The increasing public concern about food security and the stricter rules applied worldwide concerning herbicide use in the agri-food chain, reduce consumer acceptance of chemical plant protection. Site-Specific Weed Management can be achieved by applying a treatment only on the weed patches. Crop plants and weeds identification is a necessary component for various aspects of precision farming in order to perform on the spot herbicide spraying or robotic weeding and precision mechanical weed control. During the last years, a lot of different methods have been proposed, yet more improvements need to be made on this problem, concerning speed, robustness, and accuracy of the algorithms and the recognition systems. Digital cameras and Artificial Neural Networks (ANNs) have been rapidly developed in the past few years, providing new methods and tools also in agriculture and weed management. In the current work, images gathered by an RGB camera of Zea mays, Helianthus annuus, Solanum tuberosum, Alopecurus myosuroides, Amaranthus retroflexus, Avena fatua, Chenopodium album, Lamium purpureum, Matricaria chamomila, Setaria spp., Solanum nigrum and Stellaria media were provided to train Convolutional Neural Networks (CNNs). Three different CNNs, namely VGG16, ResNet–50, and Xception, were adapted and trained on a pool of 93,000 images. The training images consisted of images with plant material with only one species per image. A Top-1 accuracy between 77% and 98% was obtained in plant detection and weed species discrimination, on the testing of the images.

Pastures are botanically diverse and difficult to characterize. Digital modeling of pasture biomass and quality by non-destructive methods can provide highly valuable support for decision-making. This study aimed to evaluate aerial and on-ground methods to characterize grass ley fields, estimating plant height, biomass and volume, using digital grass models. Two fields were sampled, one timothy-dominant and the other ryegrass-dominant. Both sensing systems allowed estimation of biomass, volume and plant height, which were compared with ground truth, also taking into consideration basic economical aspects. To obtain ground-truth data for validation, 10 plots of 1 m² were manually and destructively sampled on each field. The studied systems differed in data resolution, thus in estimation capability. There was a reasonably good agreement between the UAV-based, the RGB-D-based estimates and the manual height measurements on both fields. RGB-D-based estimation correlated well with ground truth of plant height ( $R^2>0.80$ ) for both fields, and with dry biomass ( $R^2=0.88$ ), only for the timothy field. RGB-D-based estimation of plant volume for ryegrass showed a high agreement ( $R^2=0.87$ ). The UAV-based system showed a weaker estimation capability for plant height and dry biomass ( $R^2<0.6$ ). UAV-systems are more affordable, easier to operate and can cover a larger surface. On-ground techniques with RGB-D cameras can produce highly detailed models, but with more variable results than UAV-based models. On-ground RGB-D data can be effectively analysed with open source software, which is a cost reduction advantage, compared with aerial image analysis. Since the resolution for agricultural operations does not need fine identification the end-details of the grass plants, the use of aerial platforms could result a better option in grasslands.

Site-specific weed control offers a great potential for herbicide savings in agricultural crops without causing yield losses and additional weed management costs in the following years. Therefore, precision weed management is an efficient tool to meet the EU targets for pesticide reduction. This review summarizes different commercial technologies and prototypes for precision patch spraying and spot spraying. All the presented technologies have in common that they consist of three essential parts. (1) Sensors and classifiers for weed/crop detection, (2) Decision algorithms to decide whether weed control is needed and to determine a suitable type and rate of herbicide. Usually, decision algorithms are installed on a controller and (3) a precise sprayer with boom section control or single nozzle control. One point that differs between some of the techniques is the way the decision algorithms classify. They are based on different approaches. Green vegetation can be differentiated from soil and crop residues based on spectral information in the visible and near-infrared wavebands (“Green on Brown”). Those sensors can be applied for real-time on/off control of single nozzles to control weeds before sowing after conservation tillage and in the inter-row area of crops. More sophisticated imaging algorithms are used to classify weeds in crops (“Green on Green”). This paper will focus on Convolutional Neural Networks (CNN) for plant species identification. Alternatively, the position of each crop can be recorded during sowing/planting and afterward herbicides can be targeted to single weeds or larger patches of weeds if the economic weed threshold is exceeded. With a standardized protocol of data communication between sensor, controller and sprayer, the user can combine different sensors with different sprayers. In this review, an ISOBUS communication protocol is presented for a spot sprayer. Precision chemical weed control can be realized with tractor-mounted sprayers and autonomous robots. Commercial systems for both classes will be introduced and their economic and environmental benefits and limitations will be highlighted. Farmers ask for robust systems with less need for maintenance and flexible application in different crops.

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 (R2 = 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.