Key technologies of machine vision for weeding robots: A review and benchmark

Computers and Electronics in Agriculture, Journal Year: 2022, Volume and Issue: 196, P. 106880 - 106880

Published: April 5, 2022

Language: Английский

---

Herbicide Resistance: Managing Weeds in a Changing World

Agronomy, Journal Year: 2023, Volume and Issue: 13(6), P. 1595 - 1595

Published: June 13, 2023

Over the years, several agricultural interventions and technologies have contributed immensely towards intensifying food production globally. The introduction of herbicides provided a revolutionary tool for managing difficult task weed control contributing significantly global security human survival. However, in recent times, successes achieved with chemical taken turn, threatening very existence we tried to protect. side effects conventional farming, particularly increasing cases herbicide resistance weeds, is quite alarming. Global calls sustainable management approaches be used mounting. This paper provides detailed information on molecular biological background resistant biotypes highlights alternative, non-chemical methods which can prevent development spreading herbicide-resistant weeds.

Language: Английский

---

Boosting precision crop protection towards agriculture 5.0 via machine learning and emerging technologies: A contextual review

Frontiers in Plant Science, Journal Year: 2023, Volume and Issue: 14

Published: March 22, 2023

Crop protection is a key activity for the sustainability and feasibility of agriculture in current context climate change, which causing destabilization agricultural practices an increase incidence or invasive pests, growing world population that requires guaranteeing food supply chain ensuring security. In view these events, this article provides contextual review six sections on role artificial intelligence (AI), machine learning (ML) other emerging technologies to solve future challenges crop protection. Over time, has progressed from primitive 1.0 (Ag1.0) through various technological developments reach level maturity closelyin line with Ag5.0 (section 1), characterized by successfully leveraging ML capacity modern devices machines perceive, analyze actuate following main stages precision 2). Section 3 presents taxonomy algorithms support development implementation protection, while section 4 analyses scientific impact basis extensive bibliometric study >120 algorithms, outlining most widely used deep (DL) techniques currently applied relevant case studies detection control diseases, weeds plagues. 5 describes 39 fields smart sensors advanced hardware devices, telecommunications, proximal remote sensing, AI-based robotics will foreseeably lead next generation perception-based, decision-making actuation systems digitized, real-time realistic Ag5.0. Finally, 6 highlights conclusions final remarks.

Language: Английский

---

The q-rung fuzzy LOPCOW-VIKOR model to assess the role of unmanned aerial vehicles for precision agriculture realization in the Agri-Food 4.0 era

Artificial Intelligence Review, Journal Year: 2023, Volume and Issue: 56(11), P. 13373 - 13406

Published: April 11, 2023

Language: Английский

---

Transforming weed management in sustainable agriculture with artificial intelligence: A systematic literature review towards weed identification and deep learning

Crop Protection, Journal Year: 2023, Volume and Issue: 176, P. 106522 - 106522

Published: Nov. 14, 2023

In the face of increasing agricultural demands and environmental concerns, effective management weeds presents a pressing challenge in modern agriculture. Weeds not only compete with crops for resources but also pose threats to food safety sustainability through indiscriminate use herbicides, which can lead contamination herbicide-resistant weed populations. Artificial Intelligence (AI) has ushered paradigm shift agriculture, particularly domain management. AI's utilization this extends beyond mere innovation, offering precise eco-friendly solutions identification control weeds, thereby addressing critical challenges. This article aims examine application AI context detection impact deep learning techniques sector. Through an assessment research articles, study identifies factors influencing adoption implementation These criteria encompass (food safety, increased effectiveness, eco-friendliness herbicides reduction), (capture technology, training datasets, models, outcomes accuracy), ancillary technologies (IoT, UAV, field robots, herbicides), related methods (economic, social, technological, environmental). Of 5821 documents found, 99 full-text articles were assessed, 68 included study. The review highlights role enhancing by reducing herbicide residues, effectiveness strategies, promoting judicious use. It underscores importance capture accuracy metrics implementation, emphasizing their synergy revolutionizing practices. Ancillary technologies, such as IoT, UAVs, AI-enhanced complement capabilities, holistic data-driven approaches control. Additionally, influences economic, dimensions Last least, digital literacy emerges crucial enabler, empowering stakeholders navigate effectively contribute sustainable transformation practices

Language: Английский

---

A comprehensive review on smart and sustainable agriculture using IoT technologies

Smart Agricultural Technology, Journal Year: 2024, Volume and Issue: 8, P. 100487 - 100487

Published: June 11, 2024

The article provides a comprehensive review of the use Internet Things (IoT) in agriculture, along with its advantages and disadvantages. However, it's important to recognize that IoT holds immense potential for generating new ideas could drive innovations modern agriculture address several challenges faced by farmers today. Applications such as smart irrigation, precision farming, crop soil tracking, greenhouses, supply chain management, livestock monitoring, agricultural drones, pest disease prevention, farm machinery are among areas considered implementation this paper. These innovative solutions have revolutionize farming practices, improve efficiency, reduce resource wastage, ultimately enhance productivity sustainability. analysis examines each application terms utility outlines measures necessary effectiveness. Key considerations include addressing connectivity issues, managing costs, ensuring data security privacy, scaling appropriately, effectively data, promoting awareness adoption tools. Despite these challenges, offers numerous benefits sector. paper underscores importance collaboration farmers, technology companies, academia, policymakers issues fully harness IoT. To achieve goal, ongoing research, development, acceptance IoT-driven essential sustain viable option amidst emerging climate change scarcity.

Language: Английский

---

Integration of Technology in Agricultural Practices towards Agricultural Sustainability: A Case Study of Greece

Sustainability, Journal Year: 2024, Volume and Issue: 16(7), P. 2664 - 2664

Published: March 24, 2024

Agricultural technology integration has become a key strategy for attaining agricultural sustainability. This study examined the of in practices towards sustainability, using Greece as case study. Data were collected questionnaire from 240 farmers and agriculturalists Greece. The results showed significant positive effect on with p-values indicating strong statistical relevance (types used: p = 0.003; factors influencing adoption: 0.001; benefits integration: 0.021). These highlight effects that cutting-edge like artificial intelligence, Internet Things (IoT), precision agriculture have improving resource efficiency, lowering environmental effects, raising yields. Our findings cast doubt conventional dependence intensive, resource-depleting farming techniques point to move toward more technologically advanced, sustainable approaches. research advances conversation by showcasing how well may improve sustainability Greek agriculture. emphasizes significance infrastructure investment, supporting legislation, farmer education order facilitate adoption technology.

Language: Английский

---

Detection of Invasive Species (Siam Weed) Using Drone-Based Imaging and YOLO Deep Learning Model

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(1), P. 120 - 120

Published: Jan. 2, 2025

This study explores the efficacy of drone-acquired RGB images and YOLO model in detecting invasive species Siam weed (Chromolaena odorata) natural environments. is a perennial scrambling shrub from tropical sub-tropical America that outside its native range, causing substantial environmental economic impacts across Asia, Africa, Oceania. First detected Australia northern Queensland 1994 later Northern Territory 2019, there an urgent need to determine extent incursion vast, rugged areas both jurisdictions for distribution mapping at catchment scale. tests drone-based imaging train deep learning contributes goal surveying non-native vegetation We specifically examined effects input training images, solar illumination, complexity on model’s detection performance investigated sources false positives. Drone-based were acquired four sites Townsville region test (YOLOv5). Validation was performed through expert visual interpretation results image tiles. The YOLOv5 demonstrated over 0.85 F1-Score, which improved 0.95 with exposure images. A reliable found be sufficiently trained approximately 1000 tiles, additional offering marginal improvement. Increased did not notably enhance performance, indicating smaller adequate. False positives often originated foliage bark under high low reduced these errors considerably. demonstrates feasibility using models detect landscapes, providing safe alternative current method involving human spotters helicopters. Future research will focus developing tools merge duplicates, gather georeference data, report detections large datasets more efficiently, valuable insights practical applications management

Language: Английский

---

How many gigabytes per hectare are available in the digital agriculture era? A digitization footprint estimation

Computers and Electronics in Agriculture, Journal Year: 2022, Volume and Issue: 198, P. 107080 - 107080

Published: May 28, 2022

Language: Английский

---

Effect of varying training epochs of a Faster Region-Based Convolutional Neural Network on the Accuracy of an Automatic Weed Classification Scheme

Smart Agricultural Technology, Journal Year: 2022, Volume and Issue: 3, P. 100128 - 100128

Published: Oct. 14, 2022

Site-specific weed detection and management is a crucial approach for crop production herbicide contamination mitigation in precision agriculture. With the advent of unmanned aerial vehicles (UAVs) advances deep learning techniques, it has become possible to identify classify weeds from crops at desired spatial temporal resolution. In this research, faster region based convolutional neural network was implemented automatic identification classification using mixed farmland as case study. A DJI phantom 4 UAV used simultaneously collect about 254 image pairs study site. The images were annotated before transferring them into google colaboratory where they trained over five epochs; 10,000, 20,000, 100,000, 200,000, 242,000 with aim detecting point when model flattens out process automatically identifying classifying weeds. identified classified classes which are; sugarcane, spinach, banana, pepper, Finally, accuracy evaluated aid recorded loss function confusion matrix, result shows that gave 52.5%, 50%, recall 7.7% F1 score 71.6% 10,000 epochs, 67.8%, 67%, 52.4% 85.9% 20,000 97.2%, 96.2%, 97.5% 99% 100,000 98.3%, 98.1%, 99.1% 99.4% 200,000 97%, 95%, epochs. It observed model's performance improves significantly increase number epochs but got saturated findings showed RCNN robust farm.

Language: Английский

---