This work presents a machine learning method for terrain’s traversability classification. Stereo vision is used to provide the depth map of the scene. Then, a v-disparity image calculation and processing step extracts suitable features about the scene’s characteristics. The resulting data are used as input for the training of a support vector machine (SVM). The evaluation of the traversability ...

Stereo vision is important m determining three-dimensional positions of tile visible surfaces in images. Most existing stereo matching methods involve matching low-level image features such as edges. A stereo matching technique based on matching high-level image features is described in this paper. The high-level image features extracted are topographic structures, arc segments and region segme...

Real-time stereo image matching is an important computer vision task. This paper presents the architecture and implementation of an FPGA-based stereo image processor, that produces 25 dense depth maps per second from pairs of 8-bit-perpixel gray-scale images. The system implements a modification of a previously-reported variable-window-size method to determine the best correspondence for each i...

In this research, first of all, the existing problems in fragmentation measurement are reviewed for the sake of its fast and reliable evaluation. Then, the available methods used for evaluation of blast results are mentioned. The produced errors especially in recognizing the rock fragments in computer-aided methods, and also, the importance of determination of their sizes in the image analysis ...

Regular point splatting methods have a lot of problems when used on noisy data from stereo algorithms. Just a few unfiltered outliers, depth discontinuities, and holes can destroy the whole rendered image. We present a newmulti-pass splatting method on GPU hardware called Adaptive Point Splatting (APS) to render noisy point clouds. By taking advantage of image processing algorithms on the GPU, ...

This paper investigates the benefit of dense stereo for the ROI generation stage of a pedestrian detection system. Dense disparity maps allow an accurate estimation of the camera height, pitch angle and vertical road profile, which in turn enables a more precise specification of the areas on the ground where pedestrians are to be expected. An experimental comparison between sparse and dense ste...

Photometric stereo endoscopy is a technique that captures information about the high-spatial-frequency topography of the field of view simultaneously with a conventional color image. Here we describe a system that will enable photometric stereo endoscopy to be clinically evaluated in the large intestine of human patients. The clinical photometric stereo endoscopy system consists of a commercial...

Volume rendering is a well known visualization technique for volumetric scalar data. Several publications already described the acceleration of this technique when using the graphical processing unit (GPU). This enables real-time viewpoint manipulations which, in turn, facilitates the interpretation. Stereo, where two slightly different images are generated for each eye, proved to be a valuable...

This paper presents the first Optical Audio Reconstruction (OAR) approach for the long-term digital preservation of stereo phonograph records. OAR uses precision metrology and digital image processing to obtain and convert groove contour data into digital audio for access and preservation. This contactless and imaging-based approach has considerable advantages over the traditional mechanical me...

Traditional image matching approaches often fail in processing Mars Global Surveyor stereo images because of low contrast and insufficient number of features. Reliable and precision matching tool is needed for precise Mars digital elevation model generation. This paper presents a hierarchical image matching approach. First, a number of well identified points are manually measured in a stereo pa...