Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multisensor Data Fusion for Automatized Insect Monitoring (KInsecta)

Martin Tschaikner, Danja Brandt, Henning Schmidt, Felix Bießmann, Teodor Chiaburu, Ilona Schrimpf, Thomas Schrimpf, Alexandra Stadel, Frank Haußer, Ingeborg Beckers

TL;DR

The paper tackles the need for non-lethal, scalable insect monitoring amid global declines by proposing a low-cost, multisensor platform that fuses camera imagery, optoacoustic wingbeat sensing, and environmental measurements, managed on a Raspberry Pi with a web-based data app. It demonstrates a hierarchical GBIF-taxon classification approach and a data-fusion framework to improve predictive power from heterogeneous signals. In a proof-of-concept with a small, highly unbalanced dataset of 7 species, camera-based classification achieved about 0.92 accuracy, while wingbeat-only performance lagged due to data limitations, underscoring the potential of multisensor fusion pending larger datasets. The system supports biodiversity and agricultural studies and enables citizen-science integration for live, reproducible insect monitoring.

Abstract

Insect populations are declining globally, making systematic monitoring essential for conservation. Most classical methods involve death traps and counter insect conservation. This paper presents a multisensor approach that uses AI-based data fusion for insect classification. The system is designed as low-cost setup and consists of a camera module and an optical wing beat sensor as well as environmental sensors to measure temperature, irradiance or daytime as prior information. The system has been tested in the laboratory and in the field. First tests on a small very unbalanced data set with 7 species show promising results for species classification. The multisensor system will support biodiversity and agriculture studies.

Multisensor Data Fusion for Automatized Insect Monitoring (KInsecta)

TL;DR

The paper tackles the need for non-lethal, scalable insect monitoring amid global declines by proposing a low-cost, multisensor platform that fuses camera imagery, optoacoustic wingbeat sensing, and environmental measurements, managed on a Raspberry Pi with a web-based data app. It demonstrates a hierarchical GBIF-taxon classification approach and a data-fusion framework to improve predictive power from heterogeneous signals. In a proof-of-concept with a small, highly unbalanced dataset of 7 species, camera-based classification achieved about 0.92 accuracy, while wingbeat-only performance lagged due to data limitations, underscoring the potential of multisensor fusion pending larger datasets. The system supports biodiversity and agricultural studies and enables citizen-science integration for live, reproducible insect monitoring.

Abstract

Insect populations are declining globally, making systematic monitoring essential for conservation. Most classical methods involve death traps and counter insect conservation. This paper presents a multisensor approach that uses AI-based data fusion for insect classification. The system is designed as low-cost setup and consists of a camera module and an optical wing beat sensor as well as environmental sensors to measure temperature, irradiance or daytime as prior information. The system has been tested in the laboratory and in the field. First tests on a small very unbalanced data set with 7 species show promising results for species classification. The multisensor system will support biodiversity and agriculture studies.
Paper Structure (7 sections, 6 figures, 1 table)

This paper contains 7 sections, 6 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. Multisensor System
  3. Camera System
  4. Wingbeat Sensor
  5. Data fusion, ML-Methods and results
  6. Data set
  7. ML-Methods

Figures (6)

  • Figure 1: Principle of Multisensorsystem including the path of an insects exemplarily
  • Figure 2: Image taken by the camera system: An insect, species Eristalis tenax, is passing the arena.
  • Figure 3: Wingbeat sensor including Emitter, Receiver and Fresnel Lenses
  • Figure 4: Examples of wingbeat signals of two different insect species: (left) Eristalis tenax, (right) Drosophila drosophila.
  • Figure 5: A highly unbalanced data set of 7 insect species has been obtained from measurements with the multi sensor system. The presented images have been cropped for better visualisation. Note, that some insects are located at the border of the arena. Also only fast flattering wings show some blurring, but still the image quality is very good.
  • ...and 1 more figures