High-resolution Unmanned Aerial Vehicles Imagery Research Articles

Large Holocene ruptures on the Cañada David detachment, Baja California, Mexico; implications for the seismogenesis of low-angle normal faults

We present the results of detailed mapping and paleoseismic investigations along a section of the complex fault scarp array associated with the Cañada David detachment, a low-angle oblique normal fault that controls the southwestern flank of the Sierra El Mayor, Baja California, Mexico. We used high-resolution unmanned aerial vehicle imagery to map portions of a sequence of alluvial fans that comprise a bajada that flanks the southwestern range front. Their ages are distinguished based on a regional soil chronosequence. Three paleoseismic trenches were excavated across active surface faults that root into the Cañada David detachment at depth. Fine-grained stratigraphic units in the trenches were dated by optically stimulated luminescence techniques. The three trenches in this study show strong evidence for four large (Mw≥7) Holocene earthquakes at or just prior to about 1.7, 4.3–6.1, 7.7–7.6 and 8.4–10.7 ka, as well as weak to moderate evidence for two additional late Pleistocene earthquakes at or just prior to 12.7–14.1 ka and 15.2 ka, indicating an average recurrence of such events of ∼3 ka. This earthquake recurrence interval is slightly longer than that for the Laguna Salada fault to the north that flanks the Sierra Cucapah. The regular recurrence of major surface ruptures strongly suggests that severely-misoriented low-angle normal faults like the Cañada David detachment have a mechanical behavior that is very similar to other more optimally oriented faults suggesting that earthquakes on such faults should be common and may be difficult to recognize from seismologic methods due rolling-hinge ramps and/or multifault ruptures.

Understanding Growth Dynamics and Yield Prediction of Sorghum Using High Temporal Resolution UAV Imagery Time Series and Machine Learning

Unmanned aerial vehicles (UAV) carrying multispectral cameras are increasingly being used for high-throughput phenotyping (HTP) of above-ground traits of crops to study genetic diversity, resource use efficiency and responses to abiotic or biotic stresses. There is significant unexplored potential for repeated data collection through a field season to reveal information on the rates of growth and provide predictions of the final yield. Generating such information early in the season would create opportunities for more efficient in-depth phenotyping and germplasm selection. This study tested the use of high-resolution time-series imagery (5 or 10 sampling dates) to understand the relationships between growth dynamics, temporal resolution and end-of-season above-ground biomass (AGB) in 869 diverse accessions of highly productive (mean AGB = 23.4 Mg/Ha), photoperiod sensitive sorghum. Canopy surface height (CSM), ground cover (GC), and five common spectral indices were considered as features of the crop phenotype. Spline curve fitting was used to integrate data from single flights into continuous time courses. Random Forest was used to predict end-of-season AGB from aerial imagery, and to identify the most informative variables driving predictions. Improved prediction of end-of-season AGB (RMSE reduction of 0.24 Mg/Ha) was achieved earlier in the growing season (10 to 20 days) by leveraging early- and mid-season measurement of the rate of change of geometric and spectral features. Early in the season, dynamic traits describing the rates of change of CSM and GC predicted end-of-season AGB best. Late in the season, CSM on a given date was the most influential predictor of end-of-season AGB. The power to predict end-of-season AGB was greatest at 50 days after planting, accounting for 63% of variance across this very diverse germplasm collection with modest error (RMSE 1.8 Mg/ha). End-of-season AGB could be predicted equally well when spline fitting was performed on data collected from five flights versus 10 flights over the growing season. This demonstrates a more valuable and efficient approach to using UAVs for HTP, while also proposing strategies to add further value.

Deep learning-based identification system of weeds and crops in strawberry and pea fields for a precision agriculture sprayer

Controlling weed infestation through chemicals (herbicides & pesticides) is essential for crop yield. However, excessive use of these chemicals has caused severe agronomic and environmental problems. According to accurate weed detection, an appropriate dose of herbicides is recommended in site-specific weed management (SSWM) applications, which may ultimately promote chemical saving while enhancing its effectiveness. In this context of SSWM, an accurate detection and recognition system needs to be established for recognizing weeds and crops to carry out precise agrochemical treatments in real-time applications. Unmanned aerial vehicles (UAVs) and other robots offer potential in precision agriculture (PA) applications by monitoring farmland on a per-plant basis, as they have the capability of acquiring high-resolution imagery providing detailed information for the distribution of crops and weeds in the field. In this regard, UAVs offer a cost-efficient solution for providing excellent survey capabilities. In this study, a deep learning system is developed for identifying weeds and crops in croplands. The developed system was implemented and evaluated using high-resolution UAV imagery captured over two different target fields: pea and strawberry; the developed system was able to identify weeds with an average accuracy of 95.3%, whereas the overall average accuracy (crops and weeds) was 94.73% for both the fields. The average kappa coefficient of the developed system was 0.89. The developed deep learning system outperformed the existing machine learning and deep learning-based approaches on comparison and can be embedded into a precision sprayer for adopting the SSWM strategy.

Automated Mapping of Ms 7.0 Jiuzhaigou Earthquake (China) Post-Disaster Landslides Based on High-Resolution UAV Imagery

The Ms 7.0 Jiuzhaigou earthquake that occurred on 8 August 2017 triggered hundreds of landslides in the Jiuzhaigou valley scenic and historic-interest area in Sichuan, China, causing heavy casualties and serious property losses. Quick and accurate mapping of post-disaster landslide distribution is of paramount importance for earthquake emergency rescue and the analysis of post-seismic landslides distribution characteristics. The automatic identification of landslides is mostly based on medium- and low-resolution satellite-borne optical remote-sensing imageries, and the high-accuracy interpretation of earthquake-triggered landslides still relies on time-consuming manual interpretation. This paper describes a methodology based on the use of 1 m high-resolution unmanned aerial vehicle (UAV) imagery acquired after the earthquake, and proposes a support vector machine (SVM) classification method combining the roads and villages mask from pre-seismic remote sensing imagery to accurately and automatically map the landslide inventory. Compared with the results of manual visual interpretation, the automatic recognition accuracy could reach 99.89%, and the Kappa coefficient was higher than 0.9, suggesting that the proposed method and 1 m high-resolution UAV imagery greatly improved the mapping accuracy of the landslide area. We also analyzed the spatial-distribution characteristics of earthquake-triggered landslides with the influenced factors of altitude, slope gradient, slope aspect, and the nearest faults, which provided important support for the further study of post-disaster landslide distribution characteristics, susceptibility prediction, and risk assessment.

FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding

Visual scene understanding is the core task in making any crucial decision in any computer vision system. Although popular computer vision datasets like Cityscapes, MS-COCO, PASCAL provide good benchmarks for several tasks (e.g. image classification, segmentation, object detection), these datasets are hardly suitable for post disaster damage assessments. On the other hand, existing natural disaster datasets include mainly satellite imagery which has low spatial resolution and a high revisit period. Therefore, they do not have a scope to provide quick and efficient damage assessment tasks. Unmanned Aerial Vehicle (UAV) can effortlessly access difficult places during any disaster and collect high resolution imagery that is required for aforementioned tasks of computer vision. To address these issues we present a high resolution UAV imagery, FloodNet, captured after the hurricane Harvey. This dataset demonstrates the post flooded damages of the affected areas. The images are labeled pixel-wise for semantic segmentation task and questions are produced for the task of visual question answering. FloodNet poses several challenges including detection of flooded roads and buildings and distinguishing between natural water and flooded water. With the advancement of deep learning algorithms, we can analyze the impact of any disaster which can make a precise understanding of the affected areas. In this paper, we compare and contrast the performances of baseline methods for image classification, semantic segmentation, and visual question answering on our dataset. FloodNet dataset can be downloaded from here: https://github.com/BinaLab/FloodNet-Supervised_v1.0.

Constraints and Opportunities for Detecting Land Surface Phenology in Drylands

Land surface phenology (LSP) enables global-scale tracking of ecosystem processes, but its utility is limited in drylands due to low vegetation cover and resulting low annual amplitudes of vegetation indices (VIs). Due to the importance of drylands for biodiversity, food security, and the carbon cycle, it is necessary to understand the limitations in measuring dryland dynamics. Here, using simulated data and multitemporal unmanned aerial vehicle (UAV) imagery of a desert shrubland, we explore the feasibility of detecting LSP with respect to fractional vegetation cover, plant functional types, VI uncertainty, and two different detection algorithms. Using simulated data, we found that plants with distinct VI signals, such as deciduous shrubs, can require up to 60% fractional cover to consistently detect LSP. Evergreen plants, with lower seasonal VI amplitude, require considerably higher cover and can have undetectable phenology even with 100% vegetation cover. Our evaluation of two algorithms showed that neither performed the best in all cases. Even with adequate cover, biases in phenological metrics can still exceed 20 days and can never be 100% accurate due to VI uncertainty from shadows, sensor view angle, and atmospheric interference. We showed how high-resolution UAV imagery enables LSP studies in drylands and highlighted important scale effects driven by within-canopy VI variation. With high-resolution imagery, the open canopies of drylands are beneficial as they allow for straightforward identification of individual plants, enabling the tracking of phenology at the individual level. Drylands thus have the potential to become an exemplary environment for future LSP research.

Assessing a novel modelling approach with high resolution UAV imagery for monitoring health status in priority riparian forests

BackgroundBlack alder (Alnus glutinosa) forests are in severe decline across their area of distribution due to a disease caused by the soil-borne pathogenic Phytophthora alni species complex (class Oomycetes), “alder Phytopththora”. Mapping of the different types of damages caused by the disease is challenging in high density ecosystems in which spectral variability is high due to canopy heterogeneity. Data obtained by unmanned aerial vehicles (UAVs) may be particularly useful for such tasks due to the high resolution, flexibility of acquisition and cost efficiency of this type of data. In this study, A. glutinosa decline was assessed by considering four categories of tree health status in the field: asymptomatic, dead and defoliation above and below a 50% threshold. A combination of multispectral Parrot Sequoia and UAV unmanned aerial vehicles -red green blue (RGB) data were analysed using classical random forest (RF) and a simple and robust three-step logistic modelling approaches to identify the most important forest health indicators while adhering to the principle of parsimony. A total of 34 remote sensing variables were considered, including a set of vegetation indices, texture features from the normalized difference vegetation index (NDVI) and a digital surface model (DSM), topographic and digital aerial photogrammetry-derived structural data from the DSM at crown level.ResultsThe four categories identified by the RF yielded an overall accuracy of 67%, while aggregation of the legend to three classes (asymptomatic, defoliated, dead) and to two classes (alive, dead) improved the overall accuracy to 72% and 91% respectively. On the other hand, the confusion matrix, computed from the three logistic models by using the leave-out cross-validation method yielded overall accuracies of 75%, 80% and 94% for four-, three- and two-level classifications, respectively.DiscussionThe study findings provide forest managers with an alternative robust classification method for the rapid, effective assessment of areas affected and non-affected by the disease, thus enabling them to identify hotspots for conservation and plan control and restoration measures aimed at preserving black alder forests.

Exploring the use of Unmanned Aerial Vehicles (UAVs) with the simplified ‘triangle’ technique for soil water content and evaporative fraction retrievals in a Mediterranean setting

ABSTRACT Information acquired from Unmanned Aerial Vehicles (UAVs) is frequently used nowadays in a variety of disciplines and research fields. The present study explores for the first time the combined use of UAVs with a newly proposed technique for estimating evaporative fraction (EF) and surface soil moisture (SSM). The investigation is performed in a typical Mediterranean setting, a citrus field with flat topography divided in two plots with different irrigation schemes, in Sicily, Italy, at which ground data acquired during an extensive field campaign in July 2019. Reasonable estimates of both EF and surface wetness were produced, with patterns in agreement to vegetation cover fragmentation, topography, and other site-specific characteristics. Validation shows average error of 0.053 for EF and of 0.040 cm3 cm−3 for SSM. The results are comparable or better to those reported in analogous studies performed in similar areas. This implies that the investigated approach performs well under the semi-arid conditions characterizing the experimental set up. To our knowledge, this study represents the first evaluation of the combined use of the ‘simplified triangle’ with very high-resolution UAV imagery. As such, the findings are of significance regarding the potential future use of the ‘simplified triangle’ approach particularly with very fine resolution imagery such as that provided by UAV for mapping and monitoring EF and SSM in agricultural and natural ecosystems.

Mapping crop stand count and planting uniformity using high resolution imagery in a maize crop

The accurate evaluation of maize plants’ uniformity aligned with an effective improvement in germination and biomass assessment is of paramount importance for farmers. Early detection of stand count provides details on uneven emergence for farmers to make a prompt decision for replanting and applying proper agricultural inputs at defective zones. However, conventional, ground-based stand count methods are costly, time-intensive, and the accuracy of the counting method heavily depends on the selected area. This study focuses on validating the potential application of high resolution unmanned aerial vehicle (UAV) images for detecting the total number of maize plants and stand uniformity soon after maize germination. A field experiment was conducted to evaluate proper image processing algorithm for detecting the maize crop and calculating the distance between adjacent maize plants within a row. In the mosaicked images, the pixels including maize plants were segmented using two methods including excess green index (EXG) method and k-means clustering-segmentation technique. The mean accuracy using EXG method was 46%, however, the k-means clustering-segmentation method satisfactorily identified plants with mean accuracy of 91% in the field. The planting uniformity of maize plants was also evaluated based on three indices including miss index, multiple index, and coefficient of precision. Results showed that plant stand assessment using mosaicked images was closer to the values set on the planting machine. The marginal discrepancy between estimated and observed plant stand count and other indices confirms the high accuracy of UAV mosaicked images in plant density estimation for growers to make appropriate management decisions. • Maize germination and stand uniformity were evaluated accurately using UAV images. • Plant stand uniformity map were developed using high resolution UAV imagery. • The k-means clustering segmentation method could identify maize with high accuracy.

Mapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks

The use of unmanned aerial vehicles (UAVs) in vegetation remote sensing allows a time-flexible and cost-effective acquisition of very high-resolution imagery. Still, current methods for the mapping of forest tree species do not exploit the respective, rich spatial information. Here, we assessed the potential of convolutional neural networks (CNNs) and very high-resolution RGB imagery from UAVs for the mapping of tree species in temperate forests. We used multicopter UAVs to obtain very high-resolution (<2 cm) RGB imagery over 51 ha of temperate forests in the Southern Black Forest region, and the Hainich National Park in Germany. To fully harness the end-to-end learning capabilities of CNNs, we used a semantic segmentation approach (U-net) that concurrently segments and classifies tree species from imagery. With a diverse dataset in terms of study areas, site conditions, illumination properties, and phenology, we accurately mapped nine tree species, three genus-level classes, deadwood, and forest floor (mean F1-score 0.73). A larger tile size during CNN training negatively affected the model accuracies for underrepresented classes. Additional height information from normalized digital surface models slightly increased the model accuracy but increased computational complexity and data requirements. A coarser spatial resolution substantially reduced the model accuracy (mean F1-score of 0.26 at 32 cm resolution). Our results highlight the key role that UAVs can play in the mapping of forest tree species, given that air- and spaceborne remote sensing currently does not provide comparable spatial resolutions. The end-to-end learning capability of CNNs makes extensive preprocessing partly obsolete. The use of large and diverse datasets facilitate a high degree of generalization of the CNN, thus fostering transferability. The synergy of high-resolution UAV imagery and CNN provide a fast and flexible yet accurate means of mapping forest tree species.

Automated crop plant counting from very high-resolution aerial imagery

Knowing before harvesting how many plants have emerged and how they are growing is key in optimizing labour and efficient use of resources. Unmanned aerial vehicles (UAV) are a useful tool for fast and cost efficient data acquisition. However, imagery need to be converted into operational spatial products that can be further used by crop producers to have insight in the spatial distribution of the number of plants in the field. In this research, an automated method for counting plants from very high-resolution UAV imagery is addressed. The proposed method uses machine vision—Excess Green Index and Otsu’s method—and transfer learning using convolutional neural networks to identify and count plants. The integrated methods have been implemented to count 10 weeks old spinach plants in an experimental field with a surface area of 3.2 ha. Validation data of plant counts were available for 1/8 of the surface area. The results showed that the proposed methodology can count plants with an accuracy of 95% for a spatial resolution of 8 mm/pixel in an area up to 172 m2. Moreover, when the spatial resolution decreases with 50%, the maximum additional counting error achieved is 0.7%. Finally, a total amount of 170 000 plants in an area of 3.5 ha with an error of 42.5% was computed. The study shows that it is feasible to count individual plants using UAV-based off-the-shelf products and that via machine vision/learning algorithms it is possible to translate image data in non-expert practical information.

U-Net Convolutional Networks for Mining Land Cover Classification Based on High-Resolution UAV Imagery

Mining activities are the leading cause of deforestation, land-use changes, and pollution. Land use/cover mapping in Vietnam every five years is not useful to monitor land covers in mining areas, especially in the Central Highland region. It is necessary to equip managers with a better tool to monitor and map land cover using high-resolution images. Therefore, the authors proposed using the U-Net convolutional network for land-cover classification based on multispectral Unmanned aerial vehicle (UAV) image in a mining area of Daknong province, Vietnam. An area of 0.5kmx0.8km was used for training and testing seven U-Net models using seven optimizer function types. The final U-Net model can interpret six land cover types: (1) open-case mining lands, (2) old permanent croplands, (3) young permanent croplands, (4) grasslands, (5) bare soils, (6) water bodies. As a result, two models using Nadam and Adadelta optimizer function can be used to classify six land cover types with accuracy higher than 83%, especially in open-case mining lands and polluted streams flowed out from the mining areas. The trained U-Net models can potentially update new land cover types in other mining areas towards monitoring land cover changes in real-time in the future.

Convolutional Neural Networks enable efficient, accurate and fine-grained segmentation of plant species and communities from high-resolution UAV imagery

Recent technological advances in remote sensing sensors and platforms, such as high-resolution satellite imagers or unmanned aerial vehicles (UAV), facilitate the availability of fine-grained earth observation data. Such data reveal vegetation canopies in high spatial detail. Efficient methods are needed to fully harness this unpreceded source of information for vegetation mapping. Deep learning algorithms such as Convolutional Neural Networks (CNN) are currently paving new avenues in the field of image analysis and computer vision. Using multiple datasets, we test a CNN-based segmentation approach (U-net) in combination with training data directly derived from visual interpretation of UAV-based high-resolution RGB imagery for fine-grained mapping of vegetation species and communities. We demonstrate that this approach indeed accurately segments and maps vegetation species and communities (at least 84% accuracy). The fact that we only used RGB imagery suggests that plant identification at very high spatial resolutions is facilitated through spatial patterns rather than spectral information. Accordingly, the presented approach is compatible with low-cost UAV systems that are easy to operate and thus applicable to a wide range of users.

THE CROWN DIAMETER ESTIMATION FROM FIXED WING TYPE OF UAV IMAGERY

Abstract. The forest inventory is an important instrument for sustainable forest management. Canopy Height Model (CHM) and Digital Surface Model (DSM) created from high-resolution UAV (unmanned aerial vehicle) imagery provide possibility to determine tree crown diameters for the whole stand at fast. The goal of this paper is to identify the influence of tree species on the accuracy of estimation of crown diameter from high-resolution UAV imagery. In Plot 1 with coniferous tree species we identified 21 trees from total of 22 trees that leads to a detection rate of 95%. In Plot 1 with deciduous trees species we identified 24 trees from total 34 trees that leads to a detection rate of 71%. The RMSE errors calculated between the reference crown diameters and estimated crown diameters by IWS on Plot 1and Plot 2 were calculated as 0.80 m (RMSE% = 21.85) and 1.89 m (RMSE% = 21.54), respectively. The results didn’t show the significant influence of tree species on the accuracy of estimation of crown diameter from high-resolution UAV imagery. However, result showed the significant influence of tree species on the detection number trees on the plot. The detection of number trees on the plot by method Inverese Watersed Segmentation in software ArcGis is higher for coniferous tree species. It is mainly due to the overlapping crowns.

Assessment of different methods for shadow detection in high-resolution optical imagery and evaluation of shadow impact on calculation of NDVI, and evapotranspiration.

Significant efforts have been made recently in the application of high-resolution remote sensing imagery (i.e., sub-meter) captured by unmanned aerial vehicles (UAVs) for precision agricultural applications for high-value crops such as wine grapes. However, at such high resolution, shadows will appear in the optical imagery effectively reducing the reflectance and emission signal received by imaging sensors. To date, research that evaluates procedures to identify the occurrence of shadows in imagery produced by UAVs is limited. In this study, the performance of four different shadow detection methods used in satellite imagery was evaluated for high-resolution UAV imagery collected over a California vineyard during the Grape Remote sensing Atmospheric Profile and Evapotranspiration eXperiment (GRAPEX) field campaigns. The performance of the shadow detection methods was compared and impacts of shadowed areas on the normalized difference vegetation index (NDVI) and estimated evapotranspiration (ET) using the Two-Source Energy Balance (TSEB) model are presented. The results indicated that two of the shadow detection methods, the supervised classification and index-based methods, had better performance than two other methods. Furthermore, assessment of shadowed pixels in the vine canopy led to significant differences in the calculated NDVI and ET in areas affected by shadows in the high-resolution imagery. Shadows are shown to have the greatest impact on modeled soil heat flux, while net radiation and sensible heat flux are less affected. Shadows also have an impact on the modeled Bowen ratio (ratio of sensible to latent heat) which can be used as an indicator of vine stress level.

Identification of Citrus Trees from Unmanned Aerial Vehicle Imagery Using Convolutional Neural Networks

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.

Mapping land-based oil spills using high spatial resolution unmanned aerial vehicle imagery and electromagnetic induction survey data

Natural oil and gas are important sources of energy worldwide and their exploration and exploitation have significantly increased due to the global demand. The transportation of these valuable resources greatly depends on pipelines; however, pipeline leakages have huge economic and environmental impacts warranting an effective operational methodology for pipeline monitoring. We proposed a method for mapping soil contamination due to pipeline leakage in Dixonville, Alberta, Canada. In particular, very high-resolution unmanned aerial vehicle (UAV) imagery and electromagnetic induction (EM) surveying data were analyzed using a hierarchical object-based random forest (RF) algorithm. In level-1 classification, a land cover map was produced using UAV data. Next, all land cover classes, excluding contaminated soil, were masked out. In level-2 classification, the contaminated soil class was further partitioned into three subclasses representing varying degrees of contamination. Specifically, we proposed a salinity index, named the normalized salinity index, to detect areas of soil contamination. The salinity index proposed herein, as well as several other salinity indices and UAV bands, were used as input features for level-2 classification. An overall classification accuracy of about 77% was achieved for level-2 classification using the proposed method. The results demonstrate that the synergistic use of high spatial resolution UAV imagery and EM data is very promising for detecting soil contamination and examining ecosystem disturbance due to pipeline leakage.

Assessing very high resolution UAV imagery for monitoring forest health during a simulated disease outbreak

Research into remote sensing tools for monitoring physiological stress caused by biotic and abiotic factors is critical for maintaining healthy and highly-productive plantation forests. Significant research has focussed on assessing forest health using remotely sensed data from satellites and manned aircraft. Unmanned aerial vehicles (UAVs) may provide new tools for improved forest health monitoring by providing data with very high temporal and spatial resolutions. These platforms also pose unique challenges and methods for health assessments must be validated before use. In this research, we simulated a disease outbreak in mature Pinus radiata D. Don trees using targeted application of herbicide. The objective was to acquire a time-series simulated disease expression dataset to develop methods for monitoring physiological stress from a UAV platform. Time-series multi-spectral imagery was acquired using a UAV flown over a trial at regular intervals. Traditional field-based health assessments of crown health (density) and needle health (discolouration) were carried out simultaneously by experienced forest health experts. Our results showed that multi-spectral imagery collected from a UAV is useful for identifying physiological stress in mature plantation trees even during the early stages of tree stress. We found that physiological stress could be detected earliest in data from the red edge and near infra-red bands. In contrast to previous findings, red edge data did not offer earlier detection of physiological stress than the near infra-red data. A non-parametric approach was used to model physiological stress based on spectral indices and was found to provide good classification accuracy (weighted kappa=0.694). This model can be used to map physiological stress based on high-resolution multi-spectral data.

Contour Detection for UAV-Based Cadastral Mapping

Unmanned aerial vehicles (UAVs) provide a flexible and low-cost solution for the acquisition of high-resolution data. The potential of high-resolution UAV imagery to create and update cadastral maps is being increasingly investigated. Existing procedures generally involve substantial fieldwork and many manual processes. Arguably, multiple parts of UAV-based cadastral mapping workflows could be automated. Specifically, as many cadastral boundaries coincide with visible boundaries, they could be extracted automatically using image analysis methods. This study investigates the transferability of gPb contour detection, a state-of-the-art computer vision method, to remotely sensed UAV images and UAV-based cadastral mapping. Results show that the approach is transferable to UAV data and automated cadastral mapping: object contours are comprehensively detected at completeness and correctness rates of up to 80%. The detection quality is optimal when the entire scene is covered with one orthoimage, due to the global optimization of gPb contour detection. However, a balance between high completeness and correctness is hard to achieve, so a combination with area-based segmentation and further object knowledge is proposed. The localization quality exhibits the usual dependency on ground resolution. The approach has the potential to accelerate the process of general boundary delineation during the creation and updating of cadastral maps.

Water stress assessment at tree scale: high-resolution thermal UAV imagery acquisition and processing

Water stress assessment can be performed by analyzing thermal images taken onboard Unmanned Aerial Vehicles (UAVs). This study focuses on the acquisition and data extraction of high-resolution UAV-sensed thermal images. The datasets obtained, through computation of spectral indices and image classification, allowed to assess the response to drought of an apple hybrid population submitted to different water regimes. Studies were performed in an experimental apple orchard located in southern France. Flights were planned at solar noon on four successive dates during summer 2013 (40 m altitude, 0.10 m spatial resolution) and at five successive hours of the day, once water stress was established. The high temporal and spatial resolution of images allowed acquiring data at canopy and intra-canopy scales, with a short revisit time. As the miniaturized uncooled thermal camera carried onboard the UAV needs careful correction of radiometry, this was performed by continuous reference to ground thermal targets, while an automatized image processing was carried out. Thanks to the high resolution of the remote images obtained, and the capacity to efficiently delineate each individual tree within the whole trial, it was possible to analyze inter- and intra-canopy thermal variations. Indices extracted from thermal images showed significantly higher canopy temperatures in water restricted trees compared to well-irrigated ones. These differences were related to the severity of water deficit. However, responses also varied significantly according to the genotype. The image-based variables in apple trees constitute a basis for a further finely tuned analysis of the differential response to water stress.