Object Detection of Small Insects in Time-Lapse Camera Recordings
As pollinators, insects play a crucial role in ecosystem management and world food production. However, insect populations are declining, necessitating efficient insect monitoring methods. Existing methods analyze video or time-lapse images of insects in nature, but analysis is challenging as insect...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/16/7242 |
| _version_ | 1797583211580096512 |
|---|---|
| author | Kim Bjerge Carsten Eie Frigaard Henrik Karstoft |
| author_facet | Kim Bjerge Carsten Eie Frigaard Henrik Karstoft |
| author_sort | Kim Bjerge |
| collection | DOAJ |
| description | As pollinators, insects play a crucial role in ecosystem management and world food production. However, insect populations are declining, necessitating efficient insect monitoring methods. Existing methods analyze video or time-lapse images of insects in nature, but analysis is challenging as insects are small objects in complex and dynamic natural vegetation scenes. In this work, we provide a dataset of primarily honeybees visiting three different plant species during two months of the summer. The dataset consists of 107,387 annotated time-lapse images from multiple cameras, including 9423 annotated insects. We present a method for detecting insects in time-lapse RGB images, which consists of a two-step process. Firstly, the time-lapse RGB images are preprocessed to enhance insects in the images. This motion-informed enhancement technique uses motion and colors to enhance insects in images. Secondly, the enhanced images are subsequently fed into a convolutional neural network (CNN) object detector. The method improves on the deep learning object detectors You Only Look Once (YOLO) and faster region-based CNN (Faster R-CNN). Using motion-informed enhancement, the YOLO detector improves the average micro <i>F</i>1-score from 0.49 to 0.71, and the Faster R-CNN detector improves the average micro <i>F</i>1-score from 0.32 to 0.56. Our dataset and proposed method provide a step forward for automating the time-lapse camera monitoring of flying insects. |
| first_indexed | 2024-03-10T23:35:39Z |
| format | Article |
| id | doaj.art-7072e225cad843559e2d492a20a9e1e5 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:35:39Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7072e225cad843559e2d492a20a9e1e52023-11-19T02:58:48ZengMDPI AGSensors1424-82202023-08-012316724210.3390/s23167242Object Detection of Small Insects in Time-Lapse Camera RecordingsKim Bjerge0Carsten Eie Frigaard1Henrik Karstoft2Department of Electrical and Computer Engineering, Aarhus University, 8200 Aarhus N, DenmarkDepartment of Electrical and Computer Engineering, Aarhus University, 8200 Aarhus N, DenmarkDepartment of Electrical and Computer Engineering, Aarhus University, 8200 Aarhus N, DenmarkAs pollinators, insects play a crucial role in ecosystem management and world food production. However, insect populations are declining, necessitating efficient insect monitoring methods. Existing methods analyze video or time-lapse images of insects in nature, but analysis is challenging as insects are small objects in complex and dynamic natural vegetation scenes. In this work, we provide a dataset of primarily honeybees visiting three different plant species during two months of the summer. The dataset consists of 107,387 annotated time-lapse images from multiple cameras, including 9423 annotated insects. We present a method for detecting insects in time-lapse RGB images, which consists of a two-step process. Firstly, the time-lapse RGB images are preprocessed to enhance insects in the images. This motion-informed enhancement technique uses motion and colors to enhance insects in images. Secondly, the enhanced images are subsequently fed into a convolutional neural network (CNN) object detector. The method improves on the deep learning object detectors You Only Look Once (YOLO) and faster region-based CNN (Faster R-CNN). Using motion-informed enhancement, the YOLO detector improves the average micro <i>F</i>1-score from 0.49 to 0.71, and the Faster R-CNN detector improves the average micro <i>F</i>1-score from 0.32 to 0.56. Our dataset and proposed method provide a step forward for automating the time-lapse camera monitoring of flying insects.https://www.mdpi.com/1424-8220/23/16/7242camera recordingdeep learninginsect datasetmotion enhancementobject detection |
| spellingShingle | Kim Bjerge Carsten Eie Frigaard Henrik Karstoft Object Detection of Small Insects in Time-Lapse Camera Recordings Sensors camera recording deep learning insect dataset motion enhancement object detection |
| title | Object Detection of Small Insects in Time-Lapse Camera Recordings |
| title_full | Object Detection of Small Insects in Time-Lapse Camera Recordings |
| title_fullStr | Object Detection of Small Insects in Time-Lapse Camera Recordings |
| title_full_unstemmed | Object Detection of Small Insects in Time-Lapse Camera Recordings |
| title_short | Object Detection of Small Insects in Time-Lapse Camera Recordings |
| title_sort | object detection of small insects in time lapse camera recordings |
| topic | camera recording deep learning insect dataset motion enhancement object detection |
| url | https://www.mdpi.com/1424-8220/23/16/7242 |
| work_keys_str_mv | AT kimbjerge objectdetectionofsmallinsectsintimelapsecamerarecordings AT carsteneiefrigaard objectdetectionofsmallinsectsintimelapsecamerarecordings AT henrikkarstoft objectdetectionofsmallinsectsintimelapsecamerarecordings |