Next Article in Journal
Bitcoin as a Safe Haven during COVID-19 Disease
Next Article in Special Issue
Examining Gender Bias of Convolutional Neural Networks via Facial Recognition
Previous Article in Journal
Time Series Surface Temperature Prediction Based on Cyclic Evolutionary Network Model for Complex Sea Area
Previous Article in Special Issue
Your Face Mirrors Your Deepest Beliefs—Predicting Personality and Morals through Facial Emotion Recognition
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut

1
Department of Information Systems and Information Management, University of Cologne, Pohligstrasse 1, 50969 Cologne, Germany
2
MIT Center for Collective Intelligence, 245 First Street, Cambridge, MA 02142, USA
*
Author to whom correspondence should be addressed.
Future Internet 2022, 14(4), 97; https://doi.org/10.3390/fi14040097
Submission received: 31 January 2022 / Revised: 18 March 2022 / Accepted: 18 March 2022 / Published: 22 March 2022
(This article belongs to the Collection Machine Learning Approaches for User Identity)

Abstract

This paper describes an emotion recognition system for dogs automatically identifying the emotions anger, fear, happiness, and relaxation. It is based on a previously trained machine learning model, which uses automatic pose estimation to differentiate emotional states of canines. Towards that goal, we have compiled a picture library with full body dog pictures featuring 400 images with 100 samples each for the states “Anger”, “Fear”, “Happiness” and “Relaxation”. A new dog keypoint detection model was built using the framework DeepLabCut for animal keypoint detector training. The newly trained detector learned from a total of 13,809 annotated dog images and possesses the capability to estimate the coordinates of 24 different dog body part keypoints. Our application is able to determine a dog’s emotional state visually with an accuracy between 60% and 70%, exceeding human capability to recognize dog emotions.
Keywords: neural networks; machine learning; dog emotion detection; dog emotion neural networks; machine learning; dog emotion detection; dog emotion

Share and Cite

MDPI and ACS Style

Ferres, K.; Schloesser, T.; Gloor, P.A. Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut. Future Internet 2022, 14, 97. https://doi.org/10.3390/fi14040097

AMA Style

Ferres K, Schloesser T, Gloor PA. Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut. Future Internet. 2022; 14(4):97. https://doi.org/10.3390/fi14040097

Chicago/Turabian Style

Ferres, Kim, Timo Schloesser, and Peter A. Gloor. 2022. "Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut" Future Internet 14, no. 4: 97. https://doi.org/10.3390/fi14040097

APA Style

Ferres, K., Schloesser, T., & Gloor, P. A. (2022). Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut. Future Internet, 14(4), 97. https://doi.org/10.3390/fi14040097

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop