Crop row detection in maize fields inspired on the human visual perception

This paper proposes a new method, oriented to image real-time processing, for identifying crop rows in maize fields in the images. The vision system is designed to be installed onboard a mobile agricultural vehicle, that is, submitted to gyros, vibrations, and undesired movements. The images are captured under image perspective, being affected by the above undesired effects. The image processing consists of two main processes: image segmentation and crop row detection. The first one applies a threshold to separate green plants or pixels (crops and weeds) from the rest (soil, stones, and others). It is based on a fuzzy clustering process, which allows obtaining the threshold to be applied during the normal operation process. The crop row detection applies a method based on image perspective projection that searches for maximum accumulation of segmented green pixels along straight alignments. They determine the expected crop lines in the images. The method is robust enough to work under the above-mentioned undesired effects. It is favorably compared against the well-tested Hough transformation for line detection.

Automatic expert system based on images for accuracy crop row detection in maize fields

This paper proposes an automatic expert system for accuracy crop row detection in maize fields based on images acquired from a vision system. Different applications in maize, particularly those based on site specific treatments, require the identification of the crop rows. The vision system is designed with a defined geometry and installed onboard a mobile agricultural vehicle, i.e. submitted to vibrations, gyros or uncontrolled movements. Crop rows can be estimated by applying geometrical parameters under image perspective projection. Because of the above undesired effects, most often, the estimation results inaccurate as compared to the real crop rows. The proposed expert system exploits the human knowledge which is mapped into two modules based on image processing techniques. The first one is intended for separating green plants (crops and weeds) from the rest (soil, stones and others). The second one is based on the system geometry where the expected crop lines are mapped onto the image and then a correction is applied through the well-tested and robust Theil–Sen estimator in order to adjust them to the real ones. Its performance is favorably compared against the classical Pearson product–moment correlation coefficient.

Trickle irrigation: effects on papaya crop

The objective of this study was to evaluate growth and yield of papaya cv. Sunrise solo under trickle irrigation system configurations. A random block design was used with six treatments and four replications. Treatments were: T1- a 32 L h-1 micro sprinkler; T2 - a 43 L h-1 micro sprinkler and T3 - a 60 L h-1 micro sprinkler for four plants; T4 - Drip system with four emitters per plant on one lateral line per crop row; T5 - Drip system with eight emitters per plant on two laterals line per crop row; T6 - Drip system with four emitters per plant on one lateral line distributed as pig tail. The dripper flow rate was 4 L h-1and they were apart each other 0.50 m. Crop growth variables were measured every two weeks. Production variables were evaluated during harvest. The treatment that presented superiority was irrigated by micro sprinkler system with flow rate of 43 L h-1.

Real-time image processing for crop/weed discrimination in maize fields

This paper presents a computer vision system that successfully discriminates between weed patches and crop rows under uncontrolled lighting in real-time. The system consists of two independent subsystems, a fast image processing delivering results in real-time (Fast Image Processing, FIP), and a slower and more accurate processing (Robust Crop Row Detection, RCRD) that is used to correct the first subsystem's mistakes. This combination produces a system that achieves very good results under a wide variety of conditions. Tested on several maize videos taken of different fields and during different years, the system successfully detects an average of 95% of weeds and 80% of crops under different illumination, soil humidity and weed/crop growth conditions. Moreover, the system has been shown to produce acceptable results even under very difficult conditions, such as in the presence of dramatic sowing errors or abrupt camera movements. The computer vision system has been developed for integration into a treatment system because the ideal setup for any weed sprayer system would include a tool that could provide information on the weeds and crops present at each point in real-time, while the tractor mounting the spraying bar is moving

Automatic detection of crop rows in maize fields with high weeds pressure

This paper proposes a new method, oriented to crop row detection in images from maize fields with high weed pressure. The vision system is designed to be installed onboard a mobile agricultural vehicle, i.e. submitted to gyros, vibrations and undesired movements. The images are captured under image perspective, being affected by the above undesired effects. The image processing consists of three main processes: image segmentation, double thresholding, based on the Otsu’s method, and crop row detection. Image segmentation is based on the application of a vegetation index, the double thresholding achieves the separation between weeds and crops and the crop row detection applies least squares linear regression for line adjustment. Crop and weed separation becomes effective and the crop row detection can be favorably compared against the classical approach based on the Hough transform. Both gain effectiveness and accuracy thanks to the double thresholding that makes the main finding of the paper.

Aggregate stability by the "high energy moisture characteristic" method in an oxisol under differentiated management

Studies testing the High Energy Moisture Characteristic (HEMC) technique in tropical soils are still incipient. By this method, the effects of different management systems can be evaluated. This study investigated the aggregation state of an Oxisol under coffee with Brachiaria between crop rows and surface-applied gypsum rates using HEMC. Soil in an experimental area in the Upper São Francisco region, Minas Gerais, was studied at depths of 0.05 and 0.20 m in coffee rows. The treatments consisted of 0, 7, and 28 Mg ha-1 of agricultural gypsum rates distributed on the soil surface of the coffee rows, between which Brachiaria was grown and periodically cut, and compared with a treatment without Brachiaria between coffee rows and no gypsum application. To determine the aggregation state using the HEMC method, soil aggregates were placed in a Büchner funnel (500 mL) and wetted using a peristaltic pump with a volumetric syringe. The wetting was applied increasingly at two pre-set speeds: slow (2 mm h-1) and fast (100 mm h-1). Once saturated, the aggregates were exposed to a gradually increasing tension by the displacement of a water column (varying from 0 to 30 cm) to obtain the moisture retention curve [M = f (Ψ) ], underlying the calculation of the stability parameters: modal suction, volume of drainable pores (VDP), stability index (slow and fast), VDP ratio, and stability ratio. The HEMC method conferred sensitivity in quantifying the aggregate stability parameters, and independent of whether gypsum was used, the soil managed with Brachiaria between the coffee rows, with regular cuts discharged in the crop row direction, exhibited a decreased susceptibility to disaggregation.

Sampling Position under No-Tillage System Affects the Results of Soil Physical Properties

ABSTRACT Understanding the spatial behavior of soil physical properties under no-tillage system (NT) is required for the adoption and maintenance of a sustainable soil management system. The aims of this study were to quantify soil bulk density (BD), porosity in the soil macropore domain (PORp) and in the soil matrix domain (PORm), air capacity in the soil matrix (ACm), field capacity (FC), and soil water storage capacity (FC/TP) in the row (R), interrow (IR), and intermediate position between R and IR (designated IP) in the 0.0-0.10 and 0.10-0.20 m soil layers under NT; and to verify if these soil properties have systematic variation in sampling positions related to rows and interrows of corn. Soil sampling was carried out in transect perpendicular to the corn rows in which 40 sampling points were selected at each position (R, IR, IP) and in each soil layer, obtaining undisturbed samples to determine the aforementioned soil physical properties. The influence of sampling position on systematic variation of soil physical properties was evaluated by spectral analysis. In the 0.0-0.1 m layer, tilling the crop rows at the time of planting led to differences in BD, PORp, ACm, FC and FC/TP only in the R position. In the R position, the FC/TP ratio was considered close to ideal (0.66), indicating good water and air availability at this sampling position. The R position also showed BD values lower than the critical bulk density that restricts root growth, suggesting good soil physical conditions for seed germination and plant establishment. Spectral analysis indicated that there was systematic variation in soil physical properties evaluated in the 0.0-0.1 m layer, except for PORm. These results indicated that the soil physical properties evaluated in the 0.0-0.1 m layer were associated with soil position in the rows and interrows of corn. Thus, proper assessment of soil physical properties under NT must take into consideration the sampling positions and previous location of crop rows and interrows.

Eficiência e seletividade dos herbicidas trifloxysulfuron-sodium + ametryne e hexazinone + diuron em função da tecnologia de aplicação e do manejo mecânico da palha de cana-de-açúcar na linha de plantio

Com objetivo de otimizar a utilização de trifloxysulfuron-sodium + ametryne e hexazinone + diuron em função da adoção de diferentes pontas de pulverização e manejo mecânico da palha de cana-de-açúcar na linha de plantio, dois experimentos foram conduzidos na Destilaria Parálcool S/A, localizada em Paraguaçu Paulista/SP. No experimento 1, 12 tratamentos foram estudados em esquema fatorial 2 x 2 x 3, com quatro repetições, contrastando a presença e ausência de palha da cana na linha de plantio; dos herbicidas trifloxysulfuron sodium + ametryne (37 + 1.463 g i.a. ha-1 e 0,2% v/v de Aterbane®) e hexazinone + diuron (330 + 1.170 g i.a. ha-1 e 0,2% v/v de Aterbane®) e das pontas de pulverização XR11002-VS (128 L ha-1), AI11002-VS (200 L ha-1) e TF-VP5 (310 L ha-1). No experimento 2, a deposição da calda de pulverização nas plantas de cana-de-açúcar e Digitaria horizontalis, gerada pelas interações entre herbicidas e pontas, foi monitorada utilizando-se solução traçadora constituída por corante FDC-1 + herbicida. Os resultados sugerem que a presença da palhada da cultura proporcionou controle excelente das espécies infestantes mesmo na ausência do tratamento herbicida. O controle químico de D. horizontalis (6 folhas até 1-2 perfilhos) e Brachiaria decumbens (2 a 6 folhas) apresentou-se eficiente (> 91%) nas linhas sem palha a partir dos 14 DAA (dias após aplicação) para os herbicidas e pontas de pulverização estudados. D. horizontalis foi mais rapidamente controlada aos 7 DAA pelo trifloxysulfuron-sodium + ametryne com a ponta AI11002-VS. Houve toxicidade até os 21 DAA, sendo esta mais intensa para os tratamentos com hexazinone + diuron associado com as pontas AI11002-VS e TF-VP5, em decorrência da maior deposição do herbicida nas folhas da cultura.

Variáveis qualitativas da pulverização em feijão, Bidens pilosa E Brachiaria plantaginea

Conduziu-se este trabalho, com o objetivo de avaliar a qualidade da deposição da calda de pulverização em plantas de feijão (Phaseolus vulgaris L.), Bidens pilosa L. e de Brachiaria plantaginea (Link) Hitchc. presentes na linha e entrelinha da cultura. Foi utilizado como traçador o corante Azul Brilhante FDC-1 (500 ppm). Utilizaram-se cinco pontas de pulverização: jato plano (XR 110015 VS e XR 11002 VS), jato plano duplo (TJ60 11002 VS) e jato cônico (TX-6 VS e TX-8 VS) e dois volumes de aplicação 150 e 200 L ha-1. O delineamento utilizado foi de blocos ao acaso, com 4 repetições. Foram amostradas 25 plantas em cada parcela/repetição, de plantas de feijão e plantas daninhas presentes na linha e na entrelinha da cultura. Após a aplicação, as plantas foram coletadas e lavadas em água destilada para quantificação do traçador em espectrofotômetro. Os dados ajustaram-se à curva de regressão pelo modelo de Gompertz. Os resultados evidenciaram que: para as plantas de feijão as pontas XR 110015 e TJ60 proporcionaram as deposições mais uniformes, nos volumes de 150 e 200 L ha-1, respectivamente; a ponta TX-6 no volume de 150 L ha-1 apresentou melhor uniformidade de distribuição para ambas as espécies de plantas daninhas presentes na linha da cultura; para as plantas daninhas presentes na entrelinha, no volume de 150 L ha-1, destacaram-se as pontas XR 110015 e TJ60 11002 para B. pilosa e B. plantaginea, respectivamente, no volume de 200 L ha-1 destacou-se a ponta TX-8 para ambas as espécies.

Efeito de pontas e volumes de aplicação sobre os depósitos da pulverização em plantas de feijoeiro, Bidens pilosa L. e Brachiaria plantaginea (Link) Hitchc

Pós-graduação em Agronomia (Agricultura) - FCA

Aspectos qualitativos e quantitativos em pulverização na cultura do amendoim e Brachiaria plantaginea (Link) Hitch

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Resistência mecânica à penetração em latossolo vermelho após sucessivos cortes mecanizas de cana-de-açúcar

Pós-graduação em Agronomia (Produção Vegetal) - FCAV

INFLUENCE OF NOZZLE TYPE AND SPRAY RATES ON CORN AND WEED PLANTS DROP DEPOSITIONS

The objective of this study was to evaluate different nozzles and spray rates on drop deposition in corn (Zea mays), Euphorbia heterophylla and Brachiaria plantaginea, both weeds located at and between crop rows. The experimental design established was complete random blocks with treatments arranged at 2 x 2 factorial scheme (2 nozzles types: DG11002VS flat flan and medium droplets, TXVK08 cone and very fine droplets; and 2 rates: 100 and 200 L ha(-1)) with four replications. The spray applications occurred at 13 days after corn germination (3-5 expanded leaves), when E. heterophylla and B. plantaginea plants had 2-4 and 2-3 leaves, respectively. Solution of Brilliant Blue (FD&C-1) dye at 3,000 ppm was used as spray tracer. It was concluded that the greatest average deposits in corn plants was provided by TXVK08, independently of the spray rates used. The most uniform deposits occurred when the spray rates of 200 L ha(-1) was used. Spray deposits were most uniform in B. plantaginea compared to E. heterophylla when both weds were located at crop row, independently of nozzle or spray rates. However, the DG 11002VS spray nozzle provided the most uniform drop deposition on B. plantaginea located between the rows, while the most efficient deposition over E. heterophylla located between rows was TXVK08.

EFEITOS DE DIFERENTES TIPOS DE CONTROLE DE PLANTAS INFESTANTES SOBRE A MIRMECOFAUNA EM Eucalyptus grandis

Este estudo teve como objetivo avaliar os efeitos de diferentes tipos de controle de plantas infestantes sobre a mirmecofauna em um plantio inicial de Eucalyptus grandis . Para tanto, em março de 2011 foi realizado o início da implantação da cultura, em uma área localizada no município de Santa Maria - RS. Os seis tratamentos constituíram-se em controle químico total de plantas infestantes, na linha e na entrelinha de plantio, com glifosato (T1); controle químico total de plantas infestantes, na linha de plantio, com glifosato (T2); controle químico de monocotiledôneas na linha e entrelinha de plantio, com setoxidim (T3); controle químico de dicotiledôneas na linha e entrelinha de plantio, com bentazona (T4); controle químico total de plantas infestantes em faixa de um metro paralela à linha de plantio, com glifosato, e de um metro na parte central da entrelinha, sem controle (T5); e testemunha, sem controle de plantas infestantes (T6). O levantamento da mirmecofauna foi realizado no período de um ano utilizando-se três métodos de coleta: isca atrativa, armadilha de solo e funil de Berlese, com seis repetições por tratamento, em cada data de coleta. Nesse período foram coletadas 46.675 formigas, distribuídas em 37 espécies, não sendo verificada diferença significativa entre o total de espécimens coletados. Na área do tratamento constituído pelo controle de plantas infestantes somente na linha de plantio verificou-se eficiência amostral de 99,0% e Sobs = 35. Entre os índices de Diversidade de Shannon (H’), destacou-se o valor encontrado para a área do tratamento T2 (H’= 1,34) em detrimento dos valores das áreas nas quais foram instalados os tratamentos T1 (H’= 1,25) e T5 (H’= 1,23). Havendo assim, uma maior coexistência de espécies de formigas entre as áreas com estrutura florística menos alterada e entre as áreas mais simplificadas. Não tendo sido verificada correlação significativa (r = 0,0463) entre a riqueza de espécies de formigas coletadas e o número de plantas infestantes encontradas ao final do experimento. Assim, conclui-se que os efeitos indiretos da ação dos herbicidas afetam mais a composição local de espécies de formigas do que sua riqueza.

Wavelet analysis of MODIS time series to detect expansion and intensification of row-crop agriculture in Brazil

Since 2000, the southwestern Brazilian Amazon has undergone a rapid transformation from natural vegetation and pastures to row-crop agricultural with the potential to affect regional biogeochemistry. The goals of this research are to assess wavelet algorithms applied to MODIS time series to determine expansion of row-crops and intensification of the number of crops grown. MODIS provides data from February 2000 to present, a period of agricultural expansion and intensification in the southwestern Brazilian Amazon. We have selected a study area near Comodoro, Mato Grosso because of the rapid growth of row-crop agriculture and availability of ground truth data of agricultural land-use history. We used a 90% power wavelet transform to create a wavelet-smoothed time series for five years of MODIS EVI data. From this wavelet-smoothed time series we determine characteristic phenology of single and double crops. We estimate that over 3200 km(2) were converted from native vegetation and pasture to row-crop agriculture from 2000 to 2005 in our study area encompassing 40,000 km(2). We observe an increase of 2000 km(2) of agricultural intensification, where areas of single crops were converted to double crops during the study period. (C) 2007 Elsevier Inc. All rights reserved.