Hardware Architecture for High-Speed Object Detection Using Decision Tree Ensemble
Authors:
- 1 September 2018
- journal article
- research article
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E101.A (9) , 1298-1307
Abstract
Visual object detection on embedded systems involves a multi-objective optimization problem in the presence of trade-offs between power consumption, processing performance, and detection accuracy. For a new Pareto solution with high processing performance and low power consumption, this paper proposes a hardware architecture for decision tree ensemble using multiple channels of features. For efficient detection, the proposed architecture utilizes the dimensionality of feature channels in addition to parallelism in image space and adopts task scheduling to attain random memory access without conflict. Evaluation results show that an FPGA implementation of the proposed architecture with an aggregated channel features pedestrian detector can process 229 million samples per second at 100MHz operation frequency while it requires a relatively small amount of resources. Consequently, the proposed architecture achieves 350fps processing performance for 1080P Full HD images and outperforms conventional object detection hardware architectures developed for embedded systems.Keywords
This publication has 19 references indexed in Scilit:
- An Energy-Efficient Hardware Implementation of HOG-Based Object Detection at 1080HD 60 fps with Multi-Scale SupportJournal of Signal Processing Systems, 2015
- Evaluation and Acceleration of High-Throughput Fixed-Point Object Detection on FPGAsIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Fast Feature Pyramids for Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- FPGA Implementations of Feed Forward Neural Network by using Floating Point Hardware AcceleratorsAdvances in Electrical and Electronic Engineering, 2014
- HARDWARE IMPLEMENTATION OF DECISION TREE ENSEMBLESJournal of Circuits, Systems and Computers, 2013
- Pedestrian detection at 100 frames per second2012
- DECISION TREES DO NOT GENERALIZE TO NEW VARIATIONSComputational Intelligence, 2010
- Integral Channel Features2009
- Histograms of Oriented Gradients for Human Detection2005
- A compact 3-D VLSI classifier using bagging threshold network ensemblesIEEE Transactions on Neural Networks, 2003