Emerging applications in the mobile and automotive industries can benefit from a solution which can segment an image into objects. Although originally not developed for these applications, Object-based Motion Estimati...
详细信息
ISBN:
(纸本)0780377958
Emerging applications in the mobile and automotive industries can benefit from a solution which can segment an image into objects. Although originally not developed for these applications, Object-based Motion Estimation (OME) is an algorithm which provides such a segmentation. In this paper we map this algorithm on all Application Specific Instruction Processor (ASIP) based on a Very Long Instruction Word (VLIW) template. An analysis of the computational requirements is made, using Video Format Conversion as an application, since emerging applications aren't available yet. We also propose a multi-level caching architecture to keep bandwidth and power requirements low and discuss algorithmic changes to OME, which are necessary for OME to be mapped on all ASIP VLIW. A quality comparison of the resulting vector fields is made as well.
The Field Programmable Gate Array (FPGA) implementation of the commonly used Histogram of Oriented Gradients (HOG) algorithm is explored. The HOG algorithm is employed to extract features for object detection. A key f...
详细信息
ISBN:
(纸本)9781479965885
The Field Programmable Gate Array (FPGA) implementation of the commonly used Histogram of Oriented Gradients (HOG) algorithm is explored. The HOG algorithm is employed to extract features for object detection. A key focus has been to explore the use of a new FPGA-based processor which has been targeted at image processing. The paper gives details of the mapping and scheduling factors that influence the performance and the stages that were undertaken to allow the algorithm to be deployed on FPGA hardware, whilst taking into account the specific IPPro architecture features. We show that multi-core IPPro performance can exceed that of against state-of-the-art FPGA designs by up to 3.2 times with reduced design and implementation effort and increased flexibility all on a low cost, Zynq programmable system.
Algebraic Mapping Networks can describe time/space dependencies either at coarse or fine grained level. The work reported here is focused on how compiler technology can be adapted to deal with the AIMa-Net description...
详细信息
ISBN:
(纸本)0780349970
Algebraic Mapping Networks can describe time/space dependencies either at coarse or fine grained level. The work reported here is focused on how compiler technology can be adapted to deal with the AIMa-Net description of fine grain time/space dependencies within a single program. In the first phase, special Almanet statements are embedded in C/C++ and a prototype compiler has been developed which successfully interprets these dependencies and generates the correct executables. At the heart of this compiler is the space-time routine which generates a space-time matrix for each dependent variable. The compiler effectively translates an Almanet program, which is basically data-oriented, into separate process-oriented C programs.
The hardware implementation issues of multiuser interference cancellation techniques for multirate asynchronous Direct-Sequence Code Division Multi-Access (DS-CDMA) systems based on variable spreading factor (VSF) are...
详细信息
We first review the high-level signalprocessing architecture of a wireless MEM sensor system for source detection, signal enhancement, localization, and identification. A blind beamformer using only the measured data...
详细信息
ISBN:
(纸本)0780349970
We first review the high-level signalprocessing architecture of a wireless MEM sensor system for source detection, signal enhancement, localization, and identification. A blind beamformer using only the measured data of randomly distributed sensors to form a sample correlation matrix is proposed. The maximum power collection criterion is used to obtain array weights from the dominant eigenvector of the sample correlation matrix. An effective blind beamforming estimation of the time delays of the dominant source is demonstrated. Source localization based on a novel least-squares method for time delay estimation is also given. Array system performance based on analysis, simulation, and measured acoustical/seismic sensor data are presented. Applications of such a system to multimedia, intrusion detection, and surveillance are briefly discussed.
Methods for the rapid design and VLSI implementation of two key components of the class-IV partial response maximum likelihood channel (PR-IV), the adaptive filter and the Viterbi decoder, are described. These are imp...
详细信息
ISBN:
(纸本)0780349970
Methods for the rapid design and VLSI implementation of two key components of the class-IV partial response maximum likelihood channel (PR-IV), the adaptive filter and the Viterbi decoder, are described. These are implemented using parameterized modules, constructed from a synthesizable silicon architecture library containing core DSP and arithmetic functions. design studies, based on a 0.35 micron 3.3V standard cell CMOS process, indicate that worst case sampling rates of 180 mega-samples per second are achievable with a power consumption of 0.8W and an area of 4.3mm(2). sigher sampling rates can be obtained by operating a number of filter modules in parallel. This approach offers power saving advantages when compared with systems employing pipelined filters operating at the same speed.
The theory and design of critically sampled Perfect Reconstruction (PR) Uniform Filter Bank (FB) is well established. However, the principles of Non-Uniform PR FB are still an active research topic. In the recent past...
详细信息
ISBN:
(纸本)0780371453
The theory and design of critically sampled Perfect Reconstruction (PR) Uniform Filter Bank (FB) is well established. However, the principles of Non-Uniform PR FB are still an active research topic. In the recent past, a number of necessary (compatibility) conditions have been identified, which any set of integer decimation factors must satisfy for existance of a realizable maximally-decimated perfect- reconstruction non-uniform filter bank. The search for a compatible-set, in the neighborhood of a desired set of decimation factors, can be computationally prohibitive, as it is exponential to the number of filters in the bank. In this paper we propose a branch-and-bound algorithm to efficiently search for compatible-sets. We present experimental results for a compatible set of a 26-filter bank, matching the critical bands of the human auditory system very closely.
Stereo vision is the process of recreating 3-D spatial information from a pair of 2-D images. We propose a multilayer stereo vision algorithm and architecture which makes it possible to match two images in real time, ...
详细信息
ISBN:
(纸本)0780377958
Stereo vision is the process of recreating 3-D spatial information from a pair of 2-D images. We propose a multilayer stereo vision algorithm and architecture which makes it possible to match two images in real time, without the rectification of the image (the rectification means making the scan line parallel to the epipolar line). It is the self calibration method that searches the pixel within several lines of one image corresponding to a pixel on the scan line of the other image to solve the epipolar probelm. We also propose a subpixel multi-layer system which considers subpixel data. It is useful for the stereo matching of the image with the characteristics of the high frequency bandwidth. The total time complexity is O(N) so that real time processing is possible. The hardware architecture is a simple linear systolic array apt for ASIC. The hardware design is verified by simulations, and it is confirmed that this system can process typical video image sequences in real time.
This paper suggests an automated validation approach in testing advanced digital signalprocessing algorithms. These algorithms, which are intended for the implementation of the base band processor of Software defined...
详细信息
ISBN:
(纸本)9781424403820
This paper suggests an automated validation approach in testing advanced digital signalprocessing algorithms. These algorithms, which are intended for the implementation of the base band processor of Software defined radios, are developed in software (Digital signal Processors DSP) and hardware (FP(;A) environments in order to meet real-time and offline requirements. The automation of the testing of such algorithms
Massive multiuser multi-input multi-output (MUMIMO) system adopting large amount of antennas is a promising technique to improve spectral efficiency and energy efficiency for next generation wireless communication sys...
详细信息
ISBN:
(纸本)9781538604465
Massive multiuser multi-input multi-output (MUMIMO) system adopting large amount of antennas is a promising technique to improve spectral efficiency and energy efficiency for next generation wireless communication systems. In practice, the channels composed of pairs of transmit and receive antennas are often correlated and computational complexity is one of the critical concern in implementation issue. Hence, antenna selection techniques can be adopted to improve system performance. In this paper, we propose a norm-and-correlation-based selection algorithm for energy efficiency maximization to decide transmit RF chain configuration under the total power constraint in massive MU-MIMO systems.
暂无评论