Zobrazit v EDS

APPLICATION OF TARGET DETECTION ALGORITHM BASED ON DEEP LEARNING IN FARMLAND PEST RECOGNITION

Uloženo v:

Podrobná bibliografie
Název:	APPLICATION OF TARGET DETECTION ALGORITHM BASED ON DEEP LEARNING IN FARMLAND PEST RECOGNITION
Autoři:	Shi Wenxiu and Li Nianqiang
Informace o vydavateli:	Zenodo
Rok vydání:	2020
Sbírka:	Zenodo
Témata:	Object detection algorithm, Faster R-CNN, Inception network
Popis:	Combining with deep learning technology, this paper proposes a method of farmland pest recognition based on target detection algorithm, which realizes the automatic recognition of farmland pest and improves the recognition accuracy. First of all, a labeled farm pest database is established; then uses Faster R-CNN algorithm, the model uses the improved Inception network for testing; finally, the proposed target detection model is trained and tested on the farm pest database, with the average precision up to 90.54%.
Druh dokumentu:	article in journal/newspaper
Jazyk:	unknown
Relation:	https://zenodo.org/records/3889762; oai:zenodo.org:3889762; https://doi.org/10.5281/zenodo.3889762
DOI:	10.5281/zenodo.3889762
Dostupnost:	https://doi.org/10.5281/zenodo.3889762 https://zenodo.org/records/3889762
Rights:	Creative Commons Attribution 4.0 International ; cc-by-4.0 ; https://creativecommons.org/licenses/by/4.0/legalcode
Přístupové číslo:	edsbas.5D6C4C81
Databáze:	BASE

Popis
Abstrakt:	Combining with deep learning technology, this paper proposes a method of farmland pest recognition based on target detection algorithm, which realizes the automatic recognition of farmland pest and improves the recognition accuracy. First of all, a labeled farm pest database is established; then uses Faster R-CNN algorithm, the model uses the improved Inception network for testing; finally, the proposed target detection model is trained and tested on the farm pest database, with the average precision up to 90.54%.
DOI:	10.5281/zenodo.3889762