high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » Applications » Computer science » Computer vision

GPU Implementations of Object Detection using HOG Features and Deformable Models

Manato Hirabayashi, Shinpei Kato, Masato Edahiro, Kazuya Takeda, Taiki Kawano, Seiichi Mita

View

Tags: Algorithms, Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GTX 560 Ti, nVidia GeForce GTX 580, nVidia GeForce GTX 680, nVidia GeForce GTX Titan, Tesla K20

September 11, 2013 by hgpu

Fast Object Re-Detection and Localization in Video for Spatio-Temporal Fragment Creation

Evlampios Apostolidis, Vasileios Mezaris, Ioannis Kompatsiaris

View

Download (PDF)

Tags: Algorithms, Computer science, Computer vision, nVidia, nVidia GeForce GTX 560, OpenCV

August 26, 2013 by hgpu

Performance Optimization of Vision Apps on Mobile Application Processor

Kwang-Ting (Tim) Cheng, Xin Yang and Yi-Chu Wang

View

Download (PDF)

Tags: Computer science, Computer vision, Heterogeneous systems, nVidia, nVidia Tegra, OpenGL

August 24, 2013 by hgpu

A Unified Framework for Multi-Sensor HDR Video Reconstruction

Joel Kronander, Stefan Gustavson, Gerhard Bonnet, Anders Ynnerman, Jonas Unger

View

Download (PDF)

Tags: Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GTX 680

August 23, 2013 by hgpu

Accelerating Random Forests on CPUs and GPUs for Object-Class Image Segmentation

Benedikt Waldvogel

View

Download (PDF)

Source codes

Tags: Computer science, Computer vision, CUDA, Machine learning, nVidia, nVidia GeForce GTX 480, nVidia GeForce GTX 690, nVidia GeForce GTX Titan, Package, Tesla K20, Thesis

August 16, 2013 by hgpu

An Automated Video Surveillance System Using Viewpoint Feature Histogram and CUDA-enabled GPUs

Saurabh Jha, Priyank Trivedi

View

Download (PDF)

Tags: Computer science, Computer vision, CUDA, nVidia, Tesla M2050

August 14, 2013 by hgpu

Heterogeneous Computing for Real-Time Stereo Matching

A. AL-Marakeby, M. Zaki

View

Download (PDF)

Tags: Algorithms, Computer science, Computer vision, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GT 610 M, Stereo vision

August 10, 2013 by hgpu

Real-time 3D semi-local surface patch extraction using GPGPU

Sergio Orts-Escolano, Vicente Morell, Jose Garcia-Rodriguez, Miguel Cazorla, Robert B. Fisher

View

Download (PDF)

Tags: Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GT 630 M, nVidia GeForce GTX 480

July 29, 2013 by hgpu

Detecting parametric objects in large scenes by Monte Carlo sampling

Yannick Verdie, Florent Lafarge

View

Download (PDF)

Tags: Algorithms, Computer science, Computer vision, CUDA, nVidia, nVidia Quadro FX 4800

July 21, 2013 by hgpu

Parallel Image Segmentation Using Reduction-Sweeps On Multicore Processors and GPUs

Renato Farias, Ricardo Farias, Ricardo Marroquim, Esteban Clua

View

Download (PDF)

Tags: Algorithms, Clustering, Computer vision, CUDA, Image processing, nVidia, nVidia GeForce GTX 470

July 19, 2013 by hgpu

Fast PCA-BAsed Face Recognition on GPUs

Youngsang Woo, Cheongyong Yi, Youngmin Yi

View

Download (PDF)

Tags: Algorithms, Biometrics, Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GTX 580

July 12, 2013 by hgpu

Feature Tracking in Time-Varying Volumetric Data through Scale Invariant Feature Transform

Khoa Tan Nguyen, Timo Ropinski

View

Download (PDF)

Tags: Algorithms, Computer science, Computer vision, OpenCL, SIFT

July 12, 2013 by hgpu

CATO: automatic source transformation to apply HPC frameworks with minimal user interaction

Compiler-assisted distribution of OpenMP code for improved scalability

ADIOS2.jl: a Julia interface to ADIOS2

Julia as a unifying end-to-end workflow language on the Frontier exascale system

Code generated HPC Kernels Using Llama-2-70b

Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation

Scope is all you need: Transforming LLMs for HPC Code

pocl - Portable Computing Language

PoCL-R: An Open Standard Based Offloading Layer for Heterogeneous Multi-Access Edge Computing with Server Side Scalability

HPAC-Offload: Accelerating HPC Applications with Portable Approximate Computing on the GPU

openCLDispatcher

Novel insights on atomic synchronization for sort-based group-by on GPUs

CEED Benchmarks

Performant low-order matrix-free finite element kernels on GPU architectures

Sieve: Stratified GPU-Compute Workload Sampling

EngineCL: Usability and Performance in Heterogeneous Computing

Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Applications

GPU Implementations of Object Detection using HOG Features and Deformable Models

Fast Object Re-Detection and Localization in Video for Spatio-Temporal Fragment Creation

Performance Optimization of Vision Apps on Mobile Application Processor

A Unified Framework for Multi-Sensor HDR Video Reconstruction

Accelerating Random Forests on CPUs and GPUs for Object-Class Image Segmentation

An Automated Video Surveillance System Using Viewpoint Feature Histogram and CUDA-enabled GPUs

Heterogeneous Computing for Real-Time Stereo Matching

Real-time 3D semi-local surface patch extraction using GPGPU

Detecting parametric objects in large scenes by Monte Carlo sampling

Parallel Image Segmentation Using Reduction-Sweeps On Multicore Processors and GPUs

Fast PCA-BAsed Face Recognition on GPUs

Feature Tracking in Time-Varying Volumetric Data through Scale Invariant Feature Transform

Recent source codes

CATO: automatic source transformation to apply HPC frameworks with minimal user interaction

ADIOS2.jl: a Julia interface to ADIOS2

Code generated HPC Kernels Using Llama-2-70b

Scope is all you need: Transforming LLMs for HPC Code

pocl - Portable Computing Language

HPAC-Offload: Accelerating HPC Applications with Portable Approximate Computing on the GPU

openCLDispatcher

CEED Benchmarks

Sieve: Stratified GPU-Compute Workload Sampling

EngineCL: Usability and Performance in Heterogeneous Computing

Most viewed papers (last 30 days)