Algorithm-Hardware Co-Optimization for Energy-Efficient Drone Detection on Resource-Constrained FPGA

Han Sok Suh, Jian Meng, Ty Nguyen, Shreyas K. Venkataramanaiah, Vijay Kumar, Yu Cao, Jae Sun Seo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Convolutional neural network (CNN) based object detection has achieved very high accuracy, e.g. single-shot multi-box detectors (SSD) can efficiently detect and localize various objects in an input image. However, they require a high amount of computation and memory storage, which makes it difficult to perform efficient inference on resource-constrained hardware devices such as drones or unmanned aerial vehicles (UAVs). Drone/UAV detection is an important task for applications including surveillance, defense, and multi-drone self-localization and formation control. In this paper, we designed and co-optimized algorithm and hardware for energy-efficient drone detection on resource-constrained FPGA devices. We trained SSD object detection algorithm with a custom drone dataset. For inference, we employed low-precision quantization and adapted the width of the SSD CNN model. To improve throughput, we use dual-data rate operations for DSPs to effectively double the throughput with limited DSP counts. For different SSD algorithm models, we analyze accuracy or mean average precision (mAP) and evaluate the corresponding FPGA hardware utilization, DRAM communication, throughput optimization. Our proposed design achieves a high mAP of 88.42% on the multi-drone dataset, with a high energy-efficiency of 79 GOPS/W and throughput of 158 GOPS using Xilinx Zynq ZU3EG FPGA device on the Open Vision Computer version 3 (OVC3) platform. Our design achieves 2.7X higher energy efficiency than prior works using the same FPGA device, at a low-power consumption of 1.98 W.

Original languageEnglish (US)
Title of host publication2021 International Conference on Field-Programmable Technology, ICFPT 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665420105
DOIs
StatePublished - 2021
Externally publishedYes
Event20th International Conference on Field-Programmable Technology, ICFPT 2021 - Virtual, Auckland, New Zealand
Duration: Dec 6 2021Dec 10 2021

Publication series

Name2021 International Conference on Field-Programmable Technology, ICFPT 2021

Conference

Conference20th International Conference on Field-Programmable Technology, ICFPT 2021
Country/TerritoryNew Zealand
CityVirtual, Auckland
Period12/6/2112/10/21

Keywords

  • algorithm-hardware co-design
  • convolutional neural network
  • FPGA accelerator
  • object detection

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'Algorithm-Hardware Co-Optimization for Energy-Efficient Drone Detection on Resource-Constrained FPGA'. Together they form a unique fingerprint.

Cite this