Pose-Invariant Object Recognition for Event-Based Vision with Slow-ELM release_ojx7lherzng6bhucatbvpb6xo4

by Rohan Ghosh, Siyi Tang, Mahdi Rasouli, Nitish Thakor, Sunil Kukreja

Released as a article .

2019  

Abstract

Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation to name a few. However, there exists a lack of algorithms in event-based vision aimed towards capturing invariance to transformations. In this work, we propose a methodology for recognizing objects invariant to their pose with the Dynamic Vision Sensor (DVS). A novel slow-ELM architecture is proposed which combines the effectiveness of Extreme Learning Machines and Slow Feature Analysis. The system, tested on an Intel Core i5-4590 CPU, can perform 10,000 classifications per second and achieves 1% classification error for 8 objects with views accumulated over 90 degrees of 2D pose.
In text/plain format

Archived Files and Locations

application/pdf  462.1 kB
file_xgcdxu5abzd3ho6phlno77lvuq
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-03-19
Version   v1
Language   en ?
arXiv  1903.07873v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 2b67b8b2-5200-4b88-83bd-3d74f8e7cc88
API URL: JSON