Learning Strategies to Select Point Cloud Descriptors for 3D Object Classification: A Proposal

dc.contributor.authorGarstka, Jensen_US
dc.contributor.authorPeters, Gabrieleen_US
dc.contributor.editorMathias Paulin and Carsten Dachsbacheren_US
dc.date.accessioned2014-12-16T07:10:01Z
dc.date.available2014-12-16T07:10:01Z
dc.date.issued2014en_US
dc.description.abstractWe propose a reinforcement learning approach for an adaptive selection and application of 3D point cloud feature descriptors for the purpose of 3D object classification. The result of the learning process is an autonomously learned strategy of selection of descriptors with the property that the successive application of these descriptors to a 3D point cloud yields high classification rates among a large number of object classes. The order in which the descriptors are applied to an unfamiliar point cloud depends on the features calculated in previous steps of the descriptor sequence, i.e., the sequence of descriptors depends on the object to be classified, thus it is highly adaptive. Our approach starts with a given number of descriptors and object classes, but it is able to adapt dynamically to changes in the environment. For example, further descriptors can be added during the learning process, and new object classes are created autonomously if necessary.en_US
dc.description.seriesinformationEurographics 2014 - Postersen_US
dc.identifier.issn1017-4656en_US
dc.identifier.urihttps://doi.org/10.2312/egp.20141065en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.4.8 [Image Processing and Computer Vision]en_US
dc.subjectScene Analysisen_US
dc.subjectObject recognitionen_US
dc.subjectI.2.6 [Artificial Intelligence]en_US
dc.subjectLearningen_US
dc.subjectReinforcement Learningen_US
dc.subjectI.2.10 [Artificial Intelligence]en_US
dc.subjectVision and Scene Understandingen_US
dc.subject3D/stereo scene analysisen_US
dc.titleLearning Strategies to Select Point Cloud Descriptors for 3D Object Classification: A Proposalen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
011-012.pdf
Size:
132.5 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
poster1016.pdf
Size:
2.21 MB
Format:
Adobe Portable Document Format
Collections