geometric and photometric transformations between real images of indoor and outdoor scenes. Its robustness to image blur and occlusion is demonstrated. Its versatility is illustrated through matching different objects in different classes.
Keywords :
affine transforms; computational geometry; feature extraction; hidden feature removal; image matching; image restoration; affine lighting; image blur; objects matching; occlusion; photometric transformation; projective geometric transformation; ray projection; Computer vision; Feature extraction; Image matching; Image motion analysis; Layout; Lighting; Photometry; Robustness; Stereo vision; Image matching; image motion analysis; lighting change; projective transformation; stereo vision.; Algorithms; Artificial Intelligence; Depth Perception; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Lighting; Models, Theoretical; Pattern Recognition, Automated; Projective Techniques; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Subtraction Technique;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2010.96
