Daniel Marçal de Queiroz

Fall Armyworm Damaged Maize Plant Identification using Digital Images

Abstract The objectives of precision agriculture are profit maximisation, agricultural input rationalisation and environmental damage reduction, by adjusting the agricultural practices to the site demands. The fall armyworm ( Spodoptera frugiperda ) is one of the most important maize pests in Brazil and the use of insecticide is the main control method. It is believed that site-specific control can be implemented by using a machine vision system. The objective of this work was to develop and evaluate an algorithm at simplified lighting conditions for identifying damaged maize plants by the fall armyworm using digital colour images. Images of damaged and non-damaged maize plants were taken in eight different stages and in three different light intensities. The proposed algorithm had two stages: the processing and the image analysis. During the first stage, the images were processed to create binary images where the leaves were segmented from the other pixels. At the second stage, the images were subdivided into blocks and classified as ‘damaged’ or ‘non-damaged’ depending on the number of objects found in each block. The algorithm correctly classified 94·72% of 720 images.

An Automatic Data Acquisition and Control Mobile Laboratory Network for Crop Production Systems Data Management and Spatial Variability Studies in the Brazilian Center-West Region

This paper describes all tools and procedures used to structure and implement an automatic data acquisition and control mobile laboratory network for crop production systems data management and spatial variability studies in the Brazilian Center-West Region. It was set up with base in remote sensing and microprocessor techniques, microelectronic devices, sensors, controls, sampling systems, data loggers, portable microcomputers, automatic data acquisition, RF communications link, and the global positioning system (GPS), allowing for the acquisition of spatially related data during tilling, planting, and harvesting. Physical chemistries and biological characteristics of the continuous soil-water-plant-atmosphere were monitored along of the crop growth period, at field conditions, seeking the rationalization of the agricultural inputs use and the performance improvement of agricultural systems. Some results are presented.

Variabilidade espacial de atributos do solo em sistema de semeadura direta com rotação de culturas no cerrado brasileiro

This study aimed to analyze the spatial variability of the chemical attributes and texture of a red latosol. The study was carried out on a property in the town of Sidrolândia, Matto Grosso do Sul, which produces soybeans, corn and cotton, using crop rotation and a no-tillage system. In an experimental area of approximately 90 hectares, samples were taken of the soil at 181 geo-referenced points. The samples were each composed of four single samples, representing depths of from 0 to 0.2 m. The chemical and texture of the soil were measured. Initially a discrepancy analysis was performed followed by descriptive and geostatistical analyses, to characterize the samples and identify the spatial dependence of the attributes studied. No spatial dependence was detected for the attributes: active water acidity, aluminum, potential acidity, base saturation and organic matter. The best estimates of values for non-sampled locations were observed for the physical properties of the soil, which presented parameters which best fit the variograms and cross-validation. The geostatistical techniques used allowed adjustment of the theoretical models that best represented the experimental semivariance, thus enabling the construction of thematic maps of spatial distribution for the values of the attributes of the studied soil.

Definition of management zones in coffee production fields based on apparent soil electrical conductivity

Fertilizer application at variable rates requires dense sampling to determine the resulting field spatial variability. Defining management zones is a technique that facilitates the variable-rate application of agricultural inputs. The apparent electrical conductivity of the soil is an important factor in explaining the variability of soil physical-chemical properties. Thus, the objective of this study was to define management zones for coffee (Coffea Arabica L.) production fields based on spatial variability of the apparent electrical conductivity of the soil. The resistivity method was used to measure the apparent soil electrical conductivity. Soil samples were collected to measure the chemical and physical soil properties. The maps of spatial variability were generated using ordinary kriging method. The fuzzy k-means algorithm was used to delimit the management zones. To analyze the agreement between the management zones and the soil properties, the kappa coefficients were calculated. The best results were obtained for the management zones defined using the apparent electrical conductivity of the soil and the digital elevation model. In this case, the kappa coefficient was 0.45 for potassium, which is an element that is associated with quality coffee. The other variable that had a high kappa coefficient was remaining phosphorous; the coefficient obtained was 0.49. The remaining phosphorus is an important parameter for determining which fertilizers and soil types to study.

The relationship between apparent soil electrical conductivity and soil properties

Precision agriculture that is based on the physical and chemical properties of soil requires a dense sampling to evaluate spatial variability in the field. This dense sampling is often expensive and time consuming. One technique to reduce the number of samples is to define management zones based on information that is collected in the field. Some researchers have demonstrated the importance of the electrical properties of soil in defining management zones. Thus, the objective of this study was to evaluate the relationship between the apparent soil electrical conductivity and soil properties in mountainous areas of coffee production. The electrical conductivity of soil was evaluated at soil depths ranging from 0.00-0.20 m (EC20) and 0.00-0.40 m (EC40) using a portable meter. The mean values of EC20 and EC40 were 1.80 mS m-1 and 1.22 mS m-1, respectively. Both EC20 and EC40 exhibited comparatively low correlations with the soil properties, whereas higher correlations were obtained for measurements of remaining phosphorus, wherein values of 0.427 and 0.465, respectively, were obtained.

Geração de zonas de manejo para cafeicultura empregando-se sensor SPAD e análise foliar

The objective of this work was to define management zones for fertilizer application in coffee crop by using the K-means and the Fuzzy C-Means methods. The data used to define management zones were the chlorophyll index measured by SPAD sensor and the nutritional coffee leaf analysis performed in laboratory. The study was conducted in Jatoba Farm, located in Paula Candido, Minas Gerais state, Brazil. The data was collected in November, 2007 when the coffee fruits were starting their development. The coffee variety was Coffea arabica Catuai, and the total analyzed area was 2.1 ha. The management zones were generated using different set of data: the SPAD values; the N, P and K leaf concentrations; the N and Ca leaf concentrations; the N, Zn and B leaf concentrations; the N, P, K, Ca and S leaf concentrations; and the N, Ca and S leaf concentrations. The management zones generated by using K-means and Fuzzy C-Means did not present difference in management zone delimitation. The management zones defined by using the SPAD values were different from the ones generated by using leaf analysis.

Desenvolvimento e avaliação do desempenho de uma semeadora puncionadora para plantio direto de milho

The present work was accomplished to develop a punch planter to sow corn seeds in no-tillage system, and also to evaluate the performance of its seed metering and delivery systems. First of all, a requirement list was established, that the machine would have to attend. Next, the conceptual and the embodiment designs of the machine was made. Then, the detailed design of all machine parts was made and a prototype was constructed. In a testing bench the performance of the seed metering unit and its seed delivery system was assessed in relation to the punch wheel speed and the quantity of punches on the wheel. The statistical design was in random blocks arranged in sub-divided plots with the main plot made of 6, 9 and 12 punches and the sub-plot made of four rotational speeds of the punch wheel, corresponding to the travel speeds of 4, 6, 8 and 10 km h-1. Generally, the increase in velocity and the increase in the number of punches in the punch wheel decreased the number of doubles and increased the number of missing seeds; however the decrease in number of doubles was not significant compared to the increase in the number of errors. The punch planter had a satisfactory performance, with a global mean of 91% for normal seed selection and delivery.

Efeito da frequência e amplitude de vibração sobre a derriça de frutos de café

Quality parameters influence directly the coffee price. However, selective coffee harvesting is frequently associated to good quality of this product. This procedure can be performed by mechanical vibration. Therefore, the study of the frequency and amplitude parameters is important for the design of a specific harvesting machine. The objective of this work was to evaluate the effect of the frequency and amplitude of vibration, the coffee variety and the ripeness condition of the fruits upon the harvesting efficiency. The vibration tests were done in laboratory using an electromagnetic shaker. The tests were done using amplitudes in the range of 3.75 to 7.50 mm and frequencies in the range of 13.33 to 16.67 Hz. Branches of coffee plants of Mundo Novo variety were tested. The highest harvesting efficiency was obtained when using the 26.67 Hz frequency of vibration. The highest harvesting efficiency was obtained when an amplitude of 7.5 mm was used. It was also observed that the number of fruits per stem influences the harvesting efficiency of the coffee fruits of the Mundo Novo variety.

Derriçadora portátil na colheita total e seletiva de frutos do cafeeiro

The objective of this work was to evaluate the performance of a portable coffee harvester to mountain areas. Two procedures were tested: harvesting all fruits in only one operation, and the selective harvesting. Coffee yield, harvesting capacity, index of leaves taken during harvesting process, harvesting efficiency, noise level and fuel consumption were measured. The harvesting system with two portable harvester presented better performance than with only one machine. Selective harvesting was highly influenced by the percentage of ripen fruits and by coffee yield.

Avaliação de perdas em uma colhedora de fluxo axial para feijão

The evaluation performance of a harvester should include the energy needed for its operation, the harvesting capacity and the quantitative loss in the process. The objective of this work was to evaluate the performance of a bean harvester. Field tests were done in different operational conditions. Based on the collected data, it was concluded that the harvester header causes the greatest quantitative loss, responsible for 49.30% of the total loss. In the separation and cleaning systems the losses were 43.61 and 7.09%, respectively. The maximum harvesting capacity of the machine was 6.56 t h-1 of grains.