Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (2 results)

  • Thesis
  • Peer Reviewed
UC Riverside Electronic Theses and Dissertations (2014)

Computer vision algorithms, which play an significant role in vision processing, is widely applied in many aspects such as geology survey, traffic management and medical care, etc.. Most of the situations require the process to be real-timed, in other words, as fast as possible. Field Programmable Gate Arrays (FPGAs) have a advantage of parallelism fabric in programming, comparing to the serial communications of CPUs, which makes FPGA a perfect platform for implementing vision algorithms. These algorithms usually have a very high computation power because the objects, a large amount of pixels of a single picture, have to be proceeded not once, but many times. This project reconfigured onto the FPGA board, Terasic DE2i-150, a partial of a algorithm that has multiplexing computations. The algorithm of Harris corner detection is chosen, which contains an important step in many vision processing and is of good performance. The reconfiguration of the most time-consuming portion has synthesized onto the board and a result is presented to demonstrate the performance and the capacity of the FPGA. It shows that even a low-cost FPGA in 50MHz can achieve a faster speed than that of some CPUs due to the parallelism, which is the specialization of FPGAs and is unfeasible to apply to software.

    Cover page: FPGA Implementation of Computer Vision Algorithm
    • Article
    • Peer Reviewed
    UC Irvine Previously Published Works (2015)
    Network alignment is an important bridge to understanding human protein-protein interactions (PPIs) and functions through model organisms. However, the underlying subgraph isomorphism problem complicates and increases the time required to align protein interaction networks (PINs). Parallel computing technology is an effective solution to the challenge of aligning large-scale networks via sequential computing. In this study, the typical Hungarian-Greedy Algorithm (HGA) is used as an example for PIN alignment. The authors propose a HGA with 2-nearest neighbours (HGA-2N) and implement its graphics processing unit (GPU) acceleration. Numerical experiments demonstrate that HGA-2N can find alignments that are close to those found by HGA while dramatically reducing computing time. The GPU implementation of HGA-2N optimises the parallel pattern, computing mode and storage mode and it improves the computing time ratio between the CPU and GPU compared with HGA when large-scale networks are considered. By using HGA-2N in GPUs, conserved PPIs can be observed, and potential PPIs can be predicted. Among the predictions based on 25 common Gene Ontology terms, 42.8% can be found in the Human Protein Reference Database. Furthermore, a new method of reconstructing phylogenetic trees is introduced, which shows the same relationships among five herpes viruses that are obtained using other methods.
      Cover page: Graphics processing unit‐based alignment of protein interaction networks
      Top