DSpace Coleção: Artigo em anais de congresso (CNPTIA)Artigo em anais de congresso (CNPTIA)https://www.alice.cnptia.embrapa.br/alice/handle/item/1972026-04-29T08:23:14Z2026-04-29T08:23:14ZMultistep pasture vigor classification at the local scale: a comparative analysis in Guia Lopes da Laguna, MS.CASTRO, V. H. M. e de C.KLINKE NETO, G.PARREIRAS, T. C.BOLFE, E. L.BERGIER, I.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11859462026-04-04T13:03:39Z2025-01-01T00:00:00ZTítulo: Multistep pasture vigor classification at the local scale: a comparative analysis in Guia Lopes da Laguna, MS.
Autoria: CASTRO, V. H. M. e de C.; KLINKE NETO, G.; PARREIRAS, T. C.; BOLFE, E. L.; BERGIER, I.
Conteúdo: Accurate pasture mapping is essential for sustainable livestock management in Brazil, where degradation affects extensive areas. Tools like the Atlas das Pastagens provide large-scale data on pasture quality, but local-scale accuracy remains underexplored. This study assessed the accuracy of pasture vigor classification in the 2023 Atlas using 60 groundtruth points collected in Guia Lopes da Laguna, Mato Grosso do Sul, in June 2024. Field data were classified into High, Medium, or Low vigor and then grouped into a binary scheme: “non-degraded” (high vigor) and “degraded” (medium + low Vigor). A confusion matrix comparing reference (field) and estimated (Atlas) data revealed an overall accuracy of 73.3%. The method in Atlas performed better at detecting degraded areas (recall = 80.0%, precision = 70.6%, F1-score = 75.0%) than non-degraded areas (recall = 34.8%, precision = 47.1%, F1-score = 40.0%). While the binary approach improves overall accuracy, the Atlas still shows significant limitations in correctly identifying non-degraded (High Vigor) pastures at the municipal level, often underestimating their presence. Therefore, the Atlas is a useful tool for detecting degradation signs but should be used with caution in applications that require high local precision in distinguishing productive pasture areas.2025-01-01T00:00:00ZProspective analysis of the adoption of digital technologies in agriculture.DIBBERN, T.ROMANI, L. A. S.EVANGELISTA, S. R. M.MARTINS, V. A.MASSRUHÁ, S. M. F. S.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11859412026-04-04T13:03:41Z2025-01-01T00:00:00ZTítulo: Prospective analysis of the adoption of digital technologies in agriculture.
Autoria: DIBBERN, T.; ROMANI, L. A. S.; EVANGELISTA, S. R. M.; MARTINS, V. A.; MASSRUHÁ, S. M. F. S.
Conteúdo: Open innovation emerges when knowledge, experience, and capabilities are distributed across various organizations, enabling innovative activities inside and outside research institutions within a collaborative system. In the agricultural sector, this phenomenon is manifested through innovation ecosystems that involve multiple stakeholders, including universities, governments, research institutes, companies, cooperatives, and financial markets. However, one of the main challenges is measuring an innovation's success, especially in the early stages of developing technology-based products. Given this context, this paper proposes a methodological model for developing indicators that measure the level of success in adopting digital technology in the field, from the initial stages of technological product development. Five stages and the results obtained in the benchmarking phase are presented.2025-01-01T00:00:00ZSupporting riverside açaí production: field data from Breves DAT for remote sensing applications.SOARES, V. B.BOLFE, E. L.PARREIRAS, T. C.KLINKE NETO, G.COSTA, M. O. X. D.XAUD, H. A. M.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11859482026-04-04T13:03:45Z2025-01-01T00:00:00ZTítulo: Supporting riverside açaí production: field data from Breves DAT for remote sensing applications.
Autoria: SOARES, V. B.; BOLFE, E. L.; PARREIRAS, T. C.; KLINKE NETO, G.; COSTA, M. O. X. D.; XAUD, H. A. M.
Conteúdo: The municipality of Breves, located in the Marajó Archipelago - Pará State, is a strategic area for açaí production in the Brazilian Amazon. However, the characterization of its productive environments using remote sensing still represents a significant methodological challenge, due to the scarcity of field data, logistical difficulties and high cloud cover. This paper presents the collection of georeferenced data carried out by the Embrapa Digital Agriculture team during a field campaign in October 2024, using the AgroTag application. The results highlight the importance of using high-resolution data and advanced techniques for mapping land use in the Amazon. This study provides valuable reference data for future classification models and reinforces the importance of integrating remote sensing and fieldwork in data-poor regions.2025-01-01T00:00:00ZSEEmear: a system for large scale geo-referenced stereo imaging of orchards.SANTOS, T. T.KOENIGKAN, L. V.GEBLER, L.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11859502026-04-04T13:03:47Z2025-01-01T00:00:00ZTítulo: SEEmear: a system for large scale geo-referenced stereo imaging of orchards.
Autoria: SANTOS, T. T.; KOENIGKAN, L. V.; GEBLER, L.
Conteúdo: Precision agriculture applications at the plant level require high-resolution, detailed imaging that cannot be adequately provided by satellite-based remote sensing due to insufficient resolution and suboptimal viewing angles. While Unmanned Aerial Vehicles (UAVs) offer improved capabilities, their downward-facing perspective and navigation challenges in orchards limit their effectiveness for fruit monitoring and anomalies detection. To address these limitations, we present SEEmear, a novel ground-based proximal sensing system for large-scale geo-referenced stereo imaging of orchard environments. The system integrates high-performance embedded computing, wide-angle global shutter RGB-D cameras, and precision RTK GNSS positioning, enabling simultaneous imaging of both sides of orchard rows from close proximity. SEEmear's 110° field-of-view cameras capture entire tree structures even at distances of 1 meter, while global shutter sensors eliminate motion artifacts essential for moving platforms. We tested the system in apple orchards, collecting comprehensive geo-referenced RGB-D imagery across 1.50 ha in approximately 40 minutes per session. The resulting dataset supports advanced applications including depth estimation, 3D reconstruction, background filtering, and object segmentation. The adaptable platform integrates with various ground vehicles and provides substantial data storage and processing capabilities needed for hardware-accelerated AI algorithms. SEEmear addresses the critical need for high-quality proximal sensing data in precision agriculture research, supporting applications in fruit detection, tracking, yield mapping, autonomous navigation, and field robotics.2025-01-01T00:00:00Z