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.

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.

The use of depth cameras in precision agriculture is increasing day by day. This type of sensor has been used for the plant structure characterization of several crops. However, the discrimination of small plants, such as weeds, is still a challenge within agricultural fields. Improvements in the new Microsoft Kinect v2 sensor can capture the details of plants. The use of a dual methodology using height selection and RGB (Red, Green, Blue) segmentation can separate crops, weeds, and soil. This paper explores the possibilities of this sensor by using Kinect Fusion algorithms to reconstruct 3D point clouds of weed-infested maize crops under real field conditions. The processed models showed good consistency among the 3D depth images and soil measurements obtained from the actual structural parameters. Maize plants were identified in the samples by height selection of the connected faces and showed a correlation of 0.77 with maize biomass. The lower height of the weeds made RGB recognition necessary to separate them from the soil microrelief of the samples, achieving a good correlation of 0.83 with weed biomass. In addition, weed density showed good correlation with volumetric measurements. The canonical discriminant analysis showed promising results for classification into monocots and dictos. These results suggest that estimating volume using the Kinect methodology can be a highly accurate method for crop status determination and weed detection. It offers several possibilities for the automation of agricultural processes by the construction of a new system integrating these sensors and the development of algorithms to properly process the information provided by them.

Crop 3D modeling allows site-specific management at different crop stages. In recent years, light detection and ranging (LiDAR) sensors have been widely used for gathering information about plant architecture to extract biophysical parameters for decision-making programs. The study reconstructed vineyard crops using light detection and ranging (LiDAR) technology. Its accuracy and performance were assessed for vineyard crop characterization using distance measurements, aiming to obtain a 3D reconstruction. A LiDAR sensor was installed on-board a mobile platform equipped with an RTK-GNSS receiver for crop 2D scanning. The LiDAR system consisted of a 2D time-of-flight sensor, a gimbal connecting the device to the structure, and an RTK-GPS to record the sensor data position. The LiDAR sensor was facing downwards installed on-board an electric platform. It scans in planes perpendicular to the travel direction. Measurements of distance between the LiDAR and the vineyards had a high spatial resolution, providing high-density 3D point clouds. The 3D point cloud was obtained containing all the points where the laser beam impacted. The fusion of LiDAR impacts and the positions of each associated to the RTK-GPS allowed the creation of the 3D structure. Although point clouds were already filtered, discarding points out of the study area, the branch volume cannot be directly calculated, since it turns into a 3D solid cluster that encloses a volume. To obtain the 3D object surface, and therefore to be able to calculate the volume enclosed by this surface, a suitable alpha shape was generated as an outline that envelops the outer points of the point cloud. The 3D scenes were obtained during the winter season when only branches were present and defoliated. The models were used to extract information related to height and branch volume. These models might be used for automatic pruning or relating this parameter to evaluate the future yield at each location. The 3D map was correlated with ground truth, which was manually determined, pruning the remaining weight. The number of scans by LiDAR influenced the relationship with the actual biomass measurements and had a significant effect on the treatments. A positive linear fit was obtained for the comparison between actual dry biomass and LiDAR volume. The influence of individual treatments was of low significance. The results showed strong correlations with actual values of biomass and volume with R2 = 0.75, and when comparing LiDAR scans with weight, the R2 rose up to 0.85. The obtained values show that this LiDAR technique is also valid for branch reconstruction with great advantages over other types of non-contact ranging sensors, regarding a high sampling resolution and high sampling rates. Even narrow branches were properly detected, which demonstrates the accuracy of the system working on difficult scenarios such as defoliated crops.