Dierckx, Lucile
[UCL]
Beauvois, Mélanie
[UCL]
Nijssen, Siegfried
[UCL]
As bats are an important indicator for the health of their habitat, projects in multiple countries monitor bat populations by collecting audio recordings of bat calls. Analysing these recordings is however a tedious task and there is a need for systems that accurately and efficiently detect and classify bat calls. While earlier studies focused on detection and classification separately, in this paper we propose a first approach that combines these two tasks. Moreover, we aim to build a multi-label classifier that is able to detect if multiple bat species are present in the same audio recording. One of the challenges we face is that the available data focuses either on detection or single-label classification, but not on the combined task of detection and multi-label classification. We propose to address this by a data augmentation approach, and demonstrate that the resulting approach achieves the objectives of being accurate and efficient.
Bibliographic reference |
Dierckx, Lucile ; Beauvois, Mélanie ; Nijssen, Siegfried. Detection and Multi-label Classification of Bats.Symposium on Intelligent Data Analysis (Rennes, France, du 20/04/2022 au 22/04/2022). In: Advances in Intelligent Data Analysis, Vol. 20 (2022) |
Permanent URL |
http://hdl.handle.net/2078.1/264299 |