Dataset Generation and Bonobo Classification from Weakly Labelled Videos

TL;DR

This paper develops a pipeline for bonobo detection and classification from weakly labelled videos, utilizing semi-automatic dataset creation, handcrafted features, and deep learning, achieving up to 75% accuracy.

Contribution

It introduces a new semi-automatically generated bonobo dataset and evaluates various classification methods, highlighting the importance of proper data separation.

Findings

ResNet-based classifier achieves 75% accuracy.

Proper data separation significantly impacts classification performance.

Deep learning outperforms handcrafted features in bonobo identification.

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.