Project

UAS-based crop monitoring

Goal: Assessment of open field crop features based on low altitude imagery collected with UAS systems. Several approaches are addressed, such as: lodging, yield mapping, biomass and others.

Date: 17 February 2015

Updates
0 new
0
Recommendations
0 new
0
Followers
0 new
3
Reads
0 new
9

Project log

Juan Quirós
added a research item
Rapid and accurate canopy attributes estimation is highly critical in fruit crops production management. Such information can be used for canopy and crop load management as well as to develop nutrient/chemical prescription application maps. However, the existing ground based canopy sensing and attribute estimation methods are laborious and often involve complexity with field data collection and analysis. Manual methods can be subjective as well. Therefore, this study explores aerial photogrammetry based method of tree–row–volume (TRV), leaf–wall–area (LWA), canopy volume (CV) and canopy cover (CC) estimation for grapevine and apple canopies. The study used remote sensing data collected using a consumer–grade small unmanned aerial system (UAS) with an RGB imaging sensor flying at different flight altitudes i.e., 15 m (Ground sampling distance, GSD = 0.45 cm pixel⁻¹ at 65° sensor inclination), 30 m (0.90 and 0.85 cm pixel⁻¹ at 65°and 75°, respectively), 45 m (1.35 and 1.27 cm pixel⁻¹ at 65°and 75°, respectively) and 60 m (1.81 and 1.69 cm pixel⁻¹ at 65°and 75°, respectively). Crop surface model (CSM) was derived from such data to estimate canopy height, width and foliage vigor, which are further used to estimate TRV, LWA, CV and CC. The ground measured and aerial imagery estimated TRV had a strong relationship with the data collected at the lowest GSD within grapevine canopies (R² = 0.77 at 0.45 cm pixel⁻¹) as well as for apple canopies (R² = 0.82 at 0.90 cm pixel⁻¹). Similar trends were observed for the LWA (R² = 0.77 and 0.86), CV (R² = 0.43 and 0.64) and CC (R² = 0.61 and 0.68) estimates for grapevine and apple canopies, respectively. Increasing GSD (≥ 0.45 cm pixel⁻¹ in grapevine and ≥ 0.90 cm pixel⁻¹ in apple) resulted in a weak relationship between ground measurements and aerial imagery data-based estimates for grapevines (R² ≤ 0.36) and apple canopies (R² = 0.39–0.78). Overall, the aerial flights with lower GSD and double grid missions with RGB imaging sensor in 65° orientation aids in the development of field site–specific high–quality canopy vigor maps that can be used in precision crop inputs management related decision making.
Juan Quirós
added 5 research items
RESUMO: Se estudió la Conductividad Eléctrica Aparente (CEa) como indicador de la variabilidad de un suelo cultivado con arroz (Oryza sativa), en condiciones tropicales. Antes de medir la CEa en todo el terreno, se realizó un análisis de semivarianza en una parcela de 2500 m 2 para determinar la mínima densidad que se debería colectar en el muestreo final, en el cual se tomaron 10 datos de CEa por hectárea. Los datos fueron colectados con un equipo Landmapper ERM-02. Se identificaron tres puntos representativos de zonas homogéneas del terreno, en los cuales se realizaron observaciones de campo y se tomaron muestras a 30 y 60 cm de profundidad para su respectivo análisis en laboratorio. Se analizaron propiedades tanto químicas como físicas, y los resultados se correlacionaron con los valores de CEa, de tal manera que aquellas variables que muestren alta correlación serían las que determinan la heterogeneidad del suelo. En este caso las variables que correlacionaron con la CEa, y por tanto las variables que definen la heterogeneidad del terreno, fueron el contenido de Mg, la CEe, la profundidad del horizonte C, el contenido de limos y arenas y el contenido de MO. PALAVRAS-CHAVE: Mapeo de suelos, conductividad eléctrica aparente, zonas homogéneas. APPARENT ELECTRICAL CONDUCTIVITY (ECa) AS INDICATOR OF VARIABILITY IN A SOIL CULTIVATED WITH PADDY UNDER TROPICAL CONDITIONS ABSTRACT: Apparent Electrical Conductivity (ECa) was analyzed as an indicator of variability in a soil cultivated with paddy (Oryza sativa) in tropical conditions. Before measuring ECa in the complete area, an analysis of semivariance was performed in a plot of 2500 m 2 , in order to determine the minimum number of samples per hectare that should be collected in the final sampling, for which 10 measurements of ECa per hectare were taken. Data were collected with a Landmapper ERM-02 system. Three representative points of homogeneous areas of low, medium and high ECa were identified; on each point field observations were made, and soil samples were taken at 30 and 60 cm depth for its laboratory analysis. Both, physical and chemical properties were evaluated and the results were correlated with ECa values, such that the variables showing high correlation, would determine soil heterogeneity. In this case, the variables correlating with ECa, therefore the variables defining field heterogeneity, were Mg content, the ECe, depth of horizon C, silt, sand, and OM content. INTRODUÇÃO: Conocer y manejar la variabilidad de un terreno es fundamental para obtener aumentos de productividad. Por lo general, el método utilizado para determinar esa variabilidad se basa en intensos muestreos de suelo que conllevan altos costos (Pozdenyakova, 1999). Además, estos estudios no suelen ser precisos debido a que una muestra debe representar una grande área, con lo que métodos de interpolación para generar mapa presentan mayor error. La medición de la CEa es determinada por un impulso eléctrico enviado a través del suelo, que sigue tres vías: [1] la Conductividad Eléctrica (CE) de una vía que pasa de la fase líquida a la sólida de manera intermitente, [2] la CE de la fase líquida del suelo, y [3] la CE de sus partículas sólidas (Corwin y Lesch, 2005). Muchos estudios han demostrado que mapeos de CEa reproducen la heterogeneidad del terreno de una manera práctica, y con bajo costo y buena precisión (Tabbagh y Cosenza, 2007). Los mapas de CEa permiten identificar
In recent years, growers in the state are transitioning to new high yielding, pest and disease resistant cultivars. Such transition has created high demand for new tree fruit cultivars. Nursery growers have committed their incoming production of the next few years to meet such high demands. Though an opportunity, tree fruit nursery growers must grow and keep the pre-sold quantity of plants to supply the amount promised to the customers. Moreover, to keep the production economical amidst rising labor shortages, the nursery growers are looking at incorporating technological advances on the horizon. Also to insure the young nursery seedlings from adverse winter weather, growers need to accurately know the tree inventory grown in the actual field environment. Therefore, objective of this study was to develop and validate robust field grown apple nursery plant counting algorithm that is based only on elevation pixel values of small Unmanned Aerial System (UAS) based low altitude RGB imagery data. The nursery field images were obtained using small UAS operated at 30 m above the ground level. Image processing was performed in a Geographic Information System (GIS) software, where the pipeline was defined focusing on the isolation of apple plants based on thresholds of pixel height in circular regions along the crop line. In the first step the Digital Elevation Model (DEM) was processed in order to extract the Digital Terrain Model (DTM); the height of the plants was estimated according to the Crop Surface Model (CSM), which is the difference between the DEM and DTM. In the second step, the center lines of crop rows were extracted. As a third step, inside each row line generated were the points with a fixed spacing of 25 cm and buffered circular regions with a diameter of 50 cm. Those buffer areas were classified aiming following the logistic that "only the circles with maximum height higher than 23 cm can be counted as plants". The proposed methodology presented satisfactory results, reaching an estimation with an accuracy of 95%.
Aerial imaging based plant counting is a widely studied topic in remote sensing. Nevertheless, existing methodologies are not applicable for in-field nurseries tree counting due to the complexity in canopy shapes, irregular plant spacing and growth, and diverse textures captured on the images. In this study, a new algorithm has been developed in accordance to the specific requirements of apple nurseries images. Algorithm composed of two key steps, i.e. a raster processing followed by a vector analyses. First step attempt to isolate apple plant pixels using spatial, spectral, and radiometric enhancements. In vector processing, filters based on the size and location of the polygons were applied to isolate the areas resulting from earlier step to represent apple plants. Algorithm was evaluated to estimate number of apple trees in an young nursery imaged with low altitude multispectral imaging system at four altitudes of 10, 25, 40, and 50 m. Multispectral imaging sensor consisted of near-infrared (NIR), green and blue as three bands. For 10- and 25-m images, algorithm performance was evaluated in individual as well as in mosaic images. Low altitude images with ≤ 25 m above ground level were ideally suited for young apple nursery tree count with 5% or less estimation error. Tree count accuracy was 97% and 95% for 10-m altitude individual and mosaic images, respectively. Similarly, those values were 92% and 88% for 25-m altitude images. Based on the results, images at 40 m are recommended only when the methodology include four extra steps added to the base algorithm to have tree count accuracies of about 88%. Images at 50 m are not recommended in any case due to the low accuracy obtained (~ 75%). Overall, the low altitude multispectral imaging integrated with image processing algorithm developed in this study will aid nursery growers in low-cost and timely tree count needed for inventory mapping and management.
Juan Quirós
added a project goal
Assessment of open field crop features based on low altitude imagery collected with UAS systems. Several approaches are addressed, such as: lodging, yield mapping, biomass and others.