English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Dataset generation and Bonobo classification from weakly labelled videos

Martin, P.-E. (2024). Dataset generation and Bonobo classification from weakly labelled videos. In K. Arai (Ed.), Intelligent Systems and Applications: Lecture Notes in Networks and Systems: Proceedings of the 2023 Intelligent Systems Conference (IntelliSys), Volume 2 (pp. 689-700). Cham: Springer Nature Switzerland. doi:10.1007/978-3-031-47724-9_45.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-000F-3960-5 Version Permalink: https://hdl.handle.net/21.11116/0000-000F-3961-4
Genre: Book Chapter

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Martin, Pierre-Etienne1, Author                 
Affiliations:
1Department of Comparative Cultural Psychology, Max Planck Institute for Evolutionary Anthropology, Max Planck Society, ou_3040267              

Content

show
hide
Free keywords: Bonobos classification; Machine learning; Convolutional neural networks; Data splitting; Automatic dataset generation
 Abstract: This paper presents a bonobo detection and classification pipeline built from the commonly used machine learning methods. Such application is motivated by the need to test bonobos in their enclosure using touch screen devices without human assistance. This work introduces a newly acquired dataset based on bonobo recordings generated semi-automatically. The recordings are weakly labelled and fed to a macaque detector in order to spatially detect the individual present in the video. Handcrafted features coupled with different classification algorithms and deep-learning methods using a ResNet architecture are investigated for bonobo identification. Performance is compared in terms of classification accuracy on the splits of the database using different data separation methods. We demonstrate the importance of data preparation and how a wrong data separation can lead to false good results. Finally, after a meaningful separation of the data, the best classification performance is obtained using a fine-tuned ResNet model and reaches 75% of accuracy.

Details

show
hide
Language(s): eng - English
 Dates: 2024-04-192024
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1007/978-3-031-47724-9_45
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Intelligent Systems and Applications: Lecture Notes in Networks and Systems : Proceedings of the 2023 Intelligent Systems Conference (IntelliSys), Volume 2
Source Genre: Book
 Creator(s):
Arai, Kohei1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Cham : Springer Nature Switzerland
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 689 - 700 Identifier: ISBN: 978-3-031-47723-2
ISBN: 978-3-031-47724-9