{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:15:05Z","timestamp":1773965705422,"version":"3.50.1"},"reference-count":25,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"FCT\u2014Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"DOI":"10.13039\/501100015494","name":"Instituto de Telecomunica\u00e7\u00f5es","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100015494","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AgriEngineering"],"abstract":"<jats:p>Effective and sustainable livestock management within Mediterranean ecosystems depends heavily on accurate and timely monitoring of sward composition. Traditionally, this task has relied on human observers who must traverse large and often rugged areas to identify the distribution of grasses, legumes, shrubs, and other plant groups. However, this approach is not only labor-intensive and slow but also susceptible to substantial human error, especially when observations must be repeated frequently or carried out under difficult field conditions. In the present study, an alternative method that integrates wearable cameras with modern computer-vision techniques to automatically recognize pasture plant species through an edge device present in farm premises was investigated. Additionally, the feasibility of achieving reliable classification performance on resource-constrained edge devices was evaluated. To this end, five widely used pre-trained convolutional neural networks were compared against a lightweight custom model developed entirely from scratch. The results demonstrated that ResNet50 delivered the strongest classification accuracy, achieving a Matthews Correlation Coefficient (MCC) of 0.992. Nonetheless, the custom lightweight model proved to be a practical compromise for real-world field use, reaching an MCC of 0.893 while requiring only 6.24 MB of storage. The inference performance on Raspberry Pi 4, Raspberry Pi 5, and Jetson Orin Nano platforms was also evaluated, revealing that the Selective Search stage remains a major computational limitation for achieving real-time operation. The results obtained confirm the possibility of implementing a plant identification system in agricultural facilities without the need to transfer images to a cloud-based application.<\/jats:p>","DOI":"10.3390\/agriengineering8020047","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T14:12:46Z","timestamp":1770041566000},"page":"47","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Wearable Vision-Based Plant Identification System for Automated Pasture Monitoring in the Mediterranean Region"],"prefix":"10.3390","volume":"8","author":[{"given":"Rafael","family":"Curado","sequence":"first","affiliation":[{"name":"Departamento de Eletr\u00f3nica, Telecomunica\u00e7\u00f5es e Inform\u00e1tica and Instituto de Telecomunica\u00e7\u00f5es, Universidade de Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-4231","authenticated-orcid":false,"given":"Pedro","family":"Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"Escola Superior de Tecnologia e Gest\u00e3o de \u00c1gueda and Instituto de Telecomunica\u00e7\u00f5es, Universidade de Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5981-3829","authenticated-orcid":false,"given":"Maria R.","family":"Marques","sequence":"additional","affiliation":[{"name":"Instituto Nacional de Investiga\u00e7\u00e3o Agr\u00e1ria e Veterin\u00e1ria I.P. (INIAV), Avenida Professor Vaz Portugal, 2005-424 Vale de Santar\u00e9m, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6504-9441","authenticated-orcid":false,"given":"M\u00e1rio","family":"Antunes","sequence":"additional","affiliation":[{"name":"Departamento de Eletr\u00f3nica, Telecomunica\u00e7\u00f5es e Inform\u00e1tica and Instituto de Telecomunica\u00e7\u00f5es, Universidade de Aveiro, 3810-193 Aveiro, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Carreira, E., Serrano, J., Lopes de Castro, J., Shahidian, S., and Pereira, A.F. (2023). Montado Mediterranean Ecosystem (Soil\u2013Pasture\u2013Tree and Animals): A Review of Monitoring Technologies and Grazing Systems. Appl. Sci., 13.","DOI":"10.3390\/app13106242"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.isprsjprs.2016.03.010","article-title":"Mapping of Macro and Micro Nutrients of Mixed Pastures Using Airborne AisaFENIX Hyperspectral Imagery","volume":"117","author":"Pullanagari","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sales-Baptista, E., Ferraz-De-Oliveira, M.I., Terra-Braga, M., de Castro, J.A.L., Serrano, J., and d\u2019Abreu, M.C. (2022). Characterization of Grazing Behaviour Microstructure Using Point-of-View Cameras. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0265037"},{"key":"ref_4","first-page":"19","article-title":"Estudo do Comportamento Alimentar de Ovelhas Serra da Estrela em Condi\u00e7\u00f5es de Pastoreio Diferido\/\/Rotacional. Influ\u00eancia da Suplementa\u00e7\u00e3o Energ\u00e9tica da Erva na Quantidade e Qualidade do Leite Produ-Zido","volume":"22","author":"Marques","year":"2001","journal-title":"Pastagens Forrag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e11448","DOI":"10.1002\/aps3.11448","article-title":"Digital Morphometrics: Application of MorphoLeaf in Shape Visualization and Species Delimitation, Using Cucurbitaceae Leaves as a Model","volume":"9","author":"Oso","year":"2021","journal-title":"Appl. Plant Sci."},{"key":"ref_6","first-page":"471","article-title":"Plant Species Recognition from Leaf-Vein Structures Using ResNets","volume":"Volume 491","author":"Uddin","year":"2023","journal-title":"Emerging Technologies in Data Mining and Information Security"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.patcog.2011.05.013","article-title":"A Review on Automatic Image Annotation Techniques","volume":"45","author":"Zhang","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"van der Plas, T.L., Geikie, S.T., Alexander, D.G., and Simms, D.M. (2023). Multi-Stage Semantic Segmentation Quantifies Fragmentation of Small Habitats at a Landscape Scale. Remote Sens., 15.","DOI":"10.3390\/rs15225277"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Belfiore, O., and Parente, C. (2016). Comparison of Different Algorithms to Orthorectify WorldView-2 Satellite Imagery. Algorithms, 9.","DOI":"10.3390\/a9040067"},{"key":"ref_10","first-page":"12","article-title":"A New Rapid, Low-Cost and GPS-Centric Unmanned Aerial Vehicle Incorporating in-Situ Multispectral Oil Palm Trees Health Detection","volume":"2","author":"See","year":"2018","journal-title":"J. Agric. Sci. Bot."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1111\/j.1442-9993.2008.01844.x","article-title":"A Protocol for Assessment and Integration of Vegetation Maps, with an Application to Spatial Data Sets from South-eastern Australia","volume":"33","author":"Keith","year":"2008","journal-title":"Austral Ecol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Avondo, M., Bognanno, M., Beritelli, F., Avanzato, R., Biondi, L., Gimmillaro, F., Bognanno, S., Piccitto, A., and Tumino, S. (2025). Sound and Video Detection as a Tool to Estimate Free Grazing Behavior in Sheep on Different Swards. Animals, 15.","DOI":"10.3390\/ani15182671"},{"key":"ref_13","first-page":"1","article-title":"Automated Monitoring of Foraging Behaviour in Free Ranging Sheep Grazing a Bio-Diverse Pasture Using Audio and Video Information","volume":"7","author":"Sneddon","year":"2014","journal-title":"Int. J. Smart Sens. Intell. Syst."},{"key":"ref_14","unstructured":"Camara, F., Romano, R., Markkula, G., Madigan, R., Merat, N., and Fox, C. (2018, January 5\u20138). Sheep Nocturnal Grazing Behavior Using Infrared Point-of-View Camera\u2014A Preliminary Study. Proceedings of the Measuring Behavior, Manchester, UK."},{"key":"ref_15","unstructured":"Parra, L. (2024). Smart Collars for Sheep: Leveraging Machine Learning for Improved Pasture Management. Proceedings of the CSRF 2024 the First International Conference on Sustainable and Regenerative Farming, ThinkMind."},{"key":"ref_16","unstructured":"Gon\u00e7alves, P., Xavier, W., and Corrente, G. (2024, January 17\u201320). iRunMon: A Real-Time Ruminant Monitor. Proceedings of the 11th International Conference on Information and Communication Technologies in Agriculture, Food & Environment (HAICTA 2024), Karlovasi, Greece. Available online: https:\/\/ceur-ws.org\/Vol-3930\/paper5.pdf."},{"key":"ref_17","unstructured":"Gon\u00e7alves, P., Marques, M.R., and Antunes, M. (2025). Plant Species Identification, Zenodo."},{"key":"ref_18","unstructured":"(2025, October 05). Optuna\u2014A Hyperparameter Optimization Framework. Available online: https:\/\/optuna.org\/."},{"key":"ref_19","unstructured":"(2025, November 18). GitHub\u2014Akarazniewicz\/Cocosplit: Simple Tool to Split COCO Annotations into Train\/Test Datasets. Available online: https:\/\/github.com\/akarazniewicz\/cocosplit."},{"key":"ref_20","unstructured":"(2025, November 18). AlpacaTechJP\u2014GitHub. Available online: https:\/\/github.com\/AlpacaTechJP."},{"key":"ref_21","unstructured":"(2025, November 18). Raspberry Pi 4 Model B Specifications\u2014Raspberry Pi. Available online: https:\/\/www.raspberrypi.com\/products\/raspberry-pi-4-model-b\/specifications\/."},{"key":"ref_22","unstructured":"(2025, November 18). Buy a Raspberry Pi 5\u2014Raspberry Pi. Available online: https:\/\/www.raspberrypi.com\/products\/raspberry-pi-5\/."},{"key":"ref_23","unstructured":"NVIDIA (2025, November 18). Jetson Nano Traz o Poder da AI Moderna Para Dispositivos No Edge. Available online: https:\/\/www.nvidia.com\/pt-br\/autonomous-machines\/embedded-systems\/jetson-nano\/product-development\/."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hoang, V.T., and Jo, K.H. (2021, January 8\u201310). Practical Analysis on Architecture of EfficientNet. Proceedings of the International Conference on Human System Interaction, HSI 2021, Gda\u0144sk, Poland.","DOI":"10.1109\/HSI52170.2021.9538782"},{"key":"ref_25","unstructured":"(2025, November 18). GitHub\u2014AlpacaTechJP\/Selectivesearch: Selective Search Implementation for Python. Available online: https:\/\/github.com\/AlpacaTechJP\/selectivesearch."}],"container-title":["AgriEngineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2624-7402\/8\/2\/47\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T05:18:06Z","timestamp":1770182286000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2624-7402\/8\/2\/47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":25,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["agriengineering8020047"],"URL":"https:\/\/doi.org\/10.3390\/agriengineering8020047","relation":{},"ISSN":["2624-7402"],"issn-type":[{"value":"2624-7402","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]}}}