Dual-view weakly-supervised learning for apple tree flower counting.

Abstract

This paper presents a method to estimate apple tree flower cluster count using image analysis techniques. The main research question is how accurately flower clusters on apple trees can be counted using a camera-based approach and weakly-supervised learning, compared to traditional visual estimation. A camera is used to capture images of blooming apple trees from two sides. These images are processed by a weakly-supervised model based on a ResNet feature extractor and a feature pyramid network serving as the feature aggregator. The model is trained and validated using reference data obtained through manual flower cluster counts in the orchard and from estimations based on camera images. The model was trained using field-validated data and visually-estimated data, enabling a comparative evaluation. The proposed model surpassed conventional image segmentation methods in estimating both manually counted and visually estimated flower clusters. The proposed method achieves a relative error of 10.26% in estimating flower cluster quantities, demonstrating its effectiveness and improved accuracy over traditional approaches. Its reliance on field-validated reference data adds to its robustness and practical relevance.

Plant phenotyping relevance

リンゴ樹の花房数という植物形質を、カメラ画像と弱教師あり学習で推定する手法の開発・検証が研究の中心であるため。

Code and data availability

The supplied blocks describe a unique apple flower cluster image dataset (73 trees, 117 image pairs) and a weakly-supervised regression model, but contain no public deposit, availability URL, or code release for the dataset, annotations, or authors' code. The only public URL present (github.com/ultralytics/ultralytics)

No evidence-backed public reproduction asset is currently recorded.