Segmentation and Identification of Mediterranean Plant Species

Kaur, Parminder; Gigante, Daniela; Caccianiga, Marco; Bagella, Simonetta; Angiolini, Claudia; Garabini, Manolo; Angelini, Franco; Remagnino, Paolo

Abstract

Recently, object recognition and image segmentation have gained much attention in the computer vision field and image processing for effective object localisation and identification. Researchers have applied semantic segmentation and instance segmentation in diverse application areas. However, the least research has been performed in natural habitat monitoring or plant species identification in natural environments/surroundings. For this study, we composed a real image dataset from four habitats: forests, dunes, grasslands, and screes from various locations in Italy. Habitat expert botanists annotated the data using bounding box annotations which have been further utilised to generate the plant species masks using the recently proposed Segment Anything Model (SAM) for segmentation, localisation, and identification tasks. Extensive experimentation has been performed on habitat data with bounding boxes and masks using YOLOv8 detection and segmentation models. Comparative analysis of models, model training with different train data percentages, and the importance of masks over bounding boxes have been studied and discussed.

Citation

Kaur, P., Gigante, D., Caccianiga, M., Bagella, S., Angiolini, C., Garabini, M., Angelini, F., & Remagnino, P. (2023, October). Segmentation and Identification of Mediterranean Plant Species. Presented at ISVC 2023: 18th International Symposium on Visual Computing, Lake Tahoe, NV

• Presentation Conference Type: Conference Paper (published)
• Conference Name: ISVC 2023: 18th International Symposium on Visual Computing
• Start Date: Oct 16, 2023
• End Date: Oct 18, 2023
• Acceptance Date: Aug 28, 2023
• Online Publication Date: Dec 3, 2023
• Publication Date: 2023
• Deposit Date: Oct 24, 2023
• Publicly Available Date: Dec 4, 2024
• Print ISSN: 0302-9743
• Publisher: Springer
• Volume: 14362
• Pages: 431-442
• Series Title: Lecture Notes in Computer Science
• Series ISSN: 0302-9743
• Book Title: Advances in Visual Computing 18th International Symposium, ISVC 2023, Lake Tahoe, NV, USA, October 16–18, 2023, Proceedings, Part II
• ISBN: 9783031479656
• DOI: https://doi.org/10.1007/978-3-031-47966-3_34
• Public URL: https://durham-repository.worktribe.com/output/1815672