Energy-Efficient Application-Specific Instruction-Set Processor for Feature Extraction in Smart Vision Systems

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

Smart vision sensor systems enable many computer vision applications such as autonomous drones and wearable devices. These battery-powered gadgets have very stringent power consumption requirements. Close-to-sensor feature extraction compressing the full image into descriptive keypoints, is crucial as it allows for several design optimizations. First, the amount of necessary on-chip memory can be lessened. Second, the volume of data that needs to be exchanged between nodes in Internet of Things (IoT) applications can also be reduced. This work explores the usage of an Application Specific Instruction Set Processor (ASIP) tailored to perform energy-efficient feature extraction in real-time. The ASIP features a Very Long Instruction Word (VLIW) central core comprising one RV32I RISCV and three vector slots. The on-chip memory sub-system implements parallel multi-bank memories with near-memory data shuffling to enable single-cycle multi-pattern vector access. As a case study, Oriented FAST and Rotated BRIEF (ORB) is used to evaluate the proposed architecture. We show that the architecture supports VGA-resolution images at 140 Frames-Per-Second (FPS), for one scale, reducing the number of memory accesses by 2 orders of magnitude comparing to other embedded general-purpose architectures.

Original languageEnglish
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages324-328
Number of pages5
ISBN (Electronic)9781665458283
DOIs
Publication statusPublished - 2021
Event55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021 - Virtual, Pacific Grove, United States
Duration: 2021 Oct 312021 Nov 3

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2021-October
ISSN (Print)1058-6393

Conference

Conference55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
Country/TerritoryUnited States
CityVirtual, Pacific Grove
Period2021/10/312021/11/03

Subject classification (UKÄ)

  • Computer Engineering

Keywords

  • ASIP
  • Feature Extraction
  • ORB
  • vision-based Simultaneous Localization And Mapping (SLAM)

Fingerprint

Dive into the research topics of 'Energy-Efficient Application-Specific Instruction-Set Processor for Feature Extraction in Smart Vision Systems'. Together they form a unique fingerprint.

Cite this