CARTOSAT-1, launched in May 2005, is basically a stereo mission; in fact it is equipped with two cameras onboard, namely Aft and Fore, tilted in along track by -5° and +26°, allowing the acquisition of stereo data for every scene with a resolution of 2.5 m. The Institutes of Area di Geodesia e Geomatica Università di Roma “La Sapienza”, Eurimage S.p.A. and CyberCity AG participated at the ISPRS...

This paper describes a new image-based approach to tracking the 6 degrees of freedom trajectory of a stereo camera pair using a corresponding reference image pair whilst simultaneously determining pixel matching between consecutive images in a sequence. A dense minimisation approach is employed which directly uses all grey-scale information available within the stereo pair (or stereo region) le...

| This paper will report new results we have obtained in applying stereo vision algorithms to the problem of autonomous vehicle navigation on highways. The project consists of two parts: lane extraction and obstacle detection. Our lane extraction system is based on a param-eterized model for the appearance of the lanes in the images. This model captures the position, orientation and width of th...

A novel hierarchical stereo matching algorithm is presented which gives disparity map as output from illumination variant stereo pair. Illumination difference between two stereo images can lead to undesirable output. Stereo image pair often experience illumination variations due to many factors like real and practical situation, spatially and temporally separated camera positions, environmental...

Most of the research in music information retrieval (MIR) is concentrating only on monophonic source signals. The stereo information has been ignored largely in the research many years. However, commercially available music recordings typically consist of a two-track stereo mix. The type of mixing process used in the recordings can be roughly categorizes into live recordings and studio recordings.

This paper presents a new method to generate and present arbitrarily directional binocular stereo images from a sequence of omnidirectional images in real time. A sequence of omnidirectional images is taken by moving an omnidirectional image sensor in a static real environment. The motion of the omnidirectional image sensor is constrained to a plane. The sensor’s route and speed are known. In t...

We propose a new solution to stereo matching which is combined the area-based stereo method using hierarchical windows with the pixel-based stereo methods using global optimization. The areabased method has a problem that the best size of area is unknown. Since the proposed method changes the sizes of windows hierarchically, the local minima problem and a-priori knowledge of the size can be rem...

Time-lapse stereo – using natural illumination changes in stereo reconstruction for large scale outdoor scene is yet an unexplored application of spacetime stereo framework. In this project, we collect several time-lapse stereo data sets for further research use and also evaluate the performance of time-lapse stereo by comparing the quality of its disparity images to the ones using classic ster...

This paper presents an interactive object extraction approach for stereo images. The extraction task on stereo images has two significant differences compared to that on monoscopic images. First, the segmentation for both images should be consistent. Second, stereo images have implicit depth information, which supplies an important cue for object extraction. In this paper, we generate consisten...