Quantifying Bilberry Counts and Densities: A Comparative Assessment of Segmentation and Object Detection Models from Drone and Camera Imagery
Open Access
Abstract
Nordic forest management is increasingly emphasizing multi-functional goals, expanding beyond timber production towards non-wood forest products such as wild berries. Wild berry yield maps are based on sample plot data combined with meteorological, remote sensing, and geoinformation data. Automating sample plot data processing is crucial, as manual collection is labor-intensive, time-consuming, and complicated by short berry seasons and fluctuating yields. This study compares two methods for automatic bilberry detection and counting: a deep learning detector YOLO and a machine learning model using the segment anything model (SAM) followed by a random forest classification (SAM-RF). Both system camera and drone imagery were evaluated as input data. YOLOv8 clearly outperformed SAM–RF in berry detection, achieving an of 0.98 and an RMSE of 3.8 berries when evaluated against annotated system camera images, compared to an of 0.80 for SAM–RF. System camera imagery consistently produced higher accuracy than drone imagery due to higher image clarity and more optimal viewing angles, with YOLOv8 achieving an of 0.95 against field counts, compared to 0.81 for drone images. The results also indicate that the primary error source in berry counting arises from the fact that many berries are not visible in the captured images. The results from the data analysis support the use of the developed technologies in yield modeling and even in implementing future ‘follow-me’ drone berry assistants.
Keywords
Funding Information
- European Commission (10107044)
- Research Council of Finland (359175)
- Research Council of Finland (359203)
This publication has 34 references indexed in Scilit:
- A lightweight deep learning framework for wild berry detection in complex natural environmentsEngineering Applications of Artificial Intelligence, 2025
- Performance analysis of modified DeepLabv3+ architecture for fruit detection and localization in apple orchardsSmart Agricultural Technology, 2024
- A novel approach to authentication of highbush and lowbush blueberry cultivars using image analysis, traditional machine learning and deep learning algorithmsEuropean Food Research and Technology, 2024
- A fast and efficient approach to estimate wild blueberry yield using machine learning with drone photography: Flight altitude, sampling method and model effectsComputers and Electronics in Agriculture, 2023
- Object detection using YOLO: challenges, architectural successors, datasets and applicationsMultimedia Tools and Applications, 2022
- Predicting bilberry and cowberry yields using airborne laser scanning and other auxiliary data combined with National Forest Inventory field plot dataForest Ecology and Management, 2021
- Random forest in remote sensing: A review of applications and future directionsISPRS Journal of Photogrammetry and Remote Sensing, 2016
- Evaluation of bilberry and cowberry yield models by comparing model predictions with field measurements from North Karelia, FinlandForest Ecology and Management, 2016
- Crowdsourcing geospatial dataISPRS Journal of Photogrammetry and Remote Sensing, 2010
- Random ForestsMachine Learning, 2001