Universität zu Köln

Ferres, Kim, Schloesser, Timo and Gloor, Peter A. (2022). Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut. Future Internet, 14 (4). BASEL: MDPI. ISSN 1999-5903

Full text not available from this repository.

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.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Ferres, Kim UNSPECIFIED UNSPECIFIED UNSPECIFIED Schloesser, Timo UNSPECIFIED UNSPECIFIED UNSPECIFIED Gloor, Peter A. UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-664291
DOI:	10.3390/fi14040097
Journal or Publication Title:	Future Internet
Volume:	14
Number:	4
Date:	2022
Publisher:	MDPI
Place of Publication:	BASEL
ISSN:	1999-5903
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language RECOGNITION Multiple languages Computer Science, Information Systems Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/66429