Automated Wildlife Recognition

Pavlicek, Josef; Jarolímek, Jan; Pavlickova, Petra; Dvořák, Stanislav; Pavlík, Jan; Hanzlík, Petr; Forests, Military; Farms, state-owned enterprise

doi:10.7160/aol.2018.100105

Cited by 7 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Having a large dataset is one of the simple ways to prevent this problem. Furthermore, the data set must include all conditions, such as various mung bean growth stages and shadows caused by neighboring mung beans, to improve robustness [ 32 ] Accurate labeling is critical for efficient image search and retrieval.…”

Section: Methodsmentioning

confidence: 99%

“…Pound et al [ 19 ] predicted the paradigm shift in phenotyping aided by deep learning approaches. Since then, ML has demonstrated its potential in various automated agricultural systems ([ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ]). Furthermore, Kamilaris and Prenafeta-Boldú [ 33 ] reviewed studies that used ML algorithms in plant and agricultural research areas emphasizing that those algorithms provide high accuracy and outperform deterministic image processing techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-Based Plant Detection Algorithms to Automate Counting Tasks Using 3D Canopy Scans

Kartal

Choudhary

Masner

et al. 2021

Sensors

View full text Add to dashboard Cite

This study tested whether machine learning (ML) methods can effectively separate individual plants from complex 3D canopy laser scans as a prerequisite to analyzing particular plant features. For this, we scanned mung bean and chickpea crops with PlantEye (R) laser scanners. Firstly, we segmented the crop canopies from the background in 3D space using the Region Growing Segmentation algorithm. Then, Convolutional Neural Network (CNN) based ML algorithms were fine-tuned for plant counting. Application of the CNN-based (Convolutional Neural Network) processing architecture was possible only after we reduced the dimensionality of the data to 2D. This allowed for the identification of individual plants and their counting with an accuracy of 93.18% and 92.87% for mung bean and chickpea plants, respectively. These steps were connected to the phenotyping pipeline, which can now replace manual counting operations that are inefficient, costly, and error-prone. The use of CNN in this study was innovatively solved with dimensionality reduction, addition of height information as color, and consequent application of a 2D CNN-based approach. We found there to be a wide gap in the use of ML on 3D information. This gap will have to be addressed, especially for more complex plant feature extractions, which we intend to implement through further research.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Plant Detection Algorithms to Automate Counting Tasks Using 3D Canopy Scans

Kartal

Choudhary

Masner

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Cloud services, Internet of Things, Big Data Analytics) that can be important in the agriculture and food industry equally. In the article of Látečková, Bolek & Szabo (2018) cloud computing was underlined as a solution that can help in virtualisation of processes and it establishes a single modern and complex system of agricultural smart enterprises supported by ICTs. Internet of Things would have a contribution to the change of agri-food processes and towards data-driven farming supported by decision-making tools (Verdouw, Wolfert & Tekinerdogan, 2016).…”

Section: Literature Reviewmentioning

confidence: 99%

Digitalized business processes – assessment and opportunities of Hungarian agri-food companies

Botos¹,

Salais²,

Tóth³

et al. 2020

JAI

View full text Add to dashboard Cite

Digitalization in agri-food supply chain has become increasingly important since safe and secure food supply is a priority for stakeholders. ICT-based (Information and Communication Technologies) business solutions have an impact on the whole food supply chain and separately the participants (producers, processors, distributors, retailers and consumers). Advanced technologies support many business activities as proving traceability and transparency, improving internal business processes, simplifying cooperation with partners and establishing the capability to develop supplementary value-added services. The main objective of the current paper is to determine the development potentials of digitalized business processes related to the operation of companies related to the production and processing of agricultural products and food. For this aim, we analysed the differences between food producers and food processors regarding their evaluation of ICT solutions in their partnerships and for certain business activities. Institute of Applied Informatics and Logistics at University of Debrecen has prepared a questionnaire for a survey on the assessment of ICT by food producer and food processor enterprises (n=500). We go into a little bit more depth about the role of information share with the final consumers as they are more and more conscious about their food and may have special information requirements for food products. Thus, we supplemented our research with another questionnaire that was aimed at young food consumers (n=376) to survey their attitude to the main food information and the opportunities to support their choice. For the analyses, we used descriptive statistical methods and Mann-Whitney test. Our results show that both enterprise categories assessed the variables tested as being rather medium importance. Statistically, processors evaluated two variables significantly higher compared to producers these were the ‘Fast evaluation of business performance’ (Sig(2-tailed=0,010) and ‘Operating high-quality website’ (Sig(2-tailed)=0.012). For the respondent consumers, food component list is one of the most important product information. The importance of this variable was the third during the purchase (after price and quality) and second in product comparison (after price). The majority (64%) often or always read this information on the package. Most respondents indicated a willingness to use such mobile applications that may support easy information access.

show abstract

“…Solving problems related to information support of economic diagnostics in the agricultural sector have found their scientific and practical application in research on management support of agricultural enterprises (Ensslin, L. et al, 2017); support services for innovations in agriculture (Faure, G. et al, 2019); functioning information systems in agricultural enterprises (Látečková, A. et al, 2018); diagnostics and decision-making of the company management within the period of economic crisis and recession (Tomšík, P. et al, 2010) and others.…”

Section: Introductionmentioning

confidence: 99%

Forecasting the state of agricultural enterprises based on the results of economic diagnostics

Bezpartochna

2021

VUZF

View full text Add to dashboard Cite

This article is devoted to the study of information support and methodological tools for economic diagnostics of agricultural enterprises, based on the results of which the cost of resource potential predicted. Determined the factors of influence of the internal and external environment on forecasting the cost resource potential of agricultural enterprises. The methodological toolkit for forecasting the cost resource potential of agricultural enterprises used, taking into account the extrapolation of indicators and the coefficient of change. Built the economic-mathematical models for forecasting the general potential of agricultural enterprises in Ukraine. Proposed the scheme of forecasting the state of agricultural enterprises and complex information support the stages of making managerial decisions by the management of agricultural enterprises. For agricultural enterprises of Ukraine, promising directions for the development of economic activities are proposed.

show abstract

Automated Wildlife Recognition

Cited by 7 publications

References 12 publications

Machine Learning-Based Plant Detection Algorithms to Automate Counting Tasks Using 3D Canopy Scans

Machine Learning-Based Plant Detection Algorithms to Automate Counting Tasks Using 3D Canopy Scans

Digitalized business processes – assessment and opportunities of Hungarian agri-food companies

Forecasting the state of agricultural enterprises based on the results of economic diagnostics

Contact Info

Product

Resources

About