dc.contributor.author | Chicchón Apaza, Miguel Ángel | |
dc.contributor.author | Bedón Monzón, Héctor Manuel | |
dc.contributor.other | Bedón Monzón, Héctor Manuel | |
dc.contributor.other | Chicchón Apaza, Miguel Ángel | |
dc.date.accessioned | 2020-04-24T00:27:30Z | |
dc.date.available | 2020-04-24T00:27:30Z | |
dc.date.issued | 2020 | |
dc.identifier.citation | Chicchon Azapa, M. & Bedón Monzón, H. (2020). Semantic Segmentation of Weeds and Crops in Multispectral Images by Using a Convolutional Neural Networks Based on U-Net. Communications in Computer and Information Science. 473-485. https://link.springer.com/chapter/10.1007%2F978-3-030-42520-3_38 | es_PE |
dc.identifier.uri | https://hdl.handle.net/20.500.12724/10812 | |
dc.description.abstract | A first step in the process of automating weed removal in precision agriculture is the semantic segmentation of crops, weeds and soil. Deep learning techniques based on convolutional neural networks are successfully applied today and one of the most popular network architectures in semantic segmentation problems is U-Net. In this article, the variants in the U-Net architecture were evaluated based on the aggregation of residual and recurring blocks to improve their performance. For training and testing, a set of data available on the Internet was used, consisting of 60 multispectral images with unbalanced pixels, so techniques were applied to increase and balance the data. Experimental results show a slight increase in quality metrics compared to the classic U-Net architecture. | es_PE |
dc.language.iso | spa | es_PE |
dc.publisher | Springer | es_PE |
dc.rights | info:eu-repo/semantics/restrictedAccess | |
dc.source | Repositorio Institucional Ulima | es_PE |
dc.source | Universidad de Lima | es_PE |
dc.subject | Automatización | es_PE |
dc.subject | Agricultura | es_PE |
dc.subject | Redes neuronales artificiales | es_PE |
dc.subject | Automation | es_PE |
dc.subject | Agriculture | es_PE |
dc.subject | Artificial neural networks | es_PE |
dc.title | Semantic Segmentation of Weeds and Crops in Multispectral Images by Using a Convolutional Neural Networks Based on U-Net | es_PE |
dc.type | info:eu-repo/semantics/conferenceObject | |
dc.type.other | Artículo de conferencia en Scopus | |
ulima.areas.lineasdeinvestigacion | Productividad y empleo / Innovación: tecnologías y productos | es_PE |
dc.publisher.country | DE | es_PE |
dc.subject.ocde | http://purl.org/pe-repo/ocde/ford#2.02.04 | |
dc.identifier.doi | https://doi-org.ezproxy.ulima.edu.pe/10.1007/978-3-030-42520-3_38 | |
ulima.cat | 9 | |
ulima.autor.afiliacion | Chicchón Apaza, Miguel Ángel (Exponential Technology Group (GITX-ULIMA), Institute of Scientific Research (IDIC), University of Lima) | es_PE |
ulima.autor.afiliacion | Bedón Monzón, Héctor Manuel (Exponential Technology Group (GITX-ULIMA), Institute of Scientific Research (IDIC), University of Lima) | es_PE |
ulima.autor.carrera | Chicchón Apaza, Miguel Ángel (No figura en la lista del año 2019) | es_PE |
ulima.autor.carrera | Bedón Monzón, Héctor Manuel (Ingeniería Industrial) | es_PE |
dc.identifier.scopusid | 2-s2.0-85082396508 | |
dc.identifier.event | International Conference on Applied Technologies (ICAT) | |