uu.seUppsala universitets publikationer
Ändra sökning
Länk till posten
Permanent länk

Direktlänk
BETA
Publikationer (8 of 8) Visa alla publikationer
Asplund, T., Bengtsson Bernander, K. & Breznik, E. (2019). CNNs on Graphs: A New Pooling Approach and Similarities to Mathematical Morphology. In: : . Paper presented at Swedish Symposium on Deep Learning.
Öppna denna publikation i ny flik eller fönster >>CNNs on Graphs: A New Pooling Approach and Similarities to Mathematical Morphology
2019 (Engelska)Konferensbidrag, Poster (med eller utan abstract) (Övrigt vetenskapligt)
Nationell ämneskategori
Data- och informationsvetenskap
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-398138 (URN)
Konferens
Swedish Symposium on Deep Learning
Tillgänglig från: 2019-12-02 Skapad: 2019-12-02 Senast uppdaterad: 2019-12-02
Asplund, T., Serna, A., Marcotegui, B., Strand, R. & Luengo Hendriks, C. L. (2019). Mathematical Morphology on Irregularly Sampled Data Applied to Segmentation of 3D Point Clouds of Urban Scenes. In: International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing: . Paper presented at International Symposium on Mathematical Morphology (ISMM 2019).
Öppna denna publikation i ny flik eller fönster >>Mathematical Morphology on Irregularly Sampled Data Applied to Segmentation of 3D Point Clouds of Urban Scenes
Visa övriga...
2019 (Engelska)Ingår i: International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing, 2019Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper proposes an extension of mathematical morphology on irregularly sampled signals to 3D point clouds. The proposed method is applied to the segmentation of urban scenes to show its applicability to the analysis of point cloud data. Applying the proposed operators has the desirable side-effect of homogenizing signals that are sampled heterogeneously. In experiments we show that the proposed segmentation algorithm yields good results on the Paris-rue-Madame database and is robust in terms of sampling density, i.e. yielding similar labelings for more sparse samplings of the same scene.

Nationell ämneskategori
Signalbehandling
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-388524 (URN)10.1007/978-3-030-20867-7_29 (DOI)978-3-030-20866-0 (ISBN)978-3-030-20867-7 (ISBN)
Konferens
International Symposium on Mathematical Morphology (ISMM 2019)
Forskningsfinansiär
Vetenskapsrådet, 2014-5983
Tillgänglig från: 2019-07-01 Skapad: 2019-07-01 Senast uppdaterad: 2019-10-17
Asplund, T. (2019). Precise Image-Based Measurements through Irregular Sampling. (Doctoral dissertation). Uppsala: Acta Universitatis Upsaliensis
Öppna denna publikation i ny flik eller fönster >>Precise Image-Based Measurements through Irregular Sampling
2019 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Alternativ titel[sv]
Noggranna bildbaserade mätningar via irreguljär sampling
Abstract [en]

Mathematical morphology is a theory that is applicable broadly in signal processing, but in this thesis we focus mainly on image data. Fundamental concepts of morphology include the structuring element and the four operators: dilation, erosion, closing, and opening. One way of thinking about the role of the structuring element is as a probe, which traverses the signal (e.g. the image) systematically and inspects how well it "fits" in a certain sense that depends on the operator.

Although morphology is defined in the discrete as well as in the continuous domain, often only the discrete case is considered in practice. However, commonly digital images are a representation of continuous reality and thus it is of interest to maintain a correspondence between mathematical morphology operating in the discrete and in the continuous domain. Therefore, much of this thesis investigates how to better approximate continuous morphology in the discrete domain. We present a number of issues relating to this goal when applying morphology in the regular, discrete case, and show that allowing for irregularly sampled signals can improve this approximation, since moving to irregularly sampled signals frees us from constraints (namely those imposed by the sampling lattice) that harm the correspondence in the regular case. The thesis develops a framework for applying morphology in the irregular case, using a wide range of structuring elements, including non-flat structuring elements (or structuring functions) and adaptive morphology. This proposed framework is then shown to better approximate continuous morphology than its regular, discrete counterpart.

Additionally, the thesis contains work dealing with regularly sampled images using regular, discrete morphology and weighting to improve results. However, these cases can be interpreted as specific instances of irregularly sampled signals, thus naturally connecting them to the overarching theme of irregular sampling, precise measurements, and mathematical morphology.

Ort, förlag, år, upplaga, sidor
Uppsala: Acta Universitatis Upsaliensis, 2019. s. 63
Serie
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1869
Nyckelord
image analysis, image processing, mathematical morphology, irregular sampling, adaptive morphology, missing samples, continuous morphology, path opening.
Nationell ämneskategori
Signalbehandling Annan data- och informationsvetenskap
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-395205 (URN)978-91-513-0783-1 (ISBN)
Disputation
2019-12-06, Room 2446, ITC, Lägerhyddsvägen 2, Uppsala, 13:00 (Engelska)
Opponent
Handledare
Forskningsfinansiär
Vetenskapsrådet, 2014-5983
Tillgänglig från: 2019-11-13 Skapad: 2019-10-17 Senast uppdaterad: 2019-11-13
Asplund, T., Luengo Hendriks, C. L., Thurley, M. J. & Strand, R. (2017). Mathematical morphology on irregularly sampled data in one dimension. Mathematical Morphology - Theory and Applications, 2(1), 1-24
Öppna denna publikation i ny flik eller fönster >>Mathematical morphology on irregularly sampled data in one dimension
2017 (Engelska)Ingår i: Mathematical Morphology - Theory and Applications, ISSN 2353-3390, Vol. 2, nr 1, s. 1-24Artikel i tidskrift (Refereegranskat) Published
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-337288 (URN)10.1515/mathm-2017-0001 (DOI)
Forskningsfinansiär
Vetenskapsrådet, 2014-5983
Tillgänglig från: 2017-12-29 Skapad: 2017-12-21 Senast uppdaterad: 2019-10-17Bibliografiskt granskad
Asplund, T., Luengo Hendriks, C. L., Thurley, M. & Strand, R. (2017). Mathematical Morphology on Irregularly Sampled Signals. In: Computer Vision – ACCV 2016 Workshops. ACCV 2016: . Paper presented at 13th Asian Conference on Computer Vision (ACCV), Taipei, Taiwan, November 20-24, 2016 (pp. 506-520). Springer, 10117
Öppna denna publikation i ny flik eller fönster >>Mathematical Morphology on Irregularly Sampled Signals
2017 (Engelska)Ingår i: Computer Vision – ACCV 2016 Workshops. ACCV 2016, Springer, 2017, Vol. 10117, s. 506-520Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper introduces a new operator that can be used to approximate continuous-domain mathematical morphology on irregularly sampled surfaces. We define a new way of approximating the continuous domain dilation by duplicating and shifting samples according to a flat continuous structuring element. We show that the proposed algorithm can better approximate continuous dilation, and that dilations may be sampled irregularly to achieve a smaller sampling without greatly compromising the accuracy of the result.

Ort, förlag, år, upplaga, sidor
Springer, 2017
Serie
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 10117
Nationell ämneskategori
Datavetenskap (datalogi) Beräkningsmatematik
Identifikatorer
urn:nbn:se:uu:diva-309921 (URN)10.1007/978-3-319-54427-4_37 (DOI)000426193700037 ()978-3-319-54427-4 (ISBN)978-3-319-54426-7 (ISBN)
Konferens
13th Asian Conference on Computer Vision (ACCV), Taipei, Taiwan, November 20-24, 2016
Forskningsfinansiär
Vetenskapsrådet, 2014-5983
Tillgänglig från: 2016-12-08 Skapad: 2016-12-08 Senast uppdaterad: 2019-10-17Bibliografiskt granskad
Asplund, T., Luengo, C., Thurley, M. & Strand, R. (2016). A New Approach to Mathematical Morphology on One Dimensional Sampled Signals. In: IEEE Proceedings, International Conference on Pattern Recognition (ICPR 2016), Cancun, Mexico, 2016: . Paper presented at International Conference on Pattern Recognition (ICPR 2016), Cancun, Mexico, 2016.
Öppna denna publikation i ny flik eller fönster >>A New Approach to Mathematical Morphology on One Dimensional Sampled Signals
2016 (Engelska)Ingår i: IEEE Proceedings, International Conference on Pattern Recognition (ICPR 2016), Cancun, Mexico, 2016, 2016Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

We present a new approach to approximate continuous-domain mathematical morphology operators. The approach is applicable to irregularly sampled signals. We define a dilation under this new approach, where samples are duplicated and shifted according to the flat, continuous structuring element. We define the erosion by adjunction, and the opening and closing by composition. These new operators will significantly increase precision in image measurements. Experiments show that these operators indeed approximate continuous-domain operators better than the standard operators on sampled one-dimensional signals, and that they may be applied to signals using structuring elements smaller than the distance between samples. We also show that we can apply the operators to scan lines of a two-dimensional image to filter horizontal and vertical linear structures.

Nationell ämneskategori
Datavetenskap (datalogi) Beräkningsmatematik
Identifikatorer
urn:nbn:se:uu:diva-309925 (URN)10.1109/ICPR.2016.7900244 (DOI)000406771303148 ()
Konferens
International Conference on Pattern Recognition (ICPR 2016), Cancun, Mexico, 2016
Forskningsfinansiär
Vetenskapsrådet, 2014-5983
Tillgänglig från: 2016-12-08 Skapad: 2016-12-08 Senast uppdaterad: 2018-03-16Bibliografiskt granskad
Asplund, T., Luengo Hendriks, C. L., Thurley, M. J. & Strand, R. Adaptive Mathematical Morphology on Irregularly Sampled Signals in Two Dimensions.
Öppna denna publikation i ny flik eller fönster >>Adaptive Mathematical Morphology on Irregularly Sampled Signals in Two Dimensions
(Engelska)Ingår i: Artikel i tidskrift (Refereegranskat) Submitted
Nationell ämneskategori
Signalbehandling
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-395204 (URN)
Forskningsfinansiär
Vetenskapsrådet, 2014-5983
Tillgänglig från: 2019-10-15 Skapad: 2019-10-15 Senast uppdaterad: 2019-10-25
Asplund, T., Luengo Hendriks, C. L., Thurley, M. J. & Strand, R. Estimating the Gradient for Images with Missing Samples Using Elliptical Structuring Elements.
Öppna denna publikation i ny flik eller fönster >>Estimating the Gradient for Images with Missing Samples Using Elliptical Structuring Elements
(Engelska)Ingår i: Artikel i tidskrift (Refereegranskat) Submitted
Nationell ämneskategori
Signalbehandling
Forskningsämne
Datoriserad bildbehandling
Identifikatorer
urn:nbn:se:uu:diva-395200 (URN)
Forskningsfinansiär
Vetenskapsrådet, 2014-5983
Tillgänglig från: 2019-10-15 Skapad: 2019-10-15 Senast uppdaterad: 2019-10-25
Organisationer
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0002-0612-558x

Sök vidare i DiVA

Visa alla publikationer