Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and Counting
Insects play essential roles in ecosystems, providing services such as pollination and pest regulation. However, global insect populations are in decline due to factors like habitat loss and climate change, raising concerns about ecosystem stability. Traditional insect monitoring methods are limited...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/1/10 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588327248723968 |
|---|---|
| author | Ioannis Saradopoulos Ilyas Potamitis Iraklis Rigakis Antonios Konstantaras Ioannis S. Barbounakis |
| author_facet | Ioannis Saradopoulos Ilyas Potamitis Iraklis Rigakis Antonios Konstantaras Ioannis S. Barbounakis |
| author_sort | Ioannis Saradopoulos |
| collection | DOAJ |
| description | Insects play essential roles in ecosystems, providing services such as pollination and pest regulation. However, global insect populations are in decline due to factors like habitat loss and climate change, raising concerns about ecosystem stability. Traditional insect monitoring methods are limited in scope, but advancements in AI and machine learning enable automated, non-invasive monitoring with camera traps. In this study, we leverage the new Diopsis dataset that contains images from field operations to explore an approach that emphasizes both background extraction from images and the SAHI approach. By creating augmented backgrounds from extracting insects from training images and using these backgrounds as canvases to artificially relocate insects, we can improve detection accuracy, reaching mAP50 72.7% with YOLO10nano, and reduce variability when counting insects on different backgrounds and image sizes, supporting efficient insect monitoring on low-power devices such as Raspberry Pi Zero W 2. |
| format | Article |
| id | doaj-art-1866ac0b8ac447a1b746c5156d0bafbe |
| institution | Kabale University |
| issn | 2078-2489 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-1866ac0b8ac447a1b746c5156d0bafbe2025-01-24T13:35:07ZengMDPI AGInformation2078-24892024-12-011611010.3390/info16010010Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and CountingIoannis Saradopoulos0Ilyas Potamitis1Iraklis Rigakis2Antonios Konstantaras3Ioannis S. Barbounakis4Department of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, GreeceDepartment of Music Technology & Acoustics, Hellenic Mediterranean University, 74100 Chania, GreeceDepartment of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, GreeceDepartment of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, GreeceDepartment of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, GreeceInsects play essential roles in ecosystems, providing services such as pollination and pest regulation. However, global insect populations are in decline due to factors like habitat loss and climate change, raising concerns about ecosystem stability. Traditional insect monitoring methods are limited in scope, but advancements in AI and machine learning enable automated, non-invasive monitoring with camera traps. In this study, we leverage the new Diopsis dataset that contains images from field operations to explore an approach that emphasizes both background extraction from images and the SAHI approach. By creating augmented backgrounds from extracting insects from training images and using these backgrounds as canvases to artificially relocate insects, we can improve detection accuracy, reaching mAP50 72.7% with YOLO10nano, and reduce variability when counting insects on different backgrounds and image sizes, supporting efficient insect monitoring on low-power devices such as Raspberry Pi Zero W 2.https://www.mdpi.com/2078-2489/16/1/10automated insect trapsembedded systemsinsect counting |
| spellingShingle | Ioannis Saradopoulos Ilyas Potamitis Iraklis Rigakis Antonios Konstantaras Ioannis S. Barbounakis Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and Counting Information automated insect traps embedded systems insect counting |
| title | Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and Counting |
| title_full | Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and Counting |
| title_fullStr | Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and Counting |
| title_full_unstemmed | Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and Counting |
| title_short | Image Augmentation Using Both Background Extraction and the SAHI Approach in the Context of Vision-Based Insect Localization and Counting |
| title_sort | image augmentation using both background extraction and the sahi approach in the context of vision based insect localization and counting |
| topic | automated insect traps embedded systems insect counting |
| url | https://www.mdpi.com/2078-2489/16/1/10 |
| work_keys_str_mv | AT ioannissaradopoulos imageaugmentationusingbothbackgroundextractionandthesahiapproachinthecontextofvisionbasedinsectlocalizationandcounting AT ilyaspotamitis imageaugmentationusingbothbackgroundextractionandthesahiapproachinthecontextofvisionbasedinsectlocalizationandcounting AT iraklisrigakis imageaugmentationusingbothbackgroundextractionandthesahiapproachinthecontextofvisionbasedinsectlocalizationandcounting AT antonioskonstantaras imageaugmentationusingbothbackgroundextractionandthesahiapproachinthecontextofvisionbasedinsectlocalizationandcounting AT ioannissbarbounakis imageaugmentationusingbothbackgroundextractionandthesahiapproachinthecontextofvisionbasedinsectlocalizationandcounting |