Show simple item record

AuthorLayher, Georgdc.contributor.author
Date of accession2019-08-05T10:10:44Zdc.date.accessioned
Available in OPARU since2019-08-05T10:10:44Zdc.date.available
Year of creation2018dc.date.created
Date of first publication2019-08-05dc.date.issued
AbstractThe understanding and recognition of human actions is one of the major challenges for technical systems aiming at visual behavior analysis. Evidences from psychophysical and neurophysiological studies provide indications on the feature characteristics and neural processing principles involved in the perception of biological motion sequences. Modeling efforts from the field of computational neuroscience complement these empirical findings by proposing potential functional mechanisms and learning schemes enabling the establishment and recognition of biological motion representations and show how such principles can be transferred to technical domains. First, results of psychophysical investigations are presented that demonstrate significant increases in the human recognition performance for motion (sub-) sequences containing highly articulated poses, which co-occur with local extrema in the motion energy and the extension of a body. Such key poses thus qualify as candidates to establish biological motion representations. Second, based on these findings, a neural model for the learning of biological motion representations is presented. The model combines hierarchical feedforward and feedback processing along the ventral (form; what) and dorsal (motion; where) pathways with an unsupervised Hebbian learning mechanism for the learning of prototypical form and motion representations. More specifically, gated learning in the form pathway realizes the selective learning of highly articulated postures. Sequence selective representations are established using temporal association learning driven by motion and form input. The proposed model shows how the unsupervised learning of key poses can form the basis for the establishment of biological motion representations and gives a potential explanation for empirically observed phenomena, such as implied motion perception. Third, as a transfer to technical application scenarios, a real-time biologically inspired action recognition system is presented which automatically selects key poses in action sequences and employs a deep convolutional neural network (DCNN) to learn class-specific pose representations. The network is mapped onto a neuromorphic platform, enabling the real-time (~1000 fps) and energy-efficient (~70 mW) assignment of key poses to action classes. Last, it is shown how an associative learning scheme similar to the one applied in the neural model for the learning of biological motion representations can be used for the learning of visual category and subcategory representations. Here, instar learning is used to learn representations of visual categories, while outstar learning on the other hand is applied to establish representations of the expected input distribution. The category specific pattern is propagated back to the preceding stage where a residual signal reflecting the difference to the current input signal is derived. This difference is emphasized by modulation of the input with the residual signal and a subsequent normalization. If the difference is large enough, a new subcategory representation is established.dc.description.abstract
Languageen_USdc.language.iso
PublisherUniversität Ulmdc.publisher
Articles in publ.G. Layher and H. Neumann (2018). “Points and Stripes: A Novel Technique for Masking Biological Motion Point-Light Stimuli”. In: Frontiers in Psychology 9, p. 12. ISSN: 1664-1078. DOI: 10.3389/fpsyg.2018.01455dc.relation.haspart
Articles in publ.G. Layher, M. A. Giese, and H. Neumann (2014a). “Learning Representations of Animated Motion Sequences — A Neural Model”. In: Topics in Cognitive Science 6.1, pp. 170–182. ISSN: 1756-8765. DOI: 10.1111/tops.12075dc.relation.haspart
Articles in publ.G. Layher, T. Brosch, and H. Neumann (2017a). “Real-time Biologically Inspired Action Recognition from Key Poses using a Neuromorphic Architecture”. In: Frontiers in Neurorobotics 11.13, p. 19. ISSN: 1662-5218. DOI: 10.3389/fnbot.2017.00013dc.relation.haspart
Articles in publ.G. Layher, F. Schrodt, M. V. Butz, and H. Neumann (2014b). “Adaptive Learning in a Compartmental Model of Visual Cortex - How Feedback Enables Stable Category Learning and Refinement”. In: Frontiers in Psychology 5.1287, p. 19. ISSN: 1664-1078. DOI: 10.3389/fpsyg. 2014.01287dc.relation.haspart
LicenseStandarddc.rights
Link to license texthttps://oparu.uni-ulm.de/xmlui/license_v3dc.rights.uri
KeywordBiological motiondc.subject
KeywordNeural modeldc.subject
KeywordForm and motion processingdc.subject
KeywordArtificial neural networksdc.subject
KeywordDeep learningdc.subject
KeywordAction recognitiondc.subject
KeywordUnsupervised learningdc.subject
KeywordImplied motiondc.subject
KeywordPoint-light stimulidc.subject
Dewey Decimal GroupDDC 004 / Data processing & computer sciencedc.subject.ddc
Dewey Decimal GroupDDC 150 / Psychologydc.subject.ddc
LCSHPsychophysicsdc.subject.lcsh
LCSHNeural networks (Computer science)dc.subject.lcsh
LCSHMachine learningdc.subject.lcsh
LCSHMotion perception (Vision)dc.subject.lcsh
TitleWhat, where, and when? Mechanisms of learning biological motion representationsdc.title
Resource typeDissertationdc.type
Date of acceptance2019-06-05dcterms.dateAccepted
RefereeNeumann, Heikodc.contributor.referee
RefereeMinker, Wolfgangdc.contributor.referee
DOIhttp://dx.doi.org/10.18725/OPARU-17461dc.identifier.doi
PPN1670662217dc.identifier.ppn
URNhttp://nbn-resolving.de/urn:nbn:de:bsz:289-oparu-17518-3dc.identifier.urn
GNDPsychophysikdc.subject.gnd
GNDBewegungswahrnehmungdc.subject.gnd
GNDBewegungsanalyse <Technik>dc.subject.gnd
GNDMotorisches Lernendc.subject.gnd
FacultyFakultät für Ingenieurwissenschaften, Informatik und Psychologieuulm.affiliationGeneral
InstitutionInstitut für Neuroinformatikuulm.affiliationSpecific
InstitutionInstitut für Nachrichtentechnikuulm.affiliationSpecific
Grantor of degreeFakultät für Ingenieurwissenschaften, Informatik und Psychologieuulm.thesisGrantor
DCMI TypeTextuulm.typeDCMI
CategoryPublikationenuulm.category
FundingEine Companion-Technologie für kognitive technische Systeme / DFG [SFB/TRR 62, 54371073]uulm.funding
xmlui.metadata.uulm.unibibliographiejauulm.unibibliographie


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record