Accelerating object detection via a visual-feature-directed search cascade: algorithm and field programmable gate array implementation
Authors:
- 1 July 2016
- journal article
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 25 (4) , 041013
Abstract
Object detection is a major step in several computer vision applications and a requirement for most smart camera systems. Recent advances in hardware acceleration for real-time object detection feature extensive use of reconfigurable hardware [field programmable gate arrays (FPGAs)], and relevant research has produced quite fascinating results, in both the accuracy of the detection algorithms as well as the performance in terms of frames per second (fps) for use in embedded smart camera systems. Detecting objects in images, however, is a daunting task and often involves hardware-inefficient steps, both in terms of the datapath design and in terms of input/output and memory access patterns. We present how a visual-feature-directed search cascade composed of motion detection, depth computation, and edge detection, can have a significant impact in reducing the data that needs to be examined by the classification engine for the presence of an object of interest. Experimental results on a Spartan 6 FPGA platform for face detection indicate data search reduction of up to 95%, which results in the system being able to process up to 50 images per second with a significantly reduced number of false positives.
Keywords
This publication has 25 references indexed in Scilit:
- Accelerating FPGA-based object detection via a visual information extraction cascade2015
- A Tradeoff Analysis of FPGAs, GPUs, and Multicores for Sliding-Window ApplicationsACM Transactions on Reconfigurable Technology and Systems, 2015
- A hardware architecture for real-time object detection using depth and edge informationACM Transactions on Embedded Computing Systems, 2013
- FPGA-Accelerated Object Detection Using Edge Information2011
- A Parallel Hardware Architecture for Real-Time Object Detection with Support Vector MachinesIEEE Transactions on Computers, 2011
- A Flexible Parallel Hardware Architecture for AdaBoost-Based Real-Time Object DetectionIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2010
- Object motion detection using information theoretic spatio-temporal saliencyPattern Recognition, 2009
- Partially Parallel Architecture for AdaBoost-Based Detection With Haar-Like FeaturesIEEE Transactions on Circuits and Systems for Video Technology, 2008
- An Evaluation of the Suitability of FPGAs for Embedded Vision Systems2006
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004