A5048350189- Smart Agriculture and AI
- Remote Sensing and LiDAR Applications
- Remote Sensing in Agriculture
- Leaf Properties and Growth Measurement
- Sugarcane Cultivation and Processing
- Image Retrieval and Classification Techniques
- Greenhouse Technology and Climate Control
- COVID-19 diagnosis using AI
- Plant and animal studies
- Land Use and Ecosystem Services
- Spectroscopy and Chemometric Analyses
- Data Management and Algorithms
- Advanced Image and Video Retrieval Techniques
- Vehicle License Plate Recognition
- Image and Object Detection Techniques
- Handwritten Text Recognition Techniques
- Landslides and related hazards
- Visual Attention and Saliency Detection
- Image Processing Techniques and Applications
Universidade Federal de Jataí
2022
Universidade Federal de Goiás
2019-2022
Universidade Estadual de Campinas (UNICAMP)
2020
Universidade Federal de Uberlândia
2014-2017
Sugarcane planting is an important and growing activity in Brazil. Thereupon, several techniques have been developed over the years to maximize crop productivity profit, amongst them, processing of sugarcane field images. In this sense, research aims identify analyze rows measure their gaps from aerial images fields. For this, a small Remotely Piloted Aircraft captured images, generating orthomosaics areas for analysis. Then, each orthomosaic classified with K-Nearest Neighbor algorithm...
Leveraged by the production of grains, oilseeds, and fresh deciduous fruits, food has reached new heights, exceeding amount produced in previous years with an estimate records for coming years. In this sense, technological advances are essential to reduce costs increase quality productivity. paper, we present a novel method detect insect predation on plant leaves that uses geometric leaf properties digital image processing techniques construct models. Unlike other approaches, our detects...
Estimating foliar damage is essential in agricultural processes to provide proper crop management, such as monitoring the defoliation level take preventive actions. Furthermore, it helpful avoid reduction of plant energy production, nutrition decrement, and consequently, final production economic losses. In this sense, numerous proposals support estimate task, ranging from traditional methodologies computational solutions. However, subjectivity characteristics, reproducibility limitations,...
In this study, we explore some possibilities of using aerial images captured by Unmanned Aerial Vehicles (UAV) and discuss the benefits them in context intelligent agriculture. A novel method that supports detection segmentation tree crowns, delineation shadows, which shows direction sunlight is presented. It uses simple observation strategies commonly used digital image processing techniques such as visual color enhancement perception, morphological operations, based on a region growing...
Sugarcane is one of the main crops in world due to its economic value promoted by sale derivatives, such as bioethanol and sugar. In order achieve greater performance productivity sugarcane field, several digital image processing studies have been conducted on field images. However, mapping measuring gaps planting rows are still being performed manually on-site determine whether replant entire area or only gaps. High cost time manpower required perform manual measurement. Based that, aim...
Tuberculosis is a severe and contagious lung dis-ease that kills about 1.5 million people worldwide. One of the ways to combat this disease by tracking, detecting, iso-lating infected. In sense, chest radiography (CXR) an effective alternative for task, given its high availability, low charge, quick response. Thus, considering importance topic, our work proposal machine learning method tuberculosis detection in CRXs. Our combines local binary patterns (LBP) feature extraction selection...
Sugarcane is one of the main crops in world due to economic value it promotes by selling its derivatives. A diversity technologies has been developed optimize agricultural activities and maximize productivity sugarcane crops. In this sense, our primary goal contribute research area detecting planting lines measuring their faults, including evaluation curved that substantially limit numerous solutions practical applications. An automatic method identifies measures through digital image...
The focus of this work is on the use Generalized I-Divergence (GID) applied to content-based image retrieval from a real scenes database using Bag-of-Visual-Words (BoVW) in three different approaches: BoVW, BoVW with Binary Saliency Map (BSM) and Fuzzy Image (FISM). approach has shown promising performance within context retrieval, where general, similarity between two images typically measured by distance histograms cosine measure. In we Divergence measures rank similar instead measure aim...
In high-dimensional spaces, a near neighbor search (NNS) has high computational cost, which motivated research toward the development of methods based on data structures. These structures open possibility that only one part set needs to be examined, thus decreasing cost. The NNS are in their greater metric properties adopted similarity measure. However, there exist real applications involve, for example, comparison probabilities, images, among others, and adequate notion cannot defined by...
The use of unmanned aerial vehicles (UAV) is expanding rapidly throughout the world. Nowadays, it common to find some useful applications that them in both urban and rural environments. Especially second case, UAV promoting significant changes traditional agricultural activities. Thus, current technologies have been incorporated into inspection, surveillance, management. In this study, we investigated practical uses images areas. A new method for allowing a understand interpret visual...
Management of agricultural production and rural activities has been supported by recognizing machine learning patterns algorithms, as in the automation leaf analysis. However, border damage compromises structures, making it difficult to estimate lost contours. Effects caused predatory insects are be monitored inspection processes, harmful results them can deteriorate performance models. In this sense, plant leaves that not fresh or intact avoided. Consequently, number samples for use...