Lettuce Production in Intelligent Greenhouses-3D Imaging and Computer Vision for Plant Spacing Decisions

Development of a machine vision-based weight prediction system of butterhead lettuce (Lactuca sativa L.) using deep learning models for industrial plant factory

Introduction

Indoor agriculture, especially plant factories, becomes essential because of the advantages of cultivating crops yearly to address global food shortages. Plant factories have been growing in scale as commercialized. Developing an on-site system that estimates the fresh weight of crops non-destructively for decision-making on harvest time is necessary to maximize yield and profits. However, a multi-layer growing environment with on-site workers is too confined and crowded to develop a high-performance system.This research developed a machine vision-based fresh weight estimation system to monitor crops from the transplant stage to harvest with less physical labor in an on-site industrial plant factory.

Methods

A linear motion guide with a camera rail moving in both the x-axis and y-axis directions was produced and mounted on a cultivating rack with a height under 35 cm to get consistent images of crops from the top view. Raspberry Pi4 controlled its operation to capture images automatically every hour. The fresh weight was manually measured eleven times for four months to use as the ground-truth weight of the models. The attained images were preprocessed and used to develop weight prediction models based on manual and automatic feature extraction.

Results and discussion

The performance of models was compared, and the best performance among them was the automatic feature extraction-based model using convolutional neural networks (CNN; ResNet18). The CNN-based model on automatic feature extraction from images performed much better than any other manual feature extraction-based models with 0.95 of the coefficients of determination (R2) and 8.06 g of root mean square error (RMSE). However, another multiplayer perceptron model (MLP_2) was more appropriate to be adopted on-site since it showed around nine times faster inference time than CNN with a little less R2 (0.93). Through this study, field workers in a confined indoor farming environment can measure the fresh weight of crops non-destructively and easily. In addition, it would help to decide when to harvest on the spot.

Monitoring of a Productive Blue-Green Roof Using Low-Cost Sensors

Considering the rising concern over climate change and the need for local food security, productive blue-green roofs (PBGR) can be an effective solution to mitigate many relevant environmental issues. However, their cost of operation is high because they are intensive, and an economical operation and maintenance approach will render them as more viable alternative. Low-cost sensors with the Internet of Things can provide reliable solutions to the real-time management and distributed monitoring of such roofs through monitoring the plant as well soil conditions. This research assesses the extent to which a low-cost image sensor can be deployed to perform continuous, automated monitoring of a urban rooftop farm as a PBGR and evaluates the thermal performance of the roof for additional crops. An RGB-depth image sensor was used in this study to monitor crop growth. Images collected from weekly scans were processed by segmentation to estimate the plant heights of three crops species. The devised technique performed well for leafy and tall stem plants like okra, and the correlation between the estimated and observed growth characteristics was acceptable. For smaller plants, bright light and shadow considerably influenced the image quality, decreasing the precision. Six other crop species were monitored using a wireless sensor network to investigate how different crop varieties respond in terms of thermal performance. Celery, snow peas, and potato were measured with maximum daily cooling records, while beet and zucchini showed sound cooling effects in terms of mean daily cooling.