A5071750441- Remote Sensing and LiDAR Applications
- Smart Agriculture and AI
- Remote Sensing in Agriculture
- Plant Surface Properties and Treatments
- Horticultural and Viticultural Research
- 3D Surveying and Cultural Heritage
- Advanced Optical Sensing Technologies
- Spectroscopy and Chemometric Analyses
- Leaf Properties and Growth Measurement
- Robotics and Sensor-Based Localization
- Particle Dynamics in Fluid Flows
- Atmospheric aerosols and clouds
- Data Mining Algorithms and Applications
- Insect Pheromone Research and Control
- Identification and Quantification in Food
- Atmospheric chemistry and aerosols
- Spectroscopy and Laser Applications
- Computational Physics and Python Applications
- Medical Imaging Techniques and Applications
- Semiconductor Lasers and Optical Devices
- Astronomy and Astrophysical Research
- Ocular and Laser Science Research
- Face and Expression Recognition
- Irrigation Practices and Water Management
- Machine Learning in Materials Science
Universitat de Lleida
2013-2023
Universitat Politècnica de Catalunya
2006-2012
In-field fruit monitoring at different growth stages provides important information for farmers. Recent advances have focused on the detection and location of fruits, although development accurate size estimation systems is still a challenge that requires further attention. This work proposes novel methodology automatic in-field apple which based four main steps: 1) detection; 2) point cloud generation using structure-from-motion (SfM) multi-view stereo (MVS); 3) estimation; 4) visibility...
The detection and sizing of fruits with computer vision methods is interest because it provides relevant information to improve the management orchard farming. However, presence partially occluded limits performance existing methods, making reliable fruit a challenging task. While previous segmentation works limit visible region (known as modal segmentation), in this work we propose an amodal algorithm predict complete shape, which includes its regions. To do so, end-to-end convolutional...
The measurement of fruit size is great interest to estimate the yield and predict harvest resources in advance. This work proposes a novel technique for in-field apple detection based on Deep Neural Networks. proposed framework was trained with RGB-D data consists an end-to-end multitask Network architecture specifically designed perform following tasks: 1) segmentation each from its surroundings; 2) estimation diameter detected fruit. methodology tested total 15,335 annotated apples at...
In this work, a LIDAR-based 3D Dynamic Measurement System is presented and evaluated for the geometric characterization of tree crops. Using measurement system, trees were scanned from two opposing sides to obtain three-dimensional point clouds. After registration clouds, simple easily obtainable parameter number impacts received by vegetation. The work in study based on hypothesis existence linear relationship between LIDAR sensor laser beam vegetation leaf area. Tests performed under...
The measurement of geometric canopy parameters in woody crops is an important task Precision Agriculture because their correlation with crop condition and productivity. In recent years, several technological approaches have been developed as alternative to manual measurements, which are time- labour-consuming. Two the most commonly used 3D characterization technologies mobile terrestrial laser scanning (MTLS) based on light detection ranging (LiDAR) sensors, digital aerial photogrammetry...
A 6-channel dichroic-based polychromator is presented as the spectrally selective unit for U.P.C. elastic/Raman lidar. Light emission made at 355-nm (ultraviolet, UV), 532-nm (visible, VIS) and 1064-nm (near infrared, NIR) wavelengths. In reception, spectral separation that separates laser backscattered composite return into 3 elastic (355, 532, wavelengths) Raman channels (386.7, 607.4 407.5-nm (water-vapor) wavelengths). The houses photo-multiplier tubes (PMT) all except NIR one, which...
Mobile terrestrial laser scanners (MTLS), based on light detection and ranging sensors, are used worldwide in agricultural applications. MTLS applied to characterize the geometry structure of plants crops for technical scientific purposes. Although exhibit outstanding performance, their high cost is still a drawback most This paper presents low-cost alternative combination Kinect v2 depth sensor real time kinematic global navigation satellite system (GNSS) with extended color information...
The present dataset contains colour images acquired in a commercial Fuji apple orchard (
Characterizing crop canopies is especially important in the management of woody crops. In this article, two systems were compared to characterise a 50 m long vineyard row section. One was mobile terrestrial laser scanner based on light detection and ranging (LiDAR) sensor (MTLS-LiDAR). The other an uncrewed aerial vehicle (UAV) system using digital photogrammetry (UAV-DAP). resulting 3D point clouds assessed qualitatively quantitatively. Canopy heights, widths volumes obtained 0.1 sections...
This paper proposes a novel control for voltage source inverters connected to the grid. The scheme is based on droop method, and it uses some estimated variables from grid such as frequency, magnitude angle of impedance. Hence, inverter able inject independently active reactive power controller provides proper dynamics decoupled Simulation results are provided in order show feasibility proposed.
The geometric characterisation of tree orchards is a high-precision activity comprising the accurate measurement and knowledge geometry structure trees. Different types sensors can be used to perform this characterisation. In work terrestrial LIDAR sensor (SICK LMS200) whose emission source was 905-nm pulsed laser diode used. Given known dimensions beam cross-section (with diameters ranging from 12 mm at point 47.2 distance 8 m), elements that make up crops under study (flowers, leaves,...
This article contains data related to the research entitle "Multi-modal Deep Learning for Fruit Detection Using RGB-D Cameras and their Radiometric Capabilities" [1]. The development of reliable fruit detection localization systems is essential future sustainable agronomic management high-value crops. sensors have shown potential since they provide 3D information with color data. However, lack substantial datasets a barrier exploiting use these sensors. presents KFuji RGB-DS database which...
The use of 3D sensors combined with appropriate data processing and analysis has provided tools to optimise agricultural management through the application precision agriculture. recent development low-cost RGB-Depth cameras presented an opportunity introduce into community. However, due sensitivity these highly illuminated environments, it is necessary know under which conditions RGB-D are capable operating. This work presents a methodology evaluate performance different lighting distance...