TY  - JOUR
A1  - Müller, Karsten
T1  - Zustandserfassung von Kanalisationen : Strategien entwickeln
JF  - wwt Wasserwirtschaft und Wassertechnik. 2007, H. 3
Y1  - 2007
SN  - 1438-5716
SP  - 10
EP  - 15
ER  - 
TY  - JOUR
A1  - Müller, Karsten
T1  - Einsatzmöglichkeiten von Bilderkennungsverfahren zur Zustandserfassung von Kanalisationen
JF  - Bbr : Leitungsbau, Brunnenbau, Geothermie. Bd. 59. 2008, H. 5
Y1  - 2008
SN  - 1611-1478
SP  - 16
EP  - 21
ER  - 
TY  - CHAP
A1  - Müller, Karsten
T1  - Strategien zur Zustandserfassung von Kanalisationen
T2  - Integration in der Abwasserentsorgung : Tagungsband Dresden, 04.10.2007 / Dresdner Kolloquium zur Siedlungswasserwirtschaft / Hrsg.: Peter Krebs. Dresdner Berichte. 29
Y1  - 2007
SP  - 39
EP  - 50
PB  - Inst. für Siedlungs- und Industriewasserwirtschaft
CY  - Dresden
ER  - 
TY  - THES
A1  - Müller, Karsten
T1  - Strategien zur Zustandserfassung von Kanalisationen
Y1  - 2005
N1  - Aachen, Techn. Hochsch., Diss., 2005
ER  - 
TY  - JOUR
A1  - Kirstein, Simon
A1  - Müller, Karsten
A1  - Walecki-Mingers, Mark
A1  - Deserno, Thomas M.
T1  - Robust adaptive flow line detection in sewer pipes
JF  - Automation in construction
N2  - As part of a novel approach to automatic sewer inspection, this paper presents a robust algorithm for automatic flow line detection. A large image repository is obtained from about 50,000 m sewers to represent the high variability of real world sewer systems. Automatic image processing combines Canny edge detection, Hough transform for straight lines and cost minimization using Dijkstra's shortest path algorithm. Assuming that flow lines are mostly smoothly connected horizontal structures, piecewise flow line delineation is reduced to a process of selecting adjacent line candidates. Costs are derived from the gap between adjacent candidates and their reliability. A single parameter α enables simple control of the algorithm. The detected flow line may precisely follow the segmented edges (α = 0.0) or minimize gaps at joints (α = 1.0). Both, manual and ground truth-based analysis indicate that α = 0.8 is optimal and independent of the sewer's material. The algorithm forms an essential step to further automation of sewer inspection.
Y1  - 2012
U6  - http://dx.doi.org/10.1016/j.autcon.2011.05.009
SN  - 1872-7891 (E-Journal) ; 0926-5805 (Print)
IS  - 21
SP  - 24
EP  - 31
PB  - Elsevier
CY  - Amsterdam
ER  - 
TY  - CHAP
A1  - Ganegedara, H.
A1  - Alahakoon, D.
A1  - Mashford, J.
A1  - Paplinski, A.
A1  - Müller, Karsten
A1  - Deserno, T. M.
T1  - Self organising map based region of interest labelling for automated defect identification in large sewer pipe image collections
T2  - The 2012 International Joint Conference on Neural Networks (IJCNN) : 10 - 15 June 2012, Brisbane, Australia ; [part of the] 2012 IEEE World Congress on Computational Intelligence (IEEE-WCCI 2012)
Y1  - 2012
SN  - 978-1-4673-1490-9
PB  - IEEE
CY  - Piscataway, NJ
ER  -