In this paper we present discussion of our results of parallel programming techniques for image processing applications using graphics processor units (GPU's). We have considered and analyzed various GPU's tak...
详细信息
In this paper we present discussion of our results of parallel programming techniques for image processing applications using graphics processor units (GPU's). We have considered and analyzed various GPU's taking their standing development into account and have implemented a number of most typical image processing tasks and algorithms. On this basis we have not only estimated the capacity growth of GPU's but also the corresponding growth of performance especially for the parallel image processing.
In this paper, a complete architecture of the software defined radio receiver is proposed. First, a precise definition and the discussion of the problem is given. Next, an outline of the system topology is proposed, t...
详细信息
In this paper, a complete architecture of the software defined radio receiver is proposed. First, a precise definition and the discussion of the problem is given. Next, an outline of the system topology is proposed, together with the requirements for each component of the system. Finally, a custom implementation is presented, including specifications, design considerations, and simulations.
This paper presents several methods for application in CCTV systems in order to support operators' duties. These methods are based on video processing only. In result, the attention of the operator can be attracte...
详细信息
This paper presents several methods for application in CCTV systems in order to support operators' duties. These methods are based on video processing only. In result, the attention of the operator can be attracted using an alarm signal. Additional information about objects can be delivered or the automatic control of PTZ cameras applied. Among the considered methods are: people detection, silhouette extraction, multiple camera signalprocessing, moving object tracking.
In this paper an experiment designed and performed to verify the possibility of efficient windowing utilized in time domain with the Mallat type wavelet decomposition scheme is described. The main idea is that the use...
详细信息
In this paper an experiment designed and performed to verify the possibility of efficient windowing utilized in time domain with the Mallat type wavelet decomposition scheme is described. The main idea is that the used filters are designed not in the Fourier domain but in a domain of any of the 16 DTTs. It is demonstrated that the windowing technique, which reduces the number of the required computations up to 34 times, results in the error with statistically assessed PSNR of ca. 40 dB (from 36 to over 50 dB). The PSNR is obtained from MSE computed with an assumption that the processed signal is a realization of the first order Markov process with a given intersymbol correlation. If necessary, the reconstruction is assumed to be perfect.
In this paper a prototype emergency services system is presented, equipped with a multimedia database registering and storing relevant emergency situations in a semi automatic way. In this paper we assume that this da...
详细信息
In this paper a prototype emergency services system is presented, equipped with a multimedia database registering and storing relevant emergency situations in a semi automatic way. In this paper we assume that this da...
详细信息
In this paper a prototype emergency services system is presented, equipped with a multimedia database registering and storing relevant emergency situations in a semi automatic way. In this paper we assume that this database is created exclusively with sound and linguistic material won from emergency telephone calls. The presented system enables conducting speaker recognition experiments. Sources of data, metadata generation, architecture description, searching for results, and database implementation are comprised.
In this paper we present methods of parallel programming on graphics processor unit (GPU). We describe and consider usefulness of NVIDIA's SDK CUDA (Compute Unified Device Architecture), which make GPGPU easier. F...
详细信息
In this paper simple techniques based on nonlinear geometric transformations are presented for creating an effective 3D impression (stereovision or illusion of depth) from a single 2D original. Our aim is to propose s...
详细信息
In this paper we present methods of parallel programming on graphics processor unit (GPU). We describe and consider usefulness of NVIDIA's SDK CUDA (Compute Unified Device Architecture), which make GPGPU easier. F...
详细信息
In this paper we present methods of parallel programming on graphics processor unit (GPU). We describe and consider usefulness of NVIDIA's SDK CUDA (Compute Unified Device Architecture), which make GPGPU easier. Finally we try to estimate potential capacity of new graphics processors and also look closer for edge detection example program.
In this paper simple techniques based on nonlinear geometric transformations are presented for creating an effective 3D impression (stereovision or illusion of depth) from a single 2D original. Our aim is to propose s...
详细信息
In this paper simple techniques based on nonlinear geometric transformations are presented for creating an effective 3D impression (stereovision or illusion of depth) from a single 2D original. Our aim is to propose semi-automatic ways to transform 2D images into their suggestive but plausible 3D anaglyph versions. Three conversion methods based on a binary depth map are proposed and the influence of various RGB component shifts on the 3D impression quality is studied.
暂无评论