We introduce a new automated approach to parameterising multi-scale image segmentation of multiple layers, and we implemented it as a generic tool for the eCognition® software. This approach relies on the potential of the local variance (LV) to detect scale transitions in geospatial data. The tool detects the number of layers added to a project and segments them iteratively with a multiresolution segmentation algorithm in a bottom-up approach, where the scale factor in the segmentation, namely, the scale parameter (SP), increases with a constant increment. The average LV value of the objects in all of the layers is computed and serves as a condition for stopping the iterations: when a scale level records an LV value that is equal to or lower than the previous value, the iteration ends, and the objects segmented in the previous level are retained. Three orders of magnitude of SP lags produce a corresponding number of scale levels. Tests on very high resolution imagery provided satisfactory results for generic applicability. The tool has a significant potential for enabling objectivity and automation of GEOBIA analysis.

Accurate and timely detection of weeds between and within crop rows in the early growth stage is considered one of the main challenges in site-specific weed management (SSWM). In this context, a robust and innovative automatic object-based image analysis (OBIA) algorithm was developed on Unmanned Aerial Vehicle (UAV) images to design early post-emergence prescription maps. This novel algorithm makes the major contribution. The OBIA algorithm combined Digital Surface Models (DSMs), orthomosaics and machine learning techniques (Random Forest, RF). OBIA-based plant heights were accurately estimated and used as a feature in the automatic sample selection by the RF classifier; this was the second research contribution. RF randomly selected a class balanced training set, obtained the optimum features values and classified the image, requiring no manual training, making this procedure time-efficient and more accurate, since it removes errors due to a subjective manual task. The ability to discriminate weeds was significantly affected by the imagery spatial resolution and weed density, making the use of higher spatial resolution images more suitable. Finally, prescription maps for in-season post-emergence SSWM were created based on the weed maps—the third research contribution—which could help farmers in decision-making to optimize crop management by rationalization of the herbicide application. The short time involved in the process (image capture and analysis) would allow timely weed control during critical periods, crucial for preventing yield loss.

Remote sensing is important to precision agriculture and the spatial resolution provided by Unmanned Aerial Vehicles (UAVs) is revolutionizing precision agriculture workflows for measurement crop condition and yields over the growing season, for identifying and monitoring weeds and other applications. Monitoring of individual trees for growth, fruit production and pest and disease occurrence remains a high research priority and the delineation of each tree using automated means as an alternative to manual delineation would be useful for long-term farm management. In this paper, we detected citrus and other crop trees from UAV images using a simple convolutional neural network (CNN) algorithm, followed by a classification refinement using superpixels derived from a Simple Linear Iterative Clustering (SLIC) algorithm. The workflow performed well in a relatively complex agricultural environment (multiple targets, multiple size trees and ages, etc.) achieving high accuracy (overall accuracy = 96.24%, Precision (positive predictive value) = 94.59%, Recall (sensitivity) = 97.94%). To our knowledge, this is the first time a CNN has been used with UAV multi-spectral imagery to focus on citrus trees. More of these individual cases are needed to develop standard automated workflows to help agricultural managers better incorporate large volumes of high resolution UAV imagery into agricultural management operations.

Tropical forests are crucial for mitigating climate change, but many forests continue to be driven from carbon sinks to sources through human activities. To support more sustainable forest uses, we need to measure and monitor carbon stocks and emissions at high spatial and temporal resolution. We developed the first large-scale very high-resolution map of aboveground carbon stocks and emissions for the country of Peru by combining 6.7 million hectares of airborne LiDAR measurements of top-of-canopy height with thousands of Planet Dove satellite images into a random forest machine learning regression workflow, obtaining an R² of 0.70 and RMSE of 25.38 Mg C ha⁻¹ for the nationwide estimation of aboveground carbon density (ACD). The diverse ecosystems of Peru harbor 6.928 Pg C, of which only 2.9 Pg C are found in protected areas or their buffers. We found significant carbon emissions between 2012 and 2017 in areas aggressively affected by oil palm and cacao plantations, agricultural and urban expansions or illegal gold mining. Creating such a cost-effective and spatially explicit indicators of aboveground carbon stocks and emissions for tropical countries will serve as a transformative tool to quantify the climate change mitigation services that forests provide.

Speed and accuracy are important factors when dealing with time-constraint events for disaster, risk, and crisis-management support. Object-based image analysis can be a time consuming task in extracting information from large images because most of the segmentation algorithms use the pixel-grid for the initial object representation. It would be more natural and efficient to work with perceptually meaningful entities that are derived from pixels using a low-level grouping process (superpixels). Firstly, we tested a new workflow for image segmentation of remote sensing data, starting the multiresolution segmentation (MRS, using ESP2 tool) from the superpixel level and aiming at reducing the amount of time needed to automatically partition relatively large datasets of very high resolution remote sensing data. Secondly, we examined whether a Random Forest classification based on an oversegmentation produced by a Simple Linear Iterative Clustering (SLIC) superpixel algorithm performs similarly with reference to a traditional object-based classification regarding accuracy. Tests were applied on QuickBird and WorldView-2 data with different extents, scene content complexities, and number of bands to assess how the computational time and classification accuracy are affected by these factors. The proposed segmentation approach is compared with the traditional one, starting the MRS from the pixel level, regarding geometric accuracy of the objects and the computational time. The computational time was reduced in all cases, the biggest improvement being from 5 h 35 min to 13 min, for a WorldView-2 scene with eight bands and an extent of 12.2 million pixels, while the geometric accuracy is kept similar or slightly better. SLIC superpixel-based classification had similar or better overall accuracy values when compared to MRS-based classification, but the results were obtained in a fast manner and avoiding the parameterization of the MRS. These two approaches have the potential to enhance the automation of big remote sensing data analysis and processing, especially when time is an important constraint.