Proceedings
Authors
| Filter results11 paper(s) found. |
|---|
1. Characterizing Cross-Crop Stink Bug Spectral Signatures from Hyperspectral DataEffective crop protection in agricultural production systems requires the ability to detect pest-induced stress in a timely and reliable manner. In large-scale farming systems, stink bugs attack multiple crop species, making cross-crop pest detection a critical capability for scalable monitoring solutions. Rather than developing crop-specific models that require retraining for each species, identifying crop-independent spectral signatures of stink bug infestation enables transferable detection... A.O. Françani, L. Zhao, J. Ferreira , J. Yan, E.J. Ferreira, L.A. Jorge |
2. Stability-driven Framework for Robust Plant Spectral Signature IdentificationAccurate identification of agricultural crops based on spectral signatures remains a critical challenge for large-scale phytosanitary monitoring. This study proposes a stability-based structure for the robust identification of plant spectral signatures, applied to the discrimination of soybean (Glycine max) from maize (Zea mays) and cotton (Gossypium hirsutum) under biotic stress caused by the pest Spodoptera frugiperda and stink bugs. The proposed method follows a flow of proposed steps that... J. Ferreira , A.O. Françani, E. . Ferreira, L.A. Jorge, J.C. Felipe, L. Zhao |
3. A Hybrid Non-Destructive Approach Combining Image Processing and Spectral Feature Selection for Grapevine Leaf Water Content EstimationReliable and continuous estimation of leaf water content (LWC) is essential for viticulture, as it enables assessment of spatiotemporal variability in vine water demand and supports improved irrigation management efficiency within Precision Agriculture (PA) practices. Although the gravimetric method based on fresh weight (FW) and dry weight (DW) measurements provides accurate LWC estimates, it is time-consuming, destructive, and exhibits limited scalability for large sample sizes. In contrast,... L.H. Bassoi, B.S. Costa, E.J. Ferreira, H. Oldoni, L.A. Jorge |
4. Proximal and suborbital vegetation indices in yield prediction of ‘Syrah’ grapevinesThe various vegetation indices (VIs) reported in the literature, derived from different wavelengths, necessitate identifying the most suitable spectral combinations to represent agronomic variables in precision viticulture. This study evaluated the performance of proximal and suborbital VIs to explain the spatial variability of yield of the ‘Syrah’ grapevine. The study was conducted in a trellised vineyard under double pruning management in Ribeirão Preto, state of São... L.H. Bassoi, L.A. Jorge, A. Pereira, I. Oliveira Junior |
5. Consistency of Three Vegetation Indices from Suborbital and Proximal Sensing in Precision ViticultureThe integration of proximal and suborbital sensing platforms can expand the practice of precision viticulture. However, the consistency of vegetation indices (VIs) derived from different sensors remains a critical issue. This study quantified the agreement between VIs obtained by proximal and suborbital sensing using complementary metrics of association, error, and agreement. The research was conducted in a ‘Syrah’ vineyard in Ribeirão Preto, state of São Paulo, Brazil,... L.H. Bassoi, L.A. Jorge, A. Pereira, I. Oliveira Junior |
6. Early Detection of Soybean Pest Infestations Using Leaf-Level Reflectance Spectroradiometry and Machine LearningThe agricultural sector plays a central role in sustaining global food production, energy supply, and economic development. However, population growth, climate change, resource scarcity, and increasing sustainability demands have intensified production challenges. Pest and disease outbreaks are major contributors to crop losses worldwide, underscoring the urgent need for reliable methods capable of enabling early detection and timely intervention. In this context, leaf-level spectroradiometry... M. Lima, J.C. Felipe, E.J. Ferreira, L.A. Jorge, L. Zhao |
7. Enhancing Pest Detection Through Spectral Signature Extraction in Hyperspectral DataDetecting insect infestation is essential for effective crop protection, particularly in large-scale systems. Caterpillars and stink bugs induce physiological and structural alterations in plant tissues that can be captured through hyperspectral reflectance sensing, which is a non-destructive technique that measures plant responses across hundreds of wavelengths. However, raw spectral signatures are characterized by high dimensionality, strong inter-band correlation, and they often exhibit baseline... A.O. Françani, J. Ferreira , L. Zhao, L.A. Jorge, K.M. De Oliveira, J.C. Felipe |
8. Weed mapping: advantages of RGB CNN-based approaches vs multispectral pixel-based methodsWeed detection remains a major challenge in modern agriculture, and accurate weed mapping is crucial to support rapid and efficient management interventions, ensuring crop productivity and economic viability. In this context, geotechnologies such as remote sensing and computer vision, together with the widespread adoption of drones, enable the acquisition of ultra–high spatial resolution imagery, allowing more detailed analyses in complex agricultural environments. Although multispectral... |
9. Integration of LiDAR-Derived TWI and UAV Multispectral Data for Waterlogging Susceptibility Mapping in Precision AgricultureTopography directly controls water redistribution across the landscape, shaping the spatial variability of soil moisture in agricultural areas. The Topographic Wetness Index (TWI), derived from digital elevation models, is widely used to estimate the potential for water accumulation; however, its field-scale validation supported by high-resolution multispectral drone imagery remains limited. In agricultural systems, recurrent waterlogging can reduce productivity by impairing germination, promoting... |
10. Comparative Evaluation of Ground Point Classifiers in LiDAR Point Clouds for DEM Generation in Pasture AreasThe classification of ground points in LiDAR point clouds is an essential step for generating reliable Digital Terrain Models (DTMs), particularly in livestock production systems based on pastures. Despite methodological advances in forested and urban environments, studies specifically addressing ground classification in pasture areas remain limited, where the proximity between the forage canopy and the ground surface makes altimetric distinction between classes challenging. The heterogeneous... |
11. YOLOv10x-based deep learning for automated detection and counting of seeds per soybean podAccurate quantification of the number of seeds per soybean pod is a fundamental step for reliable yield estimation. However, this measurement still relies on manual procedures, which are subject to observational variability and limited scalability. In the context of digital agriculture, deep learning–based techniques have shown promise for automating the detection and counting of reproductive structures. Nevertheless, there is still limited application of models specifically aimed... |