Modeling Time-Lapse Trajectories to Characterize Cranberry Growth

2025-10-09

AI Summary

Cranberry growth monitoring has traditionally relied on labor-intensive manual assessment, resulting in low efficiency and high operational costs. To address this, we propose a self-supervised fine-tuning framework for Vision Transformers (ViTs) that models crop phenological evolution over time without requiring dense pixel-level annotations. Our method introduces two novel pretraining objectives—temporal regression and cultivar classification—jointly optimized to learn interpretable, two-dimensional growth trajectory representations. We construct and publicly release the first cranberry temporal dataset, comprising 52 field observations across eight cultivars, with synchronized agronomic activity annotations. Experiments demonstrate accurate growth-stage prediction and robust discrimination of inter-cultivar developmental timing differences. Furthermore, ablation studies suggest promising cross-crop generalization capability. This work establishes a new paradigm for intelligent, scalable phenological monitoring in precision agriculture.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Unsupervised & Self-Supervised Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Change monitoring is an essential task for cranberry farming as it provides both breeders and growers with the ability to analyze growth, predict yield, and make treatment decisions. However, this task is often done manually, requiring significant time on the part of a cranberry grower or breeder. Deep learning based change monitoring holds promise, despite the caveat of hard-to-interpret high dimensional features and hand-annotations for fine-tuning. To address this gap, we introduce a method for modeling crop growth based on fine-tuning vision transformers (ViTs) using a self-supervised approach that avoids tedious image annotations. We use a two-fold pretext task (time regression and class prediction) to learn a latent space for the time-lapse evolution of plant and fruit appearance. The resulting 2D temporal tracks provide an interpretable time-series model of crop growth that can be used to: 1) predict growth over time and 2) distinguish temporal differences of cranberry varieties. We also provide a novel time-lapse dataset of cranberry fruit featuring eight distinct varieties, observed 52 times over the growing season (span of around four months), annotated with information about fungicide application, yield, and rot. Our approach is general and can be applied to other crops and applications (code and dataset can be found at https://github. com/ronan-39/tlt/).

Problem

• Automating manual cranberry growth monitoring using deep learning
• Eliminating need for hand-annotations in crop change monitoring
• Modeling interpretable time-series of cranberry growth and variety differences

Innovation

• Fine-tuning vision transformers with self-supervised learning
• Using time regression and class prediction pretext tasks
• Creating interpretable 2D temporal tracks for crop growth