Authors: Umesh C. Pati, Pranab K. Dutta, Alok Barua
Addresses: Department of Electronics and Communication Engineering, National Institute of Technology, Rourkela 769008, Orissa, India. ' Department of Electrical Engineering, Indian Institute of Technology, Kharagpur 721302, West Bengal, India. ' Department of Electrical Engineering, Indian Institute of Technology, Kharagpur 721302, West Bengal, India
Abstract: This paper presents feature level fusion of images of an object obtained from two different imaging techniques. A draft 3-D view of the object is generated by registering range images obtained from scanning the object by a laser beam. For that purpose, the method of optical triangulation is employed for data acquisition and feature matching technique for the registration of the images. Triangle-based linear interpolation is used to obtain a 3-D mesh representing the object surface. Structural features are extracted from the draft 3-D model of the object and subsequently mapped to 2-D plane by perspective transformation. Hough transform technique has been implemented for the extraction of structural features from the intensity image of the object obtained under illumination light. Fusion of both the extracted edge maps is accomplished by affine transformation after identifying a set of control points. This provides a high-level description of the object.
Keywords: laser scanning; range images; 3D modelling; structural features; perspective transformation; control points; intensity images; image fusion; affine transformation; computational vision; optical triangulation; data acquisition; feature matching; linear interpolation; Hough transform; feature extraction.
International Journal of Computational Vision and Robotics, 2009 Vol.1 No.1, pp.2 - 33
Published online: 26 Jun 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article