The convolutional neural networks: Applications in precision agriculture

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 industriji. 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.A promising concept of artificial intelligence that records intense developments in the field of digital imaging is Deep Learning (DL). More intensive research within this field has been recorded over the past two decades, and has been applied in the agricultural industry as well. This paper will describe the DL technology which represents a part of Machine Learning (ML), based on Convolutional Neural Networks (CNN). It takes a special application in a machine vision where it allows machines to learn from experience, adapt to new technologies, and perform human tasks. Input data can be from a variety of sources: from classic digital camera shots to satellite images, as well as from recordings obtained by means of hyperspectral, thermal and infrared cameras. The increasing popularity and use of trunks in agricultural fields is increasing, and the very application of these new technologies leads to the huge amount of data that needs to be processed in real time, therefore, DL algorithms are increasingly used. The paper will summarize the current and considered possible applications of CNN in primary and precise agriculture in the future