Place recognition with event-based cameras and a neural implementation of SeqSLAM

Milford, Michael and Kim, Hanme and Mangan, Michael and Leutenegger, Stefan and Stone, Tom and Webb, Barbara and Davison, Andrew (2015) Place recognition with event-based cameras and a neural implementation of SeqSLAM. OALib Journal . ISSN 2333-9721

Full content URL: https://arxiv.org/ftp/arxiv/papers/1505/1505.04548...

Documents
23587 1505.04548.pdf
[img]
[Download]
[img]
Preview
PDF
23587 1505.04548.pdf - Whole Document

5MB
Item Type:Article
Item Status:Live Archive

Abstract

Event-based cameras (Figure 1) offer much potential to the fields of robotics and computer
vision, in part due to their large dynamic range and extremely high “frame rates”. These
attributes make them, at least in theory, particularly suitable for enabling tasks like
navigation and mapping on high speed robotic platforms under challenging lighting
conditions, a task which has been particularly challenging for traditional algorithms and
camera sensors. Before these tasks become feasible however, progress must be made
towards adapting and innovating current RGB-camera-based algorithms to work with eventbased
cameras. In this paper we present ongoing research investigating two distinct
approaches to incorporating event-based cameras for robotic navigation:
1. The investigation of suitable place recognition / loop closure techniques, and
2. The development of efficient neural implementations of place recognition
techniques that enable the possibility of place recognition using event-based
cameras at very high frame rates using neuromorphic computing hardware.
Figure 1: The first commercial event camera: (a) DVS128; (b) a stream of events (upward and
downward spikes: positive and negative events); (c) image-like visualisation of accumulated
events within a time interval (white and black: positive and negative events). From (H. Kim,
2014)].

Additional Information:arXiv preprint arXiv:1505.04548
Keywords:Place recognition, Computer science, NotOAChecked
Subjects:D Veterinary Sciences, Agriculture and related subjects > D300 Animal Science
G Mathematical and Computer Sciences > G730 Neural Computing
Divisions:College of Science > School of Computer Science
ID Code:23587
Deposited On:09 Aug 2016 11:22

Repository Staff Only: item control page