Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence

Partel, Victor; Kakarla, Sri Charan; Ampatzidis, Yiannis

doi:10.1016/j.compag.2018.12.048

Cited by 292 publications

(164 citation statements)

References 25 publications

Supporting

Mentioning

127

Contrasting

Unclassified

Order By: Relevance

“…Except the large spectrometers used in the laboratory, some portable sensing devices combined with traditional machine learning algorithms and Internet of things technology have been applied in fruit quality evaluation, egg freshness prediction (Coronel‐Reyes, Ramirez‐Morales, Fernandez‐Blanco, Rivero, & Pazos, ), and achieved acceptable results (Wang et al., ). Miniaturized hardware computing platforms are also beginning to be used, such as NVIDIA Jetson TX2 (Partel, Kakarla, & Ampatzidis, ), which is expected to be utilized to realize local accelerated computation without the help of the internet and cloud servers.…”

Section: Challenges and Future Perspective Of Deep Learning In Food Dmentioning

confidence: 99%

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

361

166

View full text Add to dashboard Cite

Deep learning has been proved to be an advanced technology for big data analysis with a large number of successful cases in image processing, speech recognition, object detection, and so on. Recently, it has also been introduced in food science and engineering. To our knowledge, this review is the first in the food domain. In this paper, we provided a brief introduction of deep learning and detailedly described the structure of some popular architectures of deep neural networks and the approaches for training a model. We surveyed dozens of articles that used deep learning as the data analysis tool to solve the problems and challenges in food domain, including food recognition, calories estimation, quality detection of fruits, vegetables, meat and aquatic products, food supply chain, and food contamination. The specific problems, the datasets, the preprocessing methods, the networks and frameworks used, the performance achieved, and the comparison with other popular solutions of each research were investigated. We also analyzed the potential of deep learning to be used as an advanced data mining tool in food sensory and consume researches. The result of our survey indicates that deep learning outperforms other methods such as manual feature extractors, conventional machine learning algorithms, and deep learning as a promising tool in food quality and safety inspection. The encouraging results in classification and regression problems achieved by deep learning will attract more research efforts to apply deep learning into the field of food in the future.

show abstract

Section: Challenges and Future Perspective Of Deep Learning In Food Dmentioning

confidence: 99%

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

361

166

View full text Add to dashboard Cite

show abstract

“…For example, some tools that may be closer to commercial use than expected are spot and spray technology (i.e., H-Sensor (Agricon GmbH, Ostrau, Germany) and See and Spray (Blue River Technology, Sunnyvale, CA, USA)) [99], variable rate applications (both herbicides and irrigation) [100,101], autonomous tractors (concept vehicle by Case IH), targeted tillage [102], unmanned aerial vehicles [103], and robots that target weeds underneath the crop canopy [104][105][106][107]. More unique options that expand on weed recognition [108,109], which itself is still a work in progress, to complementary techniques include tactics, such as laser weeding [110,111], stamping [112], microwaves and radiations [113][114][115], electrical discharge [116], flaming [117][118][119][120], pressurized air [121,122], or solar irradiation [123][124][125], have been tested in the past and are being revisited in light of new technology. These technologies have begun to be incorporated into modern remote sensing systems.…”

Section: Endless Possibilitiesmentioning

confidence: 99%

Shifting the Paradigm: An Ecological Systems Approach to Weed Management

Gage

Schwartz-Lazaro

2019

Agriculture

View full text Add to dashboard Cite

Weeds have been historically, and are still today, the primary and most economically important pest in agriculture. Several selection pressures associated with weed management, such as an overreliance on herbicides, have promoted the rapid evolution of herbicide-resistant weeds. Integrated Weed Management (IWM) is promoted as an ecological systems approach, through the combination of biological, chemical, cultural, ecological, and mechanical control methods. The concept of a systems approach is defined as managing weeds by combining practice and knowledge with the goals of increasing yield and minimizing economic loss, minimizing risks to human health and the environment, and reducing energy requirements and off-target impacts. The reliance on herbicides in modern cropping systems has shifted the management focus from requiring intimate knowledge of biology, ecology, and ecological systems to herbicide chemistry, mixes, and rotations, application technology, and herbicide-tolerant crop traits. Here, an ecological systems approach is considered, examining new trends and technologies in relation to IWM and weed ecology. Prevention of spread, seedbank management, crop rotations, tillage, cover crops, competitive cultivars, biological weed control, and future solutions in concept-only are presented, and knowledge gaps are identified where research advancements may be possible. An ecological systems approach will provide improved stewardship of new herbicide technologies and reduce herbicide resistance evolution through diversification of selection pressures. Agroecological interactions should be studied in light of new, developing weed control technologies. The science of weed management needs to refocus on the foundations of weed biology and ecology to enable an ecological systems approach and promote agricultural sustainability.

show abstract

“…Romero-Trigueros et al [25] analyzed correlations of citrus physiology stresses and gas exchange status using multispectral UAV images. Csillik et al [26] proposed a methodology to detect citrus and other crops trees from UAV images using a simple deep learning convolutional neural network (CNN).Deep learning algorithms (artificial intelligence based) are increasingly used in remote sensing applications [27][28][29]. These methods achieved dramatic improvements in many domains and attracted considerable interest of both academic and industrial communities [30].…”

mentioning

confidence: 99%

“…Deep learning algorithms (artificial intelligence based) are increasingly used in remote sensing applications [27][28][29]. These methods achieved dramatic improvements in many domains and attracted considerable interest of both academic and industrial communities [30].…”

mentioning

confidence: 99%

UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence

2019

Self Cite

View full text Add to dashboard Cite

Traditional plant breeding evaluation methods are time-consuming, labor-intensive, and costly. Accurate and rapid phenotypic trait data acquisition and analysis can improve genomic selection and accelerate cultivar development. In this work, a technique for data acquisition and image processing was developed utilizing small unmanned aerial vehicles (UAVs), multispectral imaging, and deep learning convolutional neural networks to evaluate phenotypic characteristics on citrus crops. This low-cost and automated high-throughput phenotyping technique utilizes artificial intelligence (AI) and machine learning (ML) to: (i) detect, count, and geolocate trees and tree gaps; (ii) categorize trees based on their canopy size; (iii) develop individual tree health indices; and (iv) evaluate citrus varieties and rootstocks. The proposed remote sensing technique was able to detect and count citrus trees in a grove of 4,931 trees, with precision and recall of 99.9% and 99.7%, respectively, estimate their canopy size with overall accuracy of 85.5%, and detect, count, and geolocate tree gaps with a precision and recall of 100% and 94.6%, respectively. This UAV-based technique provides a consistent, more direct, cost-effective, and rapid method to evaluate phenotypic characteristics of citrus varieties and rootstocks.UAVs allow growers to constantly monitor crop health status, estimate plant water needs, and even detect diseases [15][16][17]. They represent a low-cost method for image acquisition in high-resolution settings and are increasingly studied for agricultural applications. Nebiker et al. [18] reported one of the first successful application of UAVs combined with a low-cost multispectral camera for remote sensing to assess health of grapevine crops. Hunt et al. [19] analyzed UAV multispectral imagery for crop monitoring and they found a good correlation between leaf area index and the green normalized difference vegetation index (green NDVI). In order to achieve high spatial resolution of image data, the overlaps of the UAV images, and, hence, the flight path planning, must be critically selected [20]. Matese et al. [21] mapped the vigor of vineyards using the NDVI index from a high-resolution multispectral camera. Furthermore, UAVs were utilized to create plant inventories.Malek et al. [22] achieved promising results in detecting palm trees used an extreme learning machine classifier in UAV images.In citrus, multispectral imagery from UAVs were recently utilized to identify tree stresses and diseases. Garcia-Ruiz et al. [23] and Sankaran et al. [24] analyzed multispectral features of Huanglongbing (HLB) infected citrus trees for classification. Romero-Trigueros et al. [25] analyzed correlations of citrus physiology stresses and gas exchange status using multispectral UAV images. Csillik et al. [26] proposed a methodology to detect citrus and other crops trees from UAV images using a simple deep learning convolutional neural network (CNN).Deep learning algorithms (artificial intelligence based) are increasingly used in rem...

show abstract

Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence

Cited by 292 publications

References 25 publications

Application of Deep Learning in Food: A Review

Application of Deep Learning in Food: A Review

Shifting the Paradigm: An Ecological Systems Approach to Weed Management

UAV-Based High Throughput Phenotyping in Citrus Utilizing Multispectral Imaging and Artificial Intelligence

Contact Info

Product

Resources

About