Real-time face detection in Full HD images exploiting both embedded CPU and GPU
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19457871,p. 1-6
Abstract
CPU-GPU heterogeneous systems have become a mainstream platform in both server and embedded domains with ever increasing demand for powerful accelerator. In this paper, we present parallelization techniques that exploit both data and task parallelism of LBP based face detection algorithm on an embedded heterogeneous platform. By running tasks in a pipelined parallel way on multicore CPUs and by offloading a data-parallel task to a GPU, we could successfully achieve 29 fps for Full HD inputs on Tegra K1 platform where quad-core Cortex-A15 CPU and CUDA supported 192-core GPU are integrated. This corresponds to 5.54x speedup over a sequential version and 1.69x speedup compared to the GPU-only implementations.Keywords
This publication has 8 references indexed in Scilit:
- Real-time integrated face detection and recognition on embedded GPGPUs2014
- Cooperative heterogeneous computing for parallel processing on CPU/GPU hybrids2012
- Real-time GPU-based face detection in HD video sequences2011
- Accelerating Viola-Jones Face Detection to FPGA-Level Using GPUs2010
- Towards a robust, real-time face processing system using CUDA-enabled GPUs2009
- Fpga-based face detection system using Haar classifiers2009
- Face Description with Local Binary Patterns: Application to Face RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Rapid object detection using a boosted cascade of simple features2005