This paper presents a state of the art report on using graphics hardware for image processing and computer vision. Then we describe GPUCV, an open library for easily developing GPU accelerated image processing and analysis operators and applications.

Abstract. This paper presents briefly describes the state of the art of accelerating image processing with graphics hardware (GPU) and discusses some of its caveats. Then it describes GpuCV, an open source multi-platform library for GPU-accelerated image processing and Computer Vision operators and applications. It is meant for computer vision scientist not familiar with GPU technologies. GpuCV is designed to be compatible with the popular OpenCV library by offering GPUaccelerated operators that can be integrated into native OpenCV applications. The GpuCV framework transparently manages hardware capabilities, data synchronization, activation of low level GLSL and CUDA programs, on-the-fly benchmarking and switching to the most efficient implementation and finally offers a set of image processing operators with GPU acceleration available.

A three-dimensional (3D) reconstruction of the vessel lumen from two angiographic views, based on the reconstruction of a series of cross-sections, is proposed. Assuming uniform mixing of contrast medium and background subtraction, the cross-section of each vessel is reconstructed through a binary representation. A priori information about both the slice to be reconstructed and the relationships between adjacent slices are incorporated to lessen ambiguities on the reconstruction. Taking into account the knowledge of normal vessel geometry, an initial solution of each slice is created using an elliptic model-based method. This initial solution is then deformed to be made consistent with projection data while being constrained into a connected realistic shape. For that purpose, properties on the expected optimal solution are described through a Markov random field. To find an optimal solution, a specific optimization algorithm based on simulated annealing is used. The method performs well both on single vessels and on branching vessels possessing an additional inherent ambiguity when viewed at oblique angles. Results on 2D slice independent reconstruction and 3D reconstruction of a stack of spatially continuous 2D slices are presented for single vessels and bifurcations.

No abstract

3D human motion capture by real-time monocular vision without using markers can be achieved by registering a 3D articulated model on a video. Registration consists in iteratively optimizing the match between primitives extracted from the model and the images with respect to the model position and joint angles. We extend a previous color-based registration algorithm with a more precise edge-based registration step. We present an experimental analysis of the residual error vs. the computation time and we discuss the balance between both approaches.