Real-time applications in perennial trees and vegetables – A review
Real-time automation in agriculture shows great potential in perennial trees and vegetables allowing site-specific management by means of machine vision, and real-time processing. A lack of clarity still remains on the actual effectiveness, scalability, and limitations of such technologies in field...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525001510 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Real-time automation in agriculture shows great potential in perennial trees and vegetables allowing site-specific management by means of machine vision, and real-time processing. A lack of clarity still remains on the actual effectiveness, scalability, and limitations of such technologies in field conditions. This study critically examines the recent advancements in real-time applications in horticultural crops that are controlled using sensing systems for automating several cultivation tasks including (i) crop protection (ii) fertilization (iii) weeding (iv) harvesting and (v) crop load management. These tasks are individually evaluated, while identifying technological gaps and future research directions. Specifically, this study assesses real-time decision-making challenges and evaluates their impact in terms of processing time, resource efficiency, cost-effectiveness, and decision accuracy. The results revealed that real-time applications can increase precision and operational efficiency, while the need for improved communication and interoperability between the sensing systems and implements was highlighted. However, the effectiveness is often influenced by the sensor accuracy, the plant structure, and adaptability to crop systems. Further development of real-time applications in perennial trees and vegetables should be explored by producing artificial intelligence decision models based on plant information and multi-modal sensor systems. |
|---|---|
| ISSN: | 2772-3755 |