Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut
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,...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2022
|
| Online Access: | https://hdl.handle.net/1721.1/141371 |
| _version_ | 1826211058785714176 |
|---|---|
| author | Ferres, Kim Schloesser, Timo Gloor, Peter A. |
| author2 | Massachusetts Institute of Technology. Center for Collective Intelligence |
| author_facet | Massachusetts Institute of Technology. Center for Collective Intelligence Ferres, Kim Schloesser, Timo Gloor, Peter A. |
| author_sort | Ferres, Kim |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T14:59:54Z |
| format | Article |
| id | mit-1721.1/141371 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T14:59:54Z |
| publishDate | 2022 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | mit-1721.1/1413712023-02-10T20:10:31Z Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut Ferres, Kim Schloesser, Timo Gloor, Peter A. Massachusetts Institute of Technology. Center for Collective Intelligence 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. 2022-03-24T19:08:29Z 2022-03-24T19:08:29Z 2022-03-22 2022-03-24T14:47:07Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/141371 Future Internet 14 (4): 97 (2022) PUBLISHER_CC http://dx.doi.org/10.3390/fi14040097 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Multidisciplinary Digital Publishing Institute Multidisciplinary Digital Publishing Institute |
| spellingShingle | Ferres, Kim Schloesser, Timo Gloor, Peter A. Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut |
| title | Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut |
| title_full | Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut |
| title_fullStr | Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut |
| title_full_unstemmed | Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut |
| title_short | Predicting Dog Emotions Based on Posture Analysis Using DeepLabCut |
| title_sort | predicting dog emotions based on posture analysis using deeplabcut |
| url | https://hdl.handle.net/1721.1/141371 |
| work_keys_str_mv | AT ferreskim predictingdogemotionsbasedonpostureanalysisusingdeeplabcut AT schloessertimo predictingdogemotionsbasedonpostureanalysisusingdeeplabcut AT gloorpetera predictingdogemotionsbasedonpostureanalysisusingdeeplabcut |