Home About Browse Search
Svenska


Computer vision algorithms as a modern tool for behavioural analysis in dairy cattle

Guzhva, Oleksiy (2018). Computer vision algorithms as a modern tool for behavioural analysis in dairy cattle. Diss. (sammanfattning/summary) Alnarp : Sveriges lantbruksuniv., Acta Universitatis Agriculturae Sueciae, 1652-6880 ; 2018:33
ISBN 978-91-7760-206-4
eISBN 978-91-7760-207-1
[Doctoral thesis]

[img]
Preview
PDF
2MB

Abstract

Looking at modern dairy production, loose housing, i.e. free stalls became one of the most common practices, which, while widely implemented along with different management routines, do not always include the adjustments necessary for assuring animal welfare. The analysis of interactions occurring between cows in dairy barns and their effect on health and performance is of great importance for sustainable, animal-friendly production. The general aim of this thesis was to investigate the possibilities and limitations of computer vision approach for studying dairy cattle behaviour and interactions between animals, as well as take a first step towards the fully automated system for continuous surveillance in modern dairy barns.

In the first study, a seven-point shape-model for describing a cow from the mathematical perspective was proposed and investigated. A pilot study showed that the proposed Behavioural Detector based on the developed shape-model provided a solid basis for behavioural studies in a real-life dairy barn environment.

The second study investigated a classification case from the industry: how animal distribution and claw positioning in specific areas could affect the maximal load on floor elements. The results of the study provided more substantial background data for determining the dimensioning of the strength of the slats.

The third study aimed to take the first step towards an automated system (so-called WatchDog) for behavioural analysis and automatic filtering of the recorded video material. The results showed that the proposed solution is capable of detecting potentially interesting scenes in video-material with the precision of 92,8%.

In the fourth and final study, a state-of-the-art tracking/identification algorithm for multiple objects with near-real-time implementation in crowded scenes with varying illumination was developed and evaluated.

The algorithms forming the multi-modular WatchDog system and developed during this project are the crucial stepping stone towards a fully-automated solution for continuous surveillance of health and welfare-related parameters in dairy cattle. The proposed system could also serve as evaluation/benchmark tool for modern dairy barn assessment.

Keywords: dairy cattle, image analysis, Precision Livestock Farming, computer vision, deep learning, convolutional neural networks, social interactions, tracking, cow traffic

Authors/Creators:Guzhva, Oleksiy
Title:Computer vision algorithms as a modern tool for behavioural analysis in dairy cattle
Series/Journal:Acta Universitatis Agriculturae Sueciae (1652-6880)
Year of publishing :7 May 2018
Depositing date:24 April 2018
Volume:2018:33
Number of Pages:72
Papers/manuscripts:
NumberReferences
IGuzhva, O., Ardo, H., Herlin, A., Nilsson, M., Astrom, K. and Bergsten, C. (2016). Feasibility study for the implementation of an automatic system for the detection of social interactions in the waiting area of automatic milking stations by using a video surveillance system. Computers and Electronics in Agriculture 127, pp. 506-509.
IIArdo, H., Guzhva, O., Nilsson, M. and Herlin, A. (2016). Cows on concrete slats of the waiting area in a dairy barn estimated by use of image analysis (manuscript).
IIIArdo, H., Guzhva, O., Nilsson, M. and Herlin, A. (2017). A CNN-based Cow Interaction Watchdog. IET Computer Vision 12 (2), pp. 171-177.
IVGuzhva, O., Ardo, H., Nilsson, M. and Herlin, A. and Tufvesson, L. (2018). CNN-based animal detector with real-time tracking and identification features. Biosystems Engineering, (resubmitted after revision).
Place of Publication:Alnarp
Publisher:Department of Biosystems and Technology, Swedish University of Agricultural Sciences
ISBN for printed version:978-91-7760-206-4
ISBN for electronic version:978-91-7760-207-1
ISSN:1652-6880
Language:English
Publication Type:Doctoral thesis
Full Text Status:Public
Agris subject categories.:L Animal production > L01 Animal husbandry
Subjects:(A) Swedish standard research categories 2011 > 4 Agricultural Sciences > 402 Animal and Dairy Science > Animal and Dairy Science.
Agrovoc terms:dairy cattle, animal behaviour, animal housing, imagery, computer science, precision agriculture, image analysis
Keywords:dairy cattle, image analysis, Precision Livestock Farming, computer vision, deep learning, convolutional neural networks, social interactions, tracking, cow traffic
URN:NBN:urn:nbn:se:slu:epsilon-e-4847
Permanent URL:
http://urn.kb.se/resolve?urn=urn:nbn:se:slu:epsilon-e-4847
ID Code:15436
Faculty:VH - Faculty of Veterinary Medicine and Animal Science
Department:(LTJ, LTV) > Department of Biosystems and Technology (from 130101)
(VH) > Department of Biosystems and Technology (from 130101)
External funders:FORMAS
Deposited By: Oleksiy Guzhva
Deposited On:27 Apr 2018 06:47
Metadata Last Modified:24 May 2018 19:42

Repository Staff Only: item control page

Downloads

Downloads per year (since September 2012)

View more statistics

Downloads
Hits