← Papers

Unverified paper record

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

Sensors (Basel, Switzerland) · 12 Dec 2023 · 10.3390/s23249788

Abstract

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.

Plant phenotyping relevance

RGB-D画像センサーとセグメンテーションにより作物の草丈を自動推定し、観測値と相関検証しており、植物表現型取得手法が中心的である。

abstractThis 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
abstractImages collected from weekly scans were processed by segmentation to estimate the plant heights of three crops species.
abstractthe correlation between the estimated and observed growth characteristics was acceptable.

Code and data availability

The paper's plant-phenotyping measurements (RGB-D scans, depth maps, field plant heights, sensor temperature/moisture data) are not publicly deposited; the Data Availability Statement requires contacting the authors. No author analysis code or public repository is provided; cited URLs are generic vendor documentation,

No evidence-backed public reproduction asset is currently recorded.

This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.