Skip to main content Accessibility help
×
Home

Developing a multi-Kinect-system for monitoring in dairy cows: object recognition and surface analysis using wavelets

  • J. Salau (a1) (a2), J. H. Haas (a1), G. Thaller (a1), M. Leisen (a3) and W. Junge (a1)...

Abstract

Camera-based systems in dairy cattle were intensively studied over the last years. Different from this study, single camera systems with a limited range of applications were presented, mostly using 2D cameras. This study presents current steps in the development of a camera system comprising multiple 3D cameras (six Microsoft Kinect cameras) for monitoring purposes in dairy cows. An early prototype was constructed, and alpha versions of software for recording, synchronizing, sorting and segmenting images and transforming the 3D data in a joint coordinate system have already been implemented. This study introduced the application of two-dimensional wavelet transforms as method for object recognition and surface analyses. The method was explained in detail, and four differently shaped wavelets were tested with respect to their reconstruction error concerning Kinect recorded depth maps from different camera positions. The images’ high frequency parts reconstructed from wavelet decompositions using the haar and the biorthogonal 1.5 wavelet were statistically analyzed with regard to the effects of image fore- or background and of cows’ or persons’ surface. Furthermore, binary classifiers based on the local high frequencies have been implemented to decide whether a pixel belongs to the image foreground and if it was located on a cow or a person. Classifiers distinguishing between image regions showed high (⩾0.8) values of Area Under reciever operation characteristic Curve (AUC). The classifications due to species showed maximal AUC values of 0.69.

Copyright

Corresponding author

References

Hide All
Allwood, M 2008. The Satterthwaite formula for degrees of freedom in two-sample t-test. College Board Advanced Placement Program, AP Statistics. Retrieved October 27, 2014, from http://apcentral.collegeboard.com/apc/public/repository/ap05_stats_allwood_fin4prod. pdf.
Andersen, MR, Jensen, T, Lisouski, P, Mortensen, AK, Hansen, MK, Gregersen, T and Ahrent, P 2012. Kinect depth sensor evaluation for computer vision applications. Technical Report ECE-TR6, Department of Engineering, Aarhus University, Denmark.
Azzaro, G, Caccamo, M, Ferguson, JD, Battiato, S, Farinella, GM, Guarnera, GC, Puglisi, G, Petriglieri, R and Licitra, G 2011. Objective estimation of body condition score by modeling cow body shape from digital images. Journal of Dairy Science 94, 21262137.
Bercovich, A, Edan, Y, Alcahantis, V, Moallem, U, Parmet, Y, Honig, H, Maltz, E, Antler, A and Halachmi, I 2012. Automatic cow’s body condition scoring. Retrieved July 13, 2013, from cigr.ageng2012.org/images/fotosg/tabla_137_C0565.pdf.
Bergh, J, Ekstedt, F and Lindberg, M 2007. Wavelets mit Anwendungen in Signal- und Bildverarbeitung. Springer, Berlin/Heidelberg, Germany.
Bradley, AP 1997. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition 30, 11451159.
Cohen, J 1988. Statistical power analysis for the behavioral sciences, 2nd edition. Lawrence Erlbaum Associates, Hillsdale, NJ, USA.
Daubechies, I 1990. The wavelet transform, time-frequency localization and signal analysis. IEEE Transactions on Information Theory 36, 9611005.
Dudewicz, EJ, Ma, Y, Mai, ES and Su, H 2007. Exact solutions to the Behrens–Fisher Problem: asymptotically optimal and finite sample efficient choice among. Journal of Statistical Planning and Inference 137, 15841605.
Farge, M 1992. Wavelet transforms and their applications to turbulence. Annual Review of Fluid Mechanics 24, 395457.
Fawcett, T 2006. An introduction to ROC analysis. Pattern Recognition Letters 27, 861874.
Halachmi, I, Klopcic, M, Polak, P, Roberts, DJ and Bewley, JM 2013. Automatic assessment of dairy cattle body condition score using thermal imaging. Computers and Electronics in Agriculture 99, 3540.
Hansard, M, Lee, S, Choi, O and Horaud, R 2012. Time-of-flight cameras – principles, methods and applications. Springer, London, England.
Inc. The MathWorks 2007a MATLAB Release Notes. Retrieved March 1, 2010, from www.letu.edu/people/jaytevis/Programming-Languages/MATLAB/Mathworks-Tutorials/16-MATLAB.
Inc. The MathWorks 2007b Statistics toolbox user’s guide, MATLAB. Inc. The MathWorks. Retrieved February 27, 2008, from http://de.mathworks.com/products/statistics.
Kaur, S and Mehra, R 2010. High speed and area efficient 2D dwt processor based image compression. Signal & Image Processing: An International Journal (SIPIJ) 1, 2231.
Kiencke, U, Schwarz, M and Weickert, T 2008. Signalverarbeitung, Zeit-Frequenz-Analyse und Schätzverfahren, Oldenbourg. Wissenschaftsverlag GmbH, Munich, Germany.
Krukowski, M 2009. Automatic determination of body condition score of dairy cows from 3D images. Master’s thesis, KTH Computer Science and Communication, Stockholm, Sweden.
Lau, D 2013. The science behind kinects or kinect 1.0 versus 2.0. Retrieved August 22, 2014, from http://www.gamasutra.com/blogs/DanielLau/20131127/205820/ The_Science_Behind_Kinects_or_Kinect_10_versus_20.php.
Louis, AK, Maaß, P and Rieder, A 1998. Wavelets: Theorie und Anwendung, 2nd edition. B.G.Teubner, Stuttgart, Germany.
Megahed, AI, Moussa, AM, Elrefaie, HB and Marghany, YM 2008. Selection of a suitable mother wavelet for analyzing power system fault transients. IEEE Power and Energy Society General Meeting – Conversion and Delivery of Electrical Energy in the 21st Centruy, 1–7.
Misiti, M, Misiti, Y, Oppenheim, G and Poggi, JM 2014. Wavelet toolbox user’s guide, MATLAB. The MathWorks Inc. Retrieved November 1, 2014, from http://fr.mathworks.com/help/pdf_doc/wavelet/wavelet_ug.pdf.
Mohd Tumari, SZ, Sudirman, R and Ahmad, AH 2013. Selection of a suitable wavelet for cognitive. Memory Using Electroencephalograph Signal. Engineering 5, 1519.
OpenNI 2013. The SimpleViewer-example from the OpenNI-project. Retrieved July 31, 2013, from https://github.com/OpenNI.
Pluk, A, Bahr, C, Poursaberi, A, Maertens, W, Van Nuffel, A and Berckmanns, D 2012. Automatic measurement of touch and release angles of the fetlock joint for lameness detection in dairy cattle using vision techniques. Journal of dairy Science 95, 17381748.
Salau, J, Bauer, U, Haas, JH, Thaller, G, Harms, J and Junge, W 2015. Quantification of the effects of fur, fur color, and velocity on time-of-flight technology in dairy production. SpringerPlus 4, 114.
Salau, J, Haas, JH, Junge, W, Bauer, U, Harms, J and Bieletzki, S 2014. Feasibility of automated body trait determination using the SR4K time-of-flight camera in cow barns. Springer Plus 3, 116.
Salau, J, Haas, JH, Thaller, G, Leisen, M and Junge, W 2014. Development of a multi-kinect-system for gait analysis and measuring body characteristics in dairy cows. Proceedings of the EU-PLF, 25 August 2014, Copenhagen, Denmark.
Song, X, Leroy, T, Vranken, E, Maertens, W, Sonck, B and Berckmans, D 2008. Automatic detection of lameness in dairy cattle-vision-based trackway analysis in cow’s locomotion. Computers and Electronics in Agriculture 64, 3944.
Szeliski, R 2011. Computer vision: algorithms and applications. Springer, London, England.
Tucker, CB, Weary, DM and Fraser, D 2004. Free-stall dimensions: effects on preference and stall usage. Journal of Dairy Science 87, 12081216.
Van Hertem, T, Alchanatis, V, Antler, A, Maltz, E, Halachmi, I, Schlageter-Tello, A, Lokhorst, C, Viazzi, S, Romanini, CEB, Pluk, A, Bahr, C and Berckmans, D 2013. Comparison of segmentation algorithms for cow contour extraction from natural barn background in side view images. Computers and Electronics in Agriculture 91, 6574.
Van Hertem, T, Viazzi, S, Steensels, M, Maltz, E, Antler, A, Alchanatis, V, Schlageter-Tello, A, Lokhorst, C, Romanini, CEB, Bahr, C, Berckmans, D and Halachmi, I 2014. Automatic lameness detection based on consecutive 3D-video recordings. Biosystems Engineering 119, 108116.
Viazzi, S, Bahr, C, Schlageter-Tello, A, Van Hertem, T, Romanini, CEB, Pluk, A, Halachmi, I, Lokhorst, C and Berckmans, D 2013. Analysis of individual classification of lameness using automatic measurement of back posture in dairy cattle. Journal of Dairy Science 96, 257266.
Viazzi, S, Bahr, C, Van Hertem, T, Schlageter-Tello, A, Romanini, CEB, Halachmi, I, Lokhorst, C and Berckmans, D 2014. Comparison of a three-dimensional and a two-dimensional camera system for automated measurement of back posture in dairy cattle. Computers and Electronics in Agriculture 100, 139147.
Weber, W, Salau, J, Haas, JH, Junge, W, Bauer, U, Harms, J, Suhr, O, Schönrock, K, Rothfuß, H, Bieletzki, S and Thaller, G 2014. Estimation of backfat thickness using extracted traits from an automatic 3D optical system in lactating Holstein-Friesian cows. Livestock Science 165, 129137.
Welch, BL 1947. The generalization of ‘Student’s’ problem when several different population variances are involved. Biometrika 34, 2835.
Wilcoxon, F 1945. Individual comparisons by ranking methods. Biometrics Bulletin 1, 8083.

Keywords

Related content

Powered by UNSILO
Type Description Title
PDF
Supplementary materials

Salau supplementary material
Figure S2

 PDF (901 KB)
901 KB
PDF
Supplementary materials

Salau supplementary material
Figure S1

 PDF (1.9 MB)
1.9 MB
VIDEO
Supplementary materials

Salau supplementary material
Video

 Video (6.5 MB)
6.5 MB
WORD
Supplementary materials

Salau supplementary material
Salau supplementary material S2

 Word (614 KB)
614 KB
WORD
Supplementary materials

Salau supplementary material
Table S1

 Word (26 KB)
26 KB
WORD
Supplementary materials

Salau supplementary material
Table S2

 Word (25 KB)
25 KB

Developing a multi-Kinect-system for monitoring in dairy cows: object recognition and surface analysis using wavelets

  • J. Salau (a1) (a2), J. H. Haas (a1), G. Thaller (a1), M. Leisen (a3) and W. Junge (a1)...

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed.