Yield Evaluation of Brassica rapa, Lactuca sativa, and Brassica integrifolia Using Image Processing in an IoT-Based Aquaponics with Temperature-Controlled Greenhouse

Abstract

The paper introduced the development of a self-sustainable smart aquaponics system in a temperature-controlled greenhouse with a monitoring and automatic correction system using an Android device through the Internet of Things (IoT) and plant growth monitoring system through image processing using Raspberry Pi. The system involves the acquiring of real-time data detected by the light intensity sensor, and air temperature and humidity sensor. It also includes the monitoring of the pH level and temperature of the recirculating water of the system. If the acquired data is not within the threshold range, the correcting devices, namely grow lights, exhaust and inlet fans, evaporative cooler, aerator, and peristaltic buffer device were automatically triggered by the system to correct and achieve its normal status. The internet remote access includes the effective wireless transmission and reception of data reports between the system and an Android unit with the Android application in real-time. The study focused on the evaluation of two experimental setups comparing the plant growth between conventional soil-based farming and the smart aquaponics system using image processing. After data gathering, results showed that the smart aquaponics setup successfully produced a yield better than the conventional farming setup .

A Survey of Modern Greenhouse Technologies and Practices for Commercial Cannabis Cultivation

“…However, there is a lack of AI applications specifically targeting C. sativa cultivation. The majority of the studies employ AI for leaf disease detection, leaf area size, and optimal harvesting time [102], [103], [105], [106], [107], while only a few focus on optimising the environment and crop management [99], [100], [103], [107].Additionally, the review of greenhouse AIoT technologies discovered various innovative applications. For instanceRatnayake et al explored AI-based computer vision to improve pollinator monitoring, enabling markerless data capture for insect counting, motion tracking, behaviour analysis, and pollination prediction across large agricultural areas using edge computing and offline automated multi-species counting, tracking and behavioural analysis [109].…”

“…These variations make it challenging to create robust models applicable across various plant species and growth environments. One example, found in multiple papers within and outside this review, is the complexity of leaf segmentation in non-optimal or untrained lighting conditions [98], [102], [103], [104], [105]. These methods necessitate consistent image quality, free from low lighting or over-saturation of a single colour, as seen with LED artificial lighting favouring blue or red spectrums.…”

Cloud Data Transfer and Harmful Activity Detection using

“…Large numbers of customers that use CC are drawn to cloud service providers (CSPs) because of the unique services, flexible usage, and cost reductions that they give [4]. On the other hand, cloud data migration might be challenging due to operational and security concerns [5].…”