AI on the Bog: Monitoring and Evaluating Cranberry Crop Risk

Pipeline overview. Cloud image sequence, humidity, and wind speed are used to predict future berry temperature over a time horizon to determine high risk time periods. Aerial imagery of cranberry crops are used to obtain count density maps to determine high risk regions. Exposure metrics (number of exposed cranberries with high berry internal temperature) are made available to the farmer in order to make resource decision such as crop irrigation. Red dashed boxes indicate high risk regions. Best viewed in color and zoomed.

Training of baseline method for joint semantic segmentation and optical flow regression with additional self-supervision.

Triple-S Network architecture used in this application. Aerial image is input to a U-Net style network with output guided bysegmentation loss, L_seg, split loss, L_split, and count loss, L_count. W_select is the selective watershed algorithm introduced in [1], and CC is the connected components algorithm.

Cloud future segmentation results.

Abstract

Machine vision for precision agriculture has attracted considerable research interest in recent years. The goal of this paper is to develop an end-end cranberry health monitoring system to enable and support real time cranberry over-heating assessment to facilitate informed decisions that may sustain the economic viability of the farm. Toward this goal, we propose two main deep learning-based modules for: 1) cranberry fruit segmentation to delineate the exact fruit regions in the cranberry field image that are exposed to sun, 2) prediction of cloud coverage conditions to estimate the inner temperature of exposed cranberries. We develop drone-based field data and ground-based sky data collection systems to collect video imagery at multiple time points for use in crop health analysis. Extensive evaluation on the data set shows that it is possible to predict exposed fruit’s inner temperature with high accuracy (0.02% MAPE) when irradiance is predicted with 8.41-20.36% MAPE in the 5-20 minutes time horizon. With 62.54% mIoU for segmentation and 13.46 MAE for counting accuracies in exposed fruit identification, this system is capable of giving informed feedback to growers to take precautionary action (\eg, irrigation) in identified crop field regions with higher risk of sunburn in the near future. Though this novel system is applied for cranberry health monitoring, it represents a pioneering step forward in efficiency for farming and is useful in precision agriculture beyond the problem of cranberry overheating.

Video