---
abstract: |-2
A functional focal-plane implementation of a 2D optical flow system is presented that detects an
preserves motion discontinuities. The system is composed of two different network layers of analog
computational units arranged in a retinotopical order. The units in the first layer (the optical
flow network) estimate the local optical flow field in two visual dimensions, where the strength
of their nearest-neighbor connections determines the amount of motion integration. Whereas in an
earlier implementation \cite{Stocker_Douglas99} the connection strength was set constant in the
complete image space, it is now \emph{dynamically and locally} controlled by the second network
layer (the motion discontinuities network) that is recurrently connected to the optical flow
network. The connection strengths in the optical flow network are modulated such that visual
motion integration is ideally only facilitated within image areas that are likely to represent
common
motion sources.
Results of an experimental aVLSI chip illustrate the potential of the approach and its
functionality under real-world conditions.
altloc: []
chapter: ~
commentary: ~
commref: ~
confdates: '26th - 29th may 2002'
conference: IEEE Int. Symposium on Circuits and Systems ISCAS
confloc: 'phoenix, U.S.A.'
contact_email: ~
creators_id: []
creators_name:
- family: stocker
given: alan
honourific: ''
lineage: ''
date: 2002
date_type: published
datestamp: 2002-07-18
department: ~
dir: disk0/00/00/23/31
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name: []
eprint_status: archive
eprintid: 2331
fileinfo: /style/images/fileicons/application_pdf.png;/2331/3/stocker.pdf
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: pub
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: 'motion segmentation, vision, optical flow, neuromorphic, aVLSI, efficient, optimization'
lastmod: 2011-03-11 08:54:57
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: II-332-II-335
pubdom: FALSE
publication: ~
publisher: ~
refereed: TRUE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 12
series: ~
source: ~
status_changed: 2007-09-12 16:44:16
subjects:
- comp-neuro-sci
- comp-sci-art-intel
- comp-sci-mach-vis
- comp-sci-neural-nets
- comp-sci-robot
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: An improved 2D optical flow sensor for motion segmentation
type: confpaper
userid: 179
volume: ~