Comprehensive Direct Georeferencing of Aerial Images for Unmanned Aerial Systems Applications

Optical image sensors are the most common remote sensing data acquisition devices present in Unmanned Aerial Systems (UAS). In this context, assigning a location in a geographic frame of reference to the acquired image is a necessary task in the majority of the applications. This process is denominated direct georeferencing when ground control points are not used. Despite it applies simple mathematical fundamentals, the complete direct georeferencing process involves much information, such as camera sensor characteristics, mounting measurements, attitude and position of the UAS, among others. In addition, there are many rotations and translations between the different reference frames, among many other details, which makes the whole process a considerable complex operation. Another problem is that manufacturers and software tools may use different reference frames posing additional difficulty when implementing the direct georeferencing. As this information is spread among many sources, researchers may face difficulties on having a complete vision of the method. In fact, there is absolutely no paper in the literature that explain this process in a comprehensive way. In order to supply this implicit demand, this paper presents a comprehensive method for direct georeferencing of aerial images acquired by cameras mounted on UAS, where all required information, mathematical operations and implementation steps are explained in detail. Finally, in order to show the practical use of the method and to prove its accuracy, both simulated and real flights were performed, where objects of the acquired images were georeferenced.

Download Full-text

Deep Learning-Based Object Detection for Unmanned Aerial Systems (UASs)-Based Inspections of Construction Stormwater Practices

Sensors ◽

10.3390/s21082834 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2834

Author(s):

Billur Kazaz ◽

Subhadipto Poddar ◽

Saeed Arabi ◽

Michael A. Perez ◽

Anuj Sharma ◽

...

Keyword(s):

Deep Learning ◽

Object Detection ◽

Pollution Prevention ◽

Aerial Images ◽

Unmanned Aerial Systems ◽

Construction Sites ◽

State Regulations ◽

Novel Approach ◽

Model Training ◽

Aerial Systems

Construction activities typically create large amounts of ground disturbance, which can lead to increased rates of soil erosion. Construction stormwater practices are used on active jobsites to protect downstream waterbodies from offsite sediment transport. Federal and state regulations require routine pollution prevention inspections to ensure that temporary stormwater practices are in place and performing as intended. This study addresses the existing challenges and limitations in the construction stormwater inspections and presents a unique approach for performing unmanned aerial system (UAS)-based inspections. Deep learning-based object detection principles were applied to identify and locate practices installed on active construction sites. The system integrates a post-processing stage by clustering results. The developed framework consists of data preparation with aerial inspections, model training, validation of the model, and testing for accuracy. The developed model was created from 800 aerial images and was used to detect four different types of construction stormwater practices at 100% accuracy on the Mean Average Precision (MAP) with minimal false positive detections. Results indicate that object detection could be implemented on UAS-acquired imagery as a novel approach to construction stormwater inspections and provide accurate results for site plan comparisons by rapidly detecting the quantity and location of field-installed stormwater practices.

Download Full-text

Accuracy of 3D Landscape Reconstruction without Ground Control Points Using Different UAS Platforms

Drones ◽

10.3390/drones4020013 ◽

2020 ◽

Vol 4 (2) ◽

pp. 13 ◽

Cited By ~ 4

Author(s):

Margaret Kalacska ◽

Oliver Lucanus ◽

J. Pablo Arroyo-Mora ◽

Étienne Laliberté ◽

Kathryn Elmer ◽

...

Keyword(s):

Low Cost ◽

Ground Control ◽

Unmanned Aerial Systems ◽

Control Points ◽

Model Errors ◽

Positional Accuracy ◽

Ground Control Points ◽

Digital Elevation ◽

High Level ◽

Aerial Systems

The rapid increase of low-cost consumer-grade to enterprise-level unmanned aerial systems (UASs) has resulted in the exponential use of these systems in many applications. Structure from motion with multiview stereo (SfM-MVS) photogrammetry is now the baseline for the development of orthoimages and 3D surfaces (e.g., digital elevation models). The horizontal and vertical positional accuracies (x, y and z) of these products in general, rely heavily on the use of ground control points (GCPs). However, for many applications, the use of GCPs is not possible. Here we tested 14 UASs to assess the positional and within-model accuracy of SfM-MVS reconstructions of low-relief landscapes without GCPs ranging from consumer to enterprise-grade vertical takeoff and landing (VTOL) platforms. We found that high positional accuracy is not necessarily related to the platform cost or grade, rather the most important aspect is the use of post-processing kinetic (PPK) or real-time kinetic (RTK) solutions for geotagging the photographs. SfM-MVS products generated from UAS with onboard geotagging, regardless of grade, results in greater positional accuracies and lower within-model errors. We conclude that where repeatability and adherence to a high level of accuracy are needed, only RTK and PPK systems should be used without GCPs.

Download Full-text

Long‐duration fully autonomous operation of rotorcraft unmanned aerial systems for remote‐sensing data acquisition

Journal of Field Robotics ◽

10.1002/rob.21898 ◽

2019 ◽

Vol 37 (1) ◽

pp. 137-157 ◽

Cited By ~ 1

Author(s):

Danylo Malyuta ◽

Christian Brommer ◽

Daniel Hentzen ◽

Thomas Stastny ◽

Roland Siegwart ◽

...

Keyword(s):

Remote Sensing ◽

Data Acquisition ◽

Remote Sensing Data ◽

Unmanned Aerial Systems ◽

Sensing Data ◽

Autonomous Operation ◽

Long Duration ◽

Aerial Systems

Download Full-text

Assessing the Accuracy of Digital Surface Models Derived from Optical Imagery Acquired with Unmanned Aerial Systems

Drones ◽

10.3390/drones3010015 ◽

2019 ◽

Vol 3 (1) ◽

pp. 15 ◽

Cited By ~ 18

Author(s):

Salvatore Manfreda ◽

Petr Dvorak ◽

Jana Mullerova ◽

Sorin Herban ◽

Pietro Vuono ◽

...

Keyword(s):

3D Model ◽

Low Cost ◽

Three Dimensional ◽

Careful Consideration ◽

Ground Control ◽

Unmanned Aerial Systems ◽

Control Points ◽

Earthen Dam ◽

Ground Control Points ◽

Aerial Systems

Small unmanned aerial systems (UASs) equipped with an optical camera are a cost-effective strategy for topographic surveys. These low-cost UASs can provide useful information for three-dimensional (3D) reconstruction even if they are equipped with a low-quality navigation system. To ensure the production of high-quality topographic models, careful consideration of the flight mode and proper distribution of ground control points are required. To this end, a commercial UAS was adopted to monitor a small earthen dam using different combinations of flight configurations and by adopting a variable number of ground control points (GCPs). The results highlight that optimization of both the choice and combination of flight plans can reduce the relative error of the 3D model to within two meters without the need to include GCPs. However, the use of GCPs greatly improved the quality of the topographic survey, reducing error to the order of a few centimeters. The combined use of images extracted from two flights, one with a camera mounted at nadir and the second with a 20° angle, was found to be beneficial for increasing the overall accuracy of the 3D model and especially the vertical precision.

Download Full-text

Deep Learning Based Wildfire Event Object Detection from 4K Aerial Images Acquired by UAS

AI ◽

10.3390/ai1020010 ◽

2020 ◽

Vol 1 (2) ◽

pp. 166-179 ◽

Cited By ~ 4

Author(s):

Ziyang Tang ◽

Xiang Liu ◽

Hanlin Chen ◽

Joseph Hupy ◽

Baijian Yang

Keyword(s):

Deep Learning ◽

High Resolution ◽

Object Detection ◽

Aerial Images ◽

Unmanned Aerial Systems ◽

Computer Assisted ◽

Visual Interpretation ◽

Two Phase ◽

Aerial Systems ◽

Spot Fires

Unmanned Aerial Systems, hereafter referred to as UAS, are of great use in hazard events such as wildfire due to their ability to provide high-resolution video imagery over areas deemed too dangerous for manned aircraft and ground crews. This aerial perspective allows for identification of ground-based hazards such as spot fires and fire lines, and to communicate this information with fire fighting crews. Current technology relies on visual interpretation of UAS imagery, with little to no computer-assisted automatic detection. With the help of big labeled data and the significant increase of computing power, deep learning has seen great successes on object detection with fixed patterns, such as people and vehicles. However, little has been done for objects, such as spot fires, with amorphous and irregular shapes. Additional challenges arise when data are collected via UAS as high-resolution aerial images or videos; an ample solution must provide reasonable accuracy with low delays. In this paper, we examined 4K ( 3840 × 2160 ) videos collected by UAS from a controlled burn and created a set of labeled video sets to be shared for public use. We introduce a coarse-to-fine framework to auto-detect wildfires that are sparse, small, and irregularly-shaped. The coarse detector adaptively selects the sub-regions that are likely to contain the objects of interest while the fine detector passes only the details of the sub-regions, rather than the entire 4K region, for further scrutiny. The proposed two-phase learning therefore greatly reduced time overhead and is capable of maintaining high accuracy. Compared against the real-time one-stage object backbone of YoloV3, the proposed methods improved the mean average precision(mAP) from 0 . 29 to 0 . 67 , with an average inference speed of 7.44 frames per second. Limitations and future work are discussed with regard to the design and the experiment results.

Download Full-text

Using Digital Surface Models from UAS Imagery of Fire Damaged Sphagnum Peatlands for Monitoring and Hydrological Restoration

Drones ◽

10.3390/drones2040045 ◽

2018 ◽

Vol 2 (4) ◽

pp. 45 ◽

Cited By ~ 5

Author(s):

Shannon de Roos ◽

Darren Turner ◽

Arko Lucieer ◽

David M.J.S. Bowman

Keyword(s):

Unmanned Aerial Systems ◽

Control Points ◽

Hydrological Models ◽

Slow Recovery ◽

Ground Control Points ◽

Surface Models ◽

Good Potential ◽

Northern Peatlands ◽

Aerial Systems

The sub-alpine and alpine Sphagnum peatlands in Australia are geographically constrained to poorly drained areas c. 1000 m a.s.l. Sphagnum is an important contributor to the resilience of peatlands; however, it is also very sensitive to fire and often shows slow recovery after being damaged. Recovery is largely dependent on a sufficient water supply and impeded drainage. Monitoring the fragmented areas of Australia’s peatlands can be achieved by capturing ultra-high spatial resolution imagery from an unmanned aerial systems (UAS). High resolution digital surface models (DSMs) can be created from UAS imagery, from which hydrological models can be derived to monitor hydrological changes and assist with rehabilitation of damaged peatlands. One of the constraints of the use of UAS is the intensive fieldwork required. The need to distribute ground control points (GCPs) adds to fieldwork complexity. GCPs are often used for georeferencing of the UAS imagery, as well as for removal of artificial tilting and doming of the photogrammetric model created by camera distortions. In this study, Tasmania’s northern peatlands were mapped to test the viability of creating hydrological models. The case study was further used to test three different GCP scenarios to assess the effect on DSM quality. From the five scenarios, three required the use of all (16–20) GCPs to create accurate DSMs, whereas the two other sites provided accurate DSMs when only using four GCPs. Hydrological maps produced with the TauDEM tools software package showed high visual accuracy and a good potential for rehabilitation guidance, when using ground- controlled DSMs.

Download Full-text

Application of Postprocessing Kinematic Methods with UAS Remote Sensing in Forest Ecosystems

Journal of Forestry ◽

10.1093/jofore/fvab021 ◽

2021 ◽

Author(s):

Zachary M Miller ◽

Joseph Hupy ◽

Aishwarya Chandrasekaran ◽

Guofan Shao ◽

Songlin Fei

Keyword(s):

Remote Sensing ◽

Data Collection ◽

Ground Control ◽

Unmanned Aerial Systems ◽

Control Points ◽

Gps Technology ◽

Ground Control Points ◽

Forested Areas ◽

Rapid Deployment ◽

Aerial Systems

Abstract Unmanned Aerial Systems (UAS) serve as an excellent remote-sensing platform to fulfill an aerial imagery data collection niche previously unattainable in forestry by satellites and manned aircraft. However, for UAS-derived data to be spatially representative, a precise network of ground control points (GCP) is often required, which can be tedious and limit the logistical benefits of UAS rapid deployment capabilities, especially in densely forested areas. Therefore, methods for efficient data collection without GCPs are highly desired in UAS remote sensing. Here, we demonstrate the use of postprocessing kinematic (PPK) technology to obtain subcentimeter precision in datasets of forested areas without the need for placing GCPs. We evaluated two key measures, positional variability and time efficiency, of the PPK technology by comparing them to traditional GCP methods. Results show that PPK displays consistently higher positional precision than traditional GCP approaches. Moreover, PPK surveys and processing take less time to complete than traditional GCP methods and require fewer logistical steps, especially in image acquisition. The time and resource savings with PPK as compared to GCP processing are undeniable. We conclude that PPK technology provides a practical means to produce precise aerial forest surveys. Study Implications Unmanned Aerial Systems (UAS) have enormous potential for lowering costs and streamlining practices in the forestry management and research community. Despite this potential, however, UAS forestry applications have been limited in scope and precision because of a reliance on using ground-based GPS technology to survey ground control points (GCP), which are time intensive and require an open view of the sky. Such a need for a ground-based GCP survey, along with forest canopy serving to limit and scatter incoming GPS signals, diminishes the potential for rapid deployment and precision mapping offered by UAS. Fortunately, Postprocessing-Kinematic (PPK) GPS technology lowers these barriers by providing the means to seamlessly gather highly precise UAS imagery without needing to conduct time-intensive ground-based surveys. This study compares the precision and time-effectiveness between traditional GCP marker surveys and PPK correction methods.

Download Full-text

BLOB-Based AOMs: A Method for the Extraction of Crop Data from Aerial Images of Cotton

Agriculture ◽

10.3390/agriculture10010019 ◽

2020 ◽

Vol 10 (1) ◽

pp. 19

Author(s):

Andrew Young ◽

James Mahan ◽

William Dodge ◽

Paxton Payton

Keyword(s):

Plant Growth ◽

Growth And Development ◽

Environmental Changes ◽

Spatial Scales ◽

Computer Software ◽

Aerial Images ◽

Unmanned Aerial Systems ◽

Plant Growth And Development ◽

Temporal And Spatial ◽

Aerial Systems

The use of aerial imagery in agriculture is increasing. Improvements in unmanned aerial systems (UASs) and the hardware and software used to analyze imagery are presenting new options for agricultural studies. One of the challenges associated with improving crop performance under water deficit conditions is the increased variability in the growth and development inherent in low water settings. The nature of plant growth and development under water deficits makes it difficult to monitor the response to environmental changes. Small field and plot-level experiments are often variable enough that averages of seasonal crop characteristics may be of limited value to the researcher. This variability leads to a desire to resolve fields on finer temporal and spatial scales. While UAS imagery provides an ability to monitor the crop on a useful temporal scale, the spatial scale is still difficult to resolve. In this study, an automated computer software framework was developed to facilitate resolving field and plot-level crop imagery to finer spatial resolutions. The method uses a Binary Large Object (BLOB)-based algorithm to automate the generation of areas of measurement (AOMs) as a tool for crop analysis. The use of the BLOB-based system is demonstrated in the analysis of plots of cotton grown in Lubbock, Texas, during the summer of 2018. The method allowed the creation and analysis of 1133 AOMs from the plots and the extraction of agronomic data that described plant growth and development.

Download Full-text

Analysis of Point Cloud Generation from UAS Images

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsannals-ii-1-45-2014 ◽

2014 ◽

Vol II-1 ◽

pp. 45-51 ◽

Cited By ~ 7

Author(s):

S. Ostrowski ◽

G. Jóźków ◽

C. Toth ◽

B. Vander Jagt

Keyword(s):

Local Coordinate System ◽

Field Tests ◽

Point Clouds ◽

Aerial Images ◽

Unmanned Aerial Systems ◽

Surface Model ◽

Geospatial Information ◽

Software Packages ◽

The Ohio State University ◽

Aerial Systems

Unmanned Aerial Systems (UAS) allow for the collection of low altitude aerial images, along with other geospatial information from a variety of companion sensors. The images can then be processed using sophisticated algorithms from the Computer Vision (CV) field, guided by the traditional and established procedures from photogrammetry. Based on highly overlapped images, new software packages which were specifically developed for UAS technology can easily create ground models, such as Point Clouds (PC), Digital Surface Model (DSM), orthoimages, etc. The goal of this study is to compare the performance of three different software packages, focusing on the accuracy of the 3D products they produce. Using a Nikon D800 camera installed on an ocotocopter UAS platform, images were collected during subsequent field tests conducted over the Olentangy River, north from the Ohio State University campus. Two areas around bike bridges on the Olentangy River Trail were selected because of the challenge the packages would have in creating accurate products; matching pixels over the river and dense canopy on the shore presents difficult scenarios to model. Ground Control Points (GCP) were gathered at each site to tie the models to a local coordinate system and help assess the absolute accuracy for each package. In addition, the models were also relatively compared to each other using their PCs.

Download Full-text

Geovisualization of the Excavation Process in the Lesvos Petrified Forest, Greece Using Augmented Reality

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9060374 ◽

2020 ◽

Vol 9 (6) ◽

pp. 374

Author(s):

Ermioni-Eirini Papadopoulou ◽

Vlasios Kasapakis ◽

Christos Vasilakos ◽

Apostolos Papakonstantinou ◽

Nikolaos Zouros ◽

...

Keyword(s):

Augmented Reality ◽

Unmanned Aerial Systems ◽

Rapid Acquisition ◽

Ground Control Points ◽

Excavation Process ◽

Spatiotemporal Changes ◽

Surrounding Space ◽

User Friendly ◽

Aerial Systems ◽

2D And 3D

Augmented reality (AR), in conjunction with 3D geovisualization methods, can provide significant support in monitoring geoconservation activities in protected geosites, such as the excavation process in fossil sites. The excavation process requires a monitoring methodology that will provide a complete and accurate overview of the fossils, their dimensions, and location within the different pyroclastic horizons, and the progress of the excavation works. The main purpose of this paper is the development of a user-friendly augmented map application, specifically designed for tracking the position of petrified tree trunks, providing information for their geometric features, and mapping the spatiotemporal changes occurring in the surrounding space. It also aims to probe whether the rapid acquisition of a 4K video can generate cartographic derivatives of petrified findings during a geosite excavation. A database accumulated 2D and 3D cartographic information, while the geovisualization environment displayed the surface alterations, at two scales: a) 1:500 (excavation area) and b) 1:50 (trench level). Unmanned aerial systems (UASs), used for data acquisition in three excavation periods, consisted of two flights at two different altitudes: one to record changes throughout the study area and the other to provide information on trunks at trench level, via a high-resolution (4K) video. Image-based 3D modeling followed, in which image georeferencing was conducted with ground control points (GCPs). Finally, 2D and 3D geovisualizations were created to depict the excavation changes through time. The cartographic products generated at two cartographic scales depicted the spatiotemporal changes of the excavation.

Download Full-text