A computer vision approach for weeds identification through Support Vector Machines

This paper outlines an automatic computervision system for the identification of avena sterilis which is a special weed seed growing in cereal crops. The final goal is to reduce the quantity of herbicide to be sprayed as an important and necessary step for precision agriculture. So, only areas where the presence of weeds is important should be sprayed. The main problems for the identification of this kind of weed are its similar spectral signature with respect the crops and also its irregular distribution in the field. It has been designed a new strategy involving two processes: image segmentation and decision making. The image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and weeds. The decision making is based on the SupportVectorMachines and determines if a cell must be sprayed. The main findings of this paper are reflected in the combination of the segmentation and the SupportVectorMachines decision processes. Another important contribution of this approach is the minimum requirements of the system in terms of memory and computation power if compared with other previous works. The performance of the method is illustrated by comparative analysis against some existing strategies.

The Interactive Effects of Temperature and Osmotic Potential on the Growth of Aquatic Isolates of Fusarium culmorum.

The mycelial growth of 10 Fusarium culmorum strains isolated from water of the Andarax riverbed in the provinces of Granada and Almeria in southeastern Spain was tested on potato-dextroseagar adjusted to different osmotic potentials with either KCl or NaCl (−1.50 to−144.54 bars) at 10◦C intervals ranging from15◦ to 35◦C. Fungal growth was determined by measuring colony diameter after 4 d of incubation. Mycelial growth was maximal at 25◦C. The quantity and capacity of mycelial growth of F. culmorum were similar at 15 and 25◦C, with maximal growth occurring at −13.79 bars water potential and a lack of growth at 35◦C. The effect of water potential was independent of salt composition. The general growth pattern of Fusarium culmorum growth declined at potentials below −13.79 bars. Fungal growth at 25◦C was always greater than growth at 15◦C, at all of the water potentials tested. Significant differences were observed in the response ofmycelia to water potential and temperature as main and interactive effects. The number of isolates that showed growth was increasingly inhibited as the water potential dropped, but some growth was still observable at −99.56 bars. These findings could indicate that F. culmorum strains isolated from water have a physiological mechanism that permits survival in environments with low water potential. Propagules of Fusarium culmorum are transported long distances by river water, which could explain the severity of diseases caused by F.culmorum on cereal plants irrigated with river water and its interaction under hydric stress ormoderate soil salinity. The observed differences in growth magnitude and capacity could indicate that the biological factors governing potential and actual growth are affected by osmotic potential in different ways.

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.

Discriminating Crop, Weeds and Soil Surface with a Terrestrial LIDAR Sensor

In this study, the evaluation of the accuracy and performance of a light detection and ranging (LIDAR) sensor for vegetation using distance and reflection measurements aiming to detect and discriminate maize plants and weeds from soil surface was done. The study continues a previous work carried out in a maize field in Spain with a LIDAR sensor using exclusively one index, the height profile. The current system uses a combination of the two mentioned indexes. The experiment was carried out in a maize field at growth stage 12–14, at 16 different locations selected to represent the widest possible density of three weeds: Echinochloa crus-galli (L.) P.Beauv., Lamium purpureum L., Galium aparine L.and Veronica persica Poir.. A terrestrial LIDAR sensor was mounted on a tripod pointing to the inter-row area, with its horizontal axis and the field of view pointing vertically downwards to the ground, scanning a vertical plane with the potential presence of vegetation. Immediately after the LIDAR data acquisition (distances and reflection measurements), actual heights of plants were estimated using an appropriate methodology. For that purpose, digital images were taken of each sampled area. Data showed a high correlation between LIDAR measured height and actual plant heights (R 2 = 0.75). Binary logistic regression between weed presence/absence and the sensor readings (LIDAR height and reflection values) was used to validate the accuracy of the sensor. This permitted the discrimination of vegetation from the ground with an accuracy of up to 95%. In addition, a Canonical Discrimination Analysis (CDA) was able to discriminate mostly between soil and vegetation and, to a far lesser extent, between crop and weeds. The studied methodology arises as a good system for weed detection, which in combination with other principles, such as vision-based technologies, could improve the efficiency and accuracy of herbicide spraying.

Toxicity of ZnO nanoparticles, ZnO bulk and ZnCl2 on earthworms in a spiked natural soil and toxicological effects of leachates on aquatic organisms

The present study assessed the uptake and toxicity of ZnO nanoparticles (NPs), ZnO bulk, and ZnCl2 salt in earthworms in spiked agricultural soils. In addition, the toxicity of aqueous extracts to Daphnia magna and Chlorella vulgaris was analyzed to determine the risk of these soils to the aquatic compartment. We then investigated the distribution of Zn in soil fractions to interpret the nature of toxicity. Neither mortality nor differences in earthworm body weight were observed compared with the control. The most sensitive end point was reproduction. ZnCl2 was notably toxic in eliminating the production of cocoons. The effects induced by ZnO-NPs and bulk ZnO on fecundity were similar and lower than those of the salt. In contrast to ZnO bulk, ZnO-NPs adversely affected fertility. The internal concentrations of Zn in earthworms in the NP group were greater than those in the salt and bulk groups, although bioconcentration factors were consistently <1. No relationship was found between toxicity and internal Zn amounts in earthworms. The results from the sequential extraction of soil showed that ZnCl2 displayed the highest availability compared with both ZnO. Zn distribution was consistent with the greatest toxicity showed by the salt but not with Zn body concentrations. The soil extracts from both ZnO-NPs and bulk ZnO did not show effects on aquatic organisms (Daphnia and algae) after short-term exposure. However, ZnCl2 extracts (total and 0.45-μm filtered) were toxic to Daphnia.

Simultaneous determination of multiclass emerging contaminants in aquatic plants by ultrasound assisted matrix solid phase dispersion and GC-MS

A multiresidue method was developed for the simultaneous determination of 31 emerging contaminants (pharmaceutical compounds, hormones, personal care products, biocides and flame retardants) in aquatic plants. Analytes were extracted by ultrasound assisted-matrix solid phase dispersion (UA-MSPD) and determined by gas chromatography-mass spectrometry after sylilation. The method was validated for different aquatic plants (Typha angustifolia, Arundo donax and Lemna minor) and a semiaquatic cultivated plant (Oryza sativa) with good recoveries at concentrations of 100 and 25 ng g-1 wet weight, ranging from 70 to 120 %, and low method detection limits (0.3 to 2.2 ng g-1 wet weight). A significant difference of the chromatographic response was observed for some compounds in neat solvent versus matrix extracts and therefore quantification was carried out using matrix-matched standards in order to overcome this matrix effect. Aquatic plants taken from rivers located at three Spanish regions were analyzed and the compounds detected were parabens, bisphenol A, benzophenone-3, cyfluthrin and cypermethrin. The levels found ranged from 6 to 25 ng g-1 wet weight except for cypermethrin that was detected at 235 ng g-1 wet weight in Oryza sativa samples.