Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Incidence of farrowing assistance and neonatal challenges in hyperprolific sows: Insights from a field study.

Theriogenology·2026
Same author

A large-scale multitrait meta-analysis of 11 health and 22 conformation traits in German Holstein cows.

Journal of dairy science·2025
Same author

Does the use of Beef-on-Dairy lead to increased longevity in dairy herds?

Animal : an international journal of animal bioscience·2025
Same author

Genomic-based genetic parameters and genome-wide association studies for productive and reproductive traits in Beef-on-Dairy crossbreds.

Frontiers in genetics·2025
Same author

Sequence-based genome-wide association study and fine-mapping in German Holstein reveal new quantitative trait loci for health traits.

Journal of dairy science·2025
Same author

Factors influencing calving difficulty and gestation length in dairy cows inseminated with beef sires.

Animal : an international journal of animal bioscience·2024

Related Experiment Video

Updated: Mar 26, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.1K

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

J Salau1, J H Haas1, G Thaller1

  • 11Institute of Animal Breeding and Husbandry,Kiel University,Olshausenstraße 40,24098 Kiel,Germany.

Animal : an International Journal of Animal Bioscience
|February 4, 2016
PubMed
Summary

This study developed a multi-camera 3D monitoring system for dairy cows using Microsoft Kinect sensors. Wavelet transforms enabled accurate object recognition and surface analysis for cow and person identification.

Keywords:
3D cameradairy cattlemonitoring systemobject recognitionwavelet transform

More Related Videos

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.3K
Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings
07:08

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Published on: August 1, 2018

8.8K

Related Experiment Videos

Last Updated: Mar 26, 2026

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.1K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.3K
Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings
07:08

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Published on: August 1, 2018

8.8K

Area of Science:

  • Agricultural Engineering
  • Computer Vision
  • Animal Monitoring

Background:

  • Previous camera systems for dairy cattle monitoring primarily used 2D cameras with limited applications.
  • A need exists for advanced 3D monitoring systems to improve dairy cow management and welfare.

Purpose of the Study:

  • To develop and evaluate a novel multi-camera 3D monitoring system for dairy cows.
  • To assess the efficacy of two-dimensional wavelet transforms for object recognition and surface analysis in 3D depth data.

Main Methods:

  • A prototype system with six Microsoft Kinect 3D cameras was constructed.
  • Software was developed for data recording, synchronization, segmentation, and 3D data transformation.
  • Two-dimensional wavelet transforms (Haar, Biorthogonal 1.5) were applied to Kinect depth maps for reconstruction and analysis.
  • Binary classifiers were implemented based on local high frequencies for foreground detection and species identification.

Main Results:

  • Wavelet-based reconstruction error was analyzed for different wavelets and camera positions.
  • Statistical analysis revealed the impact of foreground/background and cow/person surfaces on image high-frequency components.
  • Classifiers achieved high Area Under the ROC Curve (AUC) values (⩾0.8) for distinguishing image regions (foreground/background).
  • Species classification accuracy reached a maximum AUC of 0.69.

Conclusions:

  • The developed multi-camera 3D system shows promise for advanced dairy cattle monitoring.
  • Two-dimensional wavelet transforms are effective for object and surface analysis in 3D depth data from Kinect cameras.
  • Further refinement is needed to improve species-specific classification accuracy.