Angela Ribeiro

A vision-based method for weeds identification through the Bayesian decision theory

One of the objectives of precision agriculture is to minimize the volume of herbicides that are applied to the fields through the use of site-specific weed management systems. This paper outlines an automatic computer vision-based approach for the detection and differential spraying of weeds in corn crops. The method is designed for post-emergence herbicide applications where weeds and corn plants display similar spectral signatures and the weeds appear irregularly distributed within the crops field. The proposed strategy involves two processes: image segmentation and decision making. 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 measuring relationships between crop and weeds. The decision making determines the cells to be sprayed based on the computation of a posterior probability under a Bayesian framework. The a priori probability in this framework is computed taking into account the dynamic of the physical system (tractor) where the method is embedded. The main contributions of this paper are: (1) the combination of the image segmentation and decision making processes and (2) the decision making itself which exploits a previous knowledge which is mapped as the a priori probability. The performance of the method is illustrated by comparative analysis against some existing strategies.

An Air-Ground Wireless Sensor Network for Crop Monitoring

This paper presents a collaborative system made up of a Wireless Sensor Network (WSN) and an aerial robot, which is applied to real-time frost monitoring in vineyards. The core feature of our system is a dynamic mobile node carried by an aerial robot, which ensures communication between sparse clusters located at fragmented parcels and a base station. This system overcomes some limitations of the wireless networks in areas with such characteristics. The use of a dedicated communication channel enables data routing to/from unlimited distances.

A computer vision approach for weeds identification through Support Vector Machines

This paper outlines an automatic computer vision 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 Support Vector Machines and determines if a cell must be sprayed. The main findings of this paper are reflected in the combination of the segmentation and the Support Vector Machines 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.

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 Otsus 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.

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.

Analysis of natural images processing for the extraction of agricultural elements

This work presents several developed computer-vision-based methods for the estimation of percentages of weed, crop and soil present in an image showing a region of interest of the crop field. The visual detection of weed, crop and soil is an arduous task due to physical similarities between weeds and crop and to the natural and therefore complex environments (with non-controlled illumination) encountered. The image processing was divided in three different stages at which each different agricultural element is extracted: (1) segmentation of vegetation against non-vegetation (soil), (2) crop row elimination (crop) and (3) weed extraction (weed). For each stage, different and interchangeable methods are proposed, each one using a series of input parameters which value can be changed for further refining the processing. A genetic algorithm was then used to find the best value of parameters and method combination for different sets of images. The whole system was tested on several images from different years and fields, resulting in an average correlation coefficient with real data (bio-mass) of 84%, with up to 96% correlation using the best methods on winter cereal images and of up to 84% on maize images. Moreover, the methods low computational complexity leads to the possibility, as future work, of adapting them to real-time processing.

A Hopfield Neural Network for combining classifiers applied to textured images

In this paper we propose a new method for combining simple classifiers through the analogue Hopfield Neural Network (HNN) optimization paradigm for classifying natural textures in images. The base classifiers are the Fuzzy clustering (FC) and the parametric Bayesian estimator (BP). An initial unsupervised training phase determines the number of clusters and estimates the parameters for both FC and BP. Then a decision phase is carried out, where we build as many Hopfield Neural Networks as the available number of clusters. The number of nodes at each network is the number of pixels in the image which is to be classified. Each node at each network is initially loaded with a state value, which is the membership degree (provided by FC) that the node (pixel) belongs to the cluster associated to the network. Each state is later iteratively updated during the HNN optimization process taking into account the previous states and two types of external influences exerted by other nodes in its neighborhood. The external influences are mapped as consistencies. One is embedded in an energy term which considers the states of the node to be updated and the states of its neighbors. The other is mapped as the inter-connection weights between the nodes. From BP, we obtain the probabilities that the nodes (pixels) belong to a cluster (network). We define these weights as a relation between states and probabilities between the nodes in the neighborhood of the node which is being updated. This is the classifier combination, making the main finding of this paper. The proposed combined strategy based on the HNN outperforms the simple classifiers and also classical combination strategies.

Accuracy and Feasibility of Optoelectronic Sensors for Weed Mapping in Wide Row Crops

The main objectives of this study were to assess the accuracy of a ground-based weed mapping system that included optoelectronic sensors for weed detection, and to determine the sampling resolution required for accurate weed maps in maize crops. The optoelectronic sensors were located in the inter-row area of maize to distinguish weeds against soil background. The system was evaluated in three maize fields in the early spring. System verification was performed with highly reliable data from digital images obtained in a regular 12 m × 12 m grid throughout the three fields. The comparison in all these sample points showed a good relationship (83% agreement on average) between the data of weed presence/absence obtained from the optoelectronic mapping system and the values derived from image processing software (“ground truth”). Regarding the optimization of sampling resolution, the comparison between the detailed maps (all crop rows with sensors separated 0.75 m) with maps obtained with various simulated distances between sensors (from 1.5 m to 6.0 m) indicated that a 4.5 m distance (equivalent to one in six crop rows) would be acceptable to construct accurate weed maps. This spatial resolution makes the system cheap and robust enough to generate maps of inter-row weeds.

Highlights and preliminary results for autonomous crop protection

Intelligent pest control remains a mayor challenge to agriculture.The autonomous tractor used in this work was able to track each straight line with high degree of accuracy.The new design concept was able to autonomously adjust spray application according tree sizes and orchard structure.The intelligent spray boom responded satisfactorily to variation in the level of weed infestation in the field. New technologies are required for safe, site-specific and efficient control of weeds, pathogens and insects in agricultural crops and in forestry. The development and use of autonomous tractors equipped with innovative sensor systems, data processing techniques and actuation tools can be highly beneficial because this technology allows pest control measures to be applied only if, when, and where they are genuinely needed, thus reducing costs, environmental damage and risks to farmers. RHEA (Robotics and associated High-technologies and Equipment for Agriculture) is an EC-funded research project conducted by a consortium composed of 15 research partners from eight European countries. The focus of the project is the design, development and testing of a new generation of automatic and robotic systems for both chemical and physical pest management. A heterogeneous fleet of small, cooperative ground and aerial robots equipped with advanced sensors, enhanced end effectors and improved decision control algorithms will be used. Initially, we are investigating three major scenarios: (a) chemical weed control in winter wheat, (b) thermal weed control (i.e., flaming) in maize and (c) variable applications of pesticides in olive crops. A preliminary system evaluation demonstrated that the intelligent sprayer boom applied the control agent to over 95% of the target area and that the response time, 10s, of the direct-injection system was anticipated in the sprayer system to ensure the accuracy of herbicide spraying. Field trial results showed that the estimated cost for site-specific flame weeding was approximately 24?ha-1, whereas approximately 52?ha-1 was needed to perform a conventional broadcast treatment. Thus, the use of VRA (Variable Rate Application) flaming reduces the use of liquid petroleum gas (cost savings of 28?ha-1). The results also indicated that the control system, mounted on a prototype, air-blast sprayer design, produced a precise system response to variation in the target features, an approximate accuracy of 0.1m in horizontal resolution and a rapid actuation response of approximately 100ms. Workshop and field experiments provide convincing evidence that autonomous agricultural vehicles equipped with intelligent implements represent an important step forward for optimizing pest control applications in sustainable row crop, orchard and cereal crop production systems.

Mapping Wide Row Crops with Video Sequences Acquired from a Tractor Moving at Treatment Speed

This paper presents a mapping method for wide row crop fields. The resulting map shows the crop rows and weeds present in the inter-row spacing. Because field videos are acquired with a camera mounted on top of an agricultural vehicle, a method for image sequence stabilization was needed and consequently designed and developed. The proposed stabilization method uses the centers of some crop rows in the image sequence as features to be tracked, which compensates for the lateral movement (sway) of the camera and leaves the pitch unchanged. A region of interest is selected using the tracked features, and an inverse perspective technique transforms the selected region into a bird’s-eye view that is centered on the image and that enables map generation. The algorithm developed has been tested on several video sequences of different fields recorded at different times and under different lighting conditions, with good initial results. Indeed, lateral displacements of up to 66% of the inter-row spacing were suppressed through the stabilization process, and crop rows in the resulting maps appear straight.