When measuring and analyzing site-specific yield known as the yield monitoring within a wider cycle of precise agriculture, about 30 parameters are measured from inertia for mapping yields. The most important parameters with the default three parameters that define the location (latitude, longitude and elevation) are mass grain yield and grain moisture. In addition to this data during the yield monitoring, the temperature of the grain, speed of the combine and delution of precision (DOP) were also observed in this paper. By simple statistical testing of the correlation between these parameters, the level of mutual influence was determined, among other things, the degree of influence of all mentioned and observed parameters on yield, in response to the research question whether the yield affects another parameter other than the location and physical and chemical properties of the land at that location. A different degree of influence was determined, but no significant additional impact on the yield was calculated by measuring and measuring the measurement itself. For the monitoring of the yield of seed wheat harvesting on the "Mladost" PKB, Tabla 2, the Class Lexion 450 harvester with an upgraded system for monitoring the AGL Technology manufacturer was used. For the statistical analysis, the parametric method of correlation within the software package SPSS Statistics v.21 was used.
Obećavajući koncept veštačke inteligencije koji beleži intenzivan razvoj u oblasti digitalne obrade slike je duboko učenje (Deep Learning-DL). Intenzivnije istraživanje u okviru ove oblasti beleži se poslednje dve decenije, a primenu poprima i u poljoprivrednoj industiji. U okviru ovog radu opisana je tehnologija DL koja predstavlja deo mašinskog učenja (Machine Learning-ML), bazirajući se na konvolucijske neuralne mreže (Convolution Neural Networks-CNN). Posebnu primenu zauzima u mašinskoj viziji gde omogućava mašinama da uče iz iskustva, prilagođavaju se novim tehnologijama i obavljaju ljudske zadatke. Ulazni podaci mogu biti iz raznovrsnih izvora: od klasičnih digitalnih snimaka kamere do satelitskih snimaka, kao i snimaka dobijenih pomoću hiperspektralnih, termalnih i infrared kamera. Sve je veća popularnost i upotreba dronova na poljoprivrednim površinama, a samom primenom ovih novih tehnologija dolazi se do ogromnog broja podataka koje je potrebno obraditi u realnom vremenu, stoga se i algoritmi DL sve više upotrebljavaju. U radu su prikazane dosadašnje primene CNN u primarnoj i preciznoj poljoprivredi kao i moguće primene DL u budućnosti. Ključne reči: precizna poljoprivreda, veštačka inteligencija, mašinski vid UVOD DL (Deep Learning) je posebna grana mašinskog učenja koja je najširu upotrebu našla u mašinskom vidu. Algoritmi DL su se pokazali neuporedivno preciznijim i bržim
Color sorting is a technological operation performed with the aim of classifying compliant and noncompliant agricultural products in large-capacity industrial systems for agricultural product processing. This paper investigates the application of the YOLOv3 algorithm on raspberry images as a method developed for the detection, localization, and classification of objects based on convolutional neural networks (CNNs). To our knowledge, this is the first time a YOLO algorithm or CNN has been used with original images from the color sorter to focus on agricultural products. Results of the F1 measure were in the 92–97% range. Images in full resolution, 1024 × 1024, produced an average detection time of 0.37 s. The impact of the hyperparameters that define the YOLOv3 model as well as the impact of the application of the chosen augmentative methods on the model are evaluated. The successful classification of stalks, which is particularly challenging due to their shape, small dimensions, and variations, was achieved. The presented model demonstrates the ability to classify noncompliant products into four classes, some of which are appropriate for reprocessing. The software, including a graphic interface that enables the real-time testing of machine learning algorithm, is developed and presented.
Sažetak: U inženjerskom projektovanju, problem prostornog rasporeda ima poseban značaj i predmet je istraživanja dugi niz godina. Tu su prisutne dve grupe problema: problem lokacije i problem raspodele elemenata. U domenu industrije problem lokacije je vezan za određivanje najpovoljnijeg mesta (proizvodnog kompleksa) na makro planu. Kada se analizira problem raspodele elemenata, potrebno je pre svega imati uvid u skup potencijalnih površina koje pojedini elementi mogu da zahtevaju u okviru nekog analiziranog sistema. Kako bi se objasnio značaj prostornog rasporeda i ciljevi njegovog uvođenja, potrebno je opisati postojeće konfiguracije linije odabranog proizvoda, na njima prikazati tok materijala, prostorni raspored i stepen automatizacije. Povećanje stepena automatizacije proizvodnih linija može imati samo prednosti, jer se povećava kvalitet gotovog proizvoda, skraćuje proizvodni ciklus i time povećava proizvodnost.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.