Low-cost Unmanned Aerial Vehicle System Research Articles

Improved estimation of aboveground biomass in rubber plantations by fusing spectral and textural information from UAV-based RGB imagery

Aboveground biomass (AGB), as a crucial indicator of forest growth and quality, plays an important role in monitoring the global carbon cycle and forest health. Rapid, accurate, and non-destructive assessment of AGB in rubber plantations is beneficial not only for predicting rubber yield but also for understanding the carbon storage potential in tropical areas. Previous studies have employed spectral information and texture features derived from unmanned aerial vehicle data to estimate the AGB of mangroves. However, few studies systematically assessed the effects of grey level co-occurrence matrix parameters for extracting texture features on AGB estimation in rubber plantations. Whether the combination of spectral information and texture features with suitable grey level co-occurrence matrix parameters selection derived from a low-cost unmanned aerial vehicle system can improve the AGB estimation accuracy remains unclear. To this end, this study evaluated the performance of spectral information and texture features derived from UAV-based high-resolution RGB imagery with different textural parameter settings. Three types of machine learning algorithms (support vector regression; random forest; extreme gradient boosting regressor) and stepwise multiple linear regression were used to compare and analyze their performance for AGB estimation of rubber plantations. The results indicated that appropriate textural parameter selection significantly improved the AGB estimation accuracy when using texture features alone. Among four regression techniques, stepwise multiple linear regression exhibited poor performance, while support vector regression performed the best. The best estimation accuracy (R2 = 0.752, RMSE = 28.72 t/ha) was obtained by support vector regression when using the combination of spectral information and texture features with the textural parameters of the orientation of 135°, displacement of 2 pixels, and moving window size parameter of 7 × 7 pixels. The findings suggested that the AGB estimation accuracy can be further improved by the integration of spectral information and texture features when considering appropriate textural parameters.

Multispectral Drone Imagery and SRGAN for Rapid Phenotypic Mapping of Individual Chinese Cabbage Plants.

The phenotypic parameters of crop plants can be evaluated accurately and quickly using an unmanned aerial vehicle (UAV) equipped with imaging equipment. In this study, hundreds of images of Chinese cabbage (Brassica rapa L. ssp. pekinensis) germplasm resources were collected with a low-cost UAV system and used to estimate cabbage width, length, and relative chlorophyll content (soil plant analysis development [SPAD] value). The super-resolution generative adversarial network (SRGAN) was used to improve the resolution of the original image, and the semantic segmentation network Unity Networking (UNet) was used to process images for the segmentation of each individual Chinese cabbage. Finally, the actual length and width were calculated on the basis of the pixel value of the individual cabbage and the ground sampling distance. The SPAD value of Chinese cabbage was also analyzed on the basis of an RGB image of a single cabbage after background removal. After comparison of various models, the model in which visible images were enhanced with SRGAN showed the best performance. With the validation set and the UNet model, the segmentation accuracy was 94.43%. For Chinese cabbage dimensions, the model was better at estimating length than width. The R2 of the visible-band model with images enhanced using SRGAN was greater than 0.84. For SPAD prediction, the R2 of the model with images enhanced with SRGAN was greater than 0.78. The root mean square errors of the 3 semantic segmentation network models were all less than 2.18. The results showed that the width, length, and SPAD value of Chinese cabbage predicted using UAV imaging were comparable to those obtained from manual measurements in the field. Overall, this research demonstrates not only that UAVs are useful for acquiring quantitative phenotypic data on Chinese cabbage but also that a regression model can provide reliable SPAD predictions. This approach offers a reliable and convenient phenotyping tool for the investigation of Chinese cabbage breeding traits.

Individual tree detection and species classification of Amazonian palms using UAV images and deep learning

Information regarding the spatial distribution of palm trees in tropical forests is crucial for commercial exploitation and management. However, spatially continuous knowledge of palms occurrence is scarce and difficult to obtain with conventional approaches such as field inventories. Here, we developed a new method to map Amazonian palm species at the individual tree crown (ITC) level using RGB images acquired by a low-cost unmanned aerial vehicle (UAV). Our approach is based on morphological operations performed in the score maps of palm species derived from a fully convolutional neural network model. We first constructed a labeled dataset by dividing the study area (135 ha within an old-growth Amazon forest) into 28 plots of 250 m × 150 m. Then, we manually outlined all palm trees seen in RGB images with 4 cm pixels. We identified three palm species: Attalea butyracea, Euterpe precatoria and Iriartea deltoidea. We randomly selected 22 plots (80%) for training and six plots (20%) for testing. We changed the plots for training and testing to evaluate the variability in the classification accuracy and assess model generalization. Our method outperformed the average producer’s accuracy of conventional patch-wise semantic segmentation (CSS) in 4.7%. Moreover, our method correctly identified, on average, 34.7 percentage points more ITCs than CSS, which tended to merge trees that are close to each other. The producer’s accuracy of A. butyracea, E. precatoria and I. deltoidea was 78.6 ± 5.5%, 98.6 ± 1.4% and 96.6 ± 3.4%, respectively. Fortunately, one of the most exploited and commercialized palm species in the Amazon (E. precatoria, a.k.a, Açaí) was mapped with the highest classification accuracy. Maps of E. precatoria derived from low-cost UAV systems can support management projects and community-based forest monitoring programs in the Amazon.

Assessing the effect of flight altitude and overlap on orthoimage generation for UAV estimates of coastal wetlands

There has been a constant increase in technology regarding unmanned aerial vehicle (UAV) systems in the last decade; yet the possibility of surveying large areas with such aerial platforms has been hampered by their low endurance. This situation has been exacerbated in low institutional capacity countries with high biodiversity coastal environments where constant monitoring is required for conservation purposes. The objective of this study was hence to determine an optimal flight mission over an initial area of 40 ha of coastal wetlands using a low-cost UAV system. The UAV missions were planned at altitudes of 60, 80, 100, and 120 m. Several orthoimages were generated with different along/across track overlaps (in intervals of 10% from 40 to 90%) in order to determine the minimum flight duration and computational efficiency. Results indicated that flight altitude and across track overlap were the most relevant variables in terms of flight distance, flight duration, number of generated images, and computer processing time. The optimal flight mission was found to be at 120-m altitude with an along/across track overlap of 60/50%. Based on the aforementioned parameters, we were able to survey a larger area of 200 ha with minimum flight duration and computer processing time. Our study highlights the feasibility and limitations of using a consumer-grade UAV in order to assess coastal wetland areas rapidly when field-based surveys approaches are not possible.

An Improved Ground Control Point Configuration for Digital Surface Model Construction in a Coal Waste Dump Using an Unmanned Aerial Vehicle System

Coal production in opencast mining generates substantial waste materials, which are typically delivered to an on-site waste dump. As a large artificial loose pile, such dumps have a special multi-berm structure accompanied by some security issues due to wind and water erosion. Highly accurate digital surface models (DSMs) provide the basic information for detection and analysis of elevation change. Low-cost unmanned aerial vehicle systems (UAS) equipped with a digital camera have become a useful tool for DSM reconstruction. To achieve high-quality UAS products, consideration of the number and configuration of ground control points (GCPs) is required. Although increasing of GCPs will improve the accuracy of UAS products, the workload of placing GCPs is difficult and laborious, especially in a multi-berm structure such as a waste dump. Thus, the aim of this study is to propose an improved GCPs configuration to generate accurate DSMs of a waste dump to obtain accurate elevation information, with less time and fewer resources. The results of this study suggest that: (1) the vertical accuracy of DSMs is affected by the number of GCPs and their configuration. (2) Under a set number of GCPs, a difference of accuracy is obtained when the GCPs are located on different berms. (3) For the same number of GCPs, the type 4 (GCPs located on the 1st and 4th berms) in the study is the best configuration for higher vertical accuracy compared with other types. The principal objective of this study provides an effective GCP configuration for DSM construction of coal waste dumps with four berms, and also a reference for engineering piles using multiple berms.

NRLI-UAV: Non-rigid registration of sequential raw laser scans and images for low-cost UAV LiDAR point cloud quality improvement

Accurate registration of light detection and ranging (LiDAR) point clouds and images is a prerequisite for integrating the spectral and geometrical information collected by low-cost unmanned aerial vehicle (UAV) systems. Most registration approaches take the directly georeferenced LiDAR point cloud as a rigid body, based on the assumption that the high-precision positioning and orientation system (POS) in the LiDAR system provides sufficient precision, and that the POS errors are negligible. However, due to the large errors of the low-precision POSs commonly used in the low-cost UAV LiDAR systems (ULSs), dramatic deformation may exist in the directly georeferenced ULS point cloud, resulting in non-rigid transformation between the images and the deformed ULS point cloud. As a result, registration may fail when using a rigid transformation between the images and the directly georeferenced LiDAR point clouds. To address this problem, we proposed NRLI-UAV, which is a non-rigid registration method for registration of sequential raw laser scans and images collected by low-cost UAV systems. NRLI-UAV is a two-step registration method that exploits trajectory correction and discrepancy minimization between the depths derived from structure from motion (SfM) and the raw laser scans to achieve LiDAR point cloud quality improvement. Firstly, the coarse registration procedure utilizes global navigation satellite system (GNSS) and inertial measurement unit (IMU)-aided SfM to obtain accurate image orientation and corrects the errors of the low-precision POS. Secondly, the fine registration procedure transforms the original 2D-3D registration to 3D-3D registration. This is performed by setting the oriented images as the reference, and iteratively minimizing the discrepancy between the depth maps derived from SfM and the raw laser scans, resulting in accurate registration between the images and the LiDAR point clouds. In addition, an improved LiDAR point cloud is generated in the mapping frame. Experiments were conducted with data collected by a low-cost UAV system in three challenging scenes to evaluate NRLI-UAV. The final registration errors of the images and the LiDAR point cloud are less than one pixel in image space and less than 0.13 m in object space. The LiDAR point cloud quality was also evaluated by plane fitting, and the results show that the LiDAR point cloud quality is improved by 8.8 times from 0.45 m (root-mean-square error [RMSE] of plane fitting) to 0.05 m (RMSE of plane fitting) using NRLI-UAV, demonstrating a high level of automation, robustness, and accuracy.

A Special Issue on Hyperspectral Imaging [From the Guest Editors

Hyperspectral imaging (HSI) for geoscience remote sensing and Earth observation has been around since the mid-1980s. For many years, it was the purview of research laboratories and proof-of-concept satellite missions. Hundreds of research articles have been published exploring algorithms for analysis and demonstrating applications across many Earth observational fields of interest. Most have focused on a relatively small group of publicly available data sets due to the high cost of sensor operation and collection of ground reference data necessary for algorithm and product evaluation. More recently, as the cost of focal planes and sensor technology has decreased, together with the emergence of inexpensive unmanned aerial vehicle (UAV) systems and Cube- Sats/smallSats in space access, the availability of hyperspectral imagery is poised to grow dramatically. Several airborne and spaceborne systems have been deployed or are being planned. Commercial remote sensing and image processing software systems provide more support and extended functionality for such data, while the practical use of hyperspectral data in both commercial and scientific applications has increased. The community now has access to relatively low-cost UAV systems and data and will soon see more routine availability of space-based HSI data. This special issue of IEEE Geoscience and Remote Sensing Magazine on HSI was put together based on the recognition that the field is on the cusp of expanded data availability. While formerly the domain of a relatively small group of specialists, it is anticipated HSI data will soon become available to a wider range of scientists and data users. This special issue was compiled to bring together a comprehensive look at the characteristics, phenomenology, algorithms, and applications as a resource for practitioners and students who wish to gain familiarity with the field.

Improved estimation of aboveground biomass in wheat from RGB imagery and point cloud data acquired with a low-cost unmanned aerial vehicle system

BackgroundAboveground biomass (AGB) is a widely used agronomic parameter for characterizing crop growth status and predicting grain yield. The rapid and accurate estimation of AGB in a non-destructive way is useful for making informed decisions on precision crop management. Previous studies have investigated vegetation indices (VIs) and canopy height metrics derived from Unmanned Aerial Vehicle (UAV) data to estimate the AGB of various crops. However, the input variables were derived either from one type of data or from different sensors on board UAVs. Whether the combination of VIs and canopy height metrics derived from a single low-cost UAV system can improve the AGB estimation accuracy remains unclear. This study used a low-cost UAV system to acquire imagery at 30 m flight altitude at critical growth stages of wheat in Rugao of eastern China. The experiments were conducted in 2016 and 2017 and involved 36 field plots representing variations in cultivar, nitrogen fertilization level and sowing density. We evaluated the performance of VIs, canopy height metrics and their combination for AGB estimation in wheat with the stepwise multiple linear regression (SMLR) and three types of machine learning algorithms (support vector regression, SVR; extreme learning machine, ELM; random forest, RF).ResultsOur results demonstrated that the combination of VIs and canopy height metrics improved the estimation accuracy for AGB of wheat over the use of VIs or canopy height metrics alone. Specifically, RF performed the best among the SMLR and three machine learning algorithms regardless of using all the original variables or selected variables by the SMLR. The best accuracy (R2 = 0.78, RMSE = 1.34 t/ha, rRMSE = 28.98%) was obtained when applying RF to the combination of VIs and canopy height metrics.ConclusionsOur findings implied that an inexpensive approach consisting of the RF algorithm and the combination of RGB imagery and point cloud data derived from a low-cost UAV system at the consumer-grade level can be used to improve the accuracy of AGB estimation and have potential in the practical applications in the rapid estimation of other growth parameters.

3D MODEL GENERATION USING OBLIQUE IMAGES ACQUIRED BY UAV

Abstract. In recent years, many studies revealed the advantages of using airborne oblique images for obtaining improved 3D city models (including façades and building footprints). Here the acquisition and use of oblique images from a low cost and open source Unmanned Aerial Vehicle (UAV) for the 3D high-level-of-detail reconstruction of historical architectures is evaluated. The critical issues of such acquisitions (flight planning strategies, ground control points distribution, etc.) are described. Several problems should be considered in the flight planning: best approach to cover the whole object with the minimum time of flight; visibility of vertical structures; occlusions due to the context; acquisition of all the parts of the objects (the closest and the farthest) with similar resolution; suitable camera inclination, and so on. In this paper a solution is proposed in order to acquire oblique images with one only flight. The data processing was realized using Structure-from-Motion-based approach for point cloud generation using dense image-matching algorithms implemented in an open source software. The achieved results are analysed considering some check points and some reference LiDAR data. The system was tested for surveying a historical architectonical complex: the “Sacro Mo nte di Varallo Sesia” in north-west of Italy. This study demonstrates that the use of oblique images acquired from a low cost UAV system and processed through an open source software is an effective methodology to survey cultural heritage, characterized by limited accessibility, need for detail and rapidity of the acquisition phase, and often reduced budgets.

Remote estimation of canopy height and aboveground biomass of maize using high-resolution stereo images from a low-cost unmanned aerial vehicle system

Canopy height (Hcanopy) and aboveground biomass (AGB) of crops are two basic agro-ecological indicators that can provide important indications on the growth, light use efficiency, and carbon stocks in agro-ecosystems. In this study, hundreds of stereo images with very high resolution were collected to estimate Hcanopy and AGB of maize using a low-cost unmanned aerial vehicle (UAV) system. Millions of point clouds that are related to the structure from motion (SfM) were produced from the UAV stereo images through a photogrammetric workflow. Metrics that are commonly used in airborne laser scanning (ALS) were calculated from the SfM point clouds and were tested in the estimation of maize parameters for the first time. In addition, the commonly used spectral vegetation indices calculated from the UAV orthorectified image were also tested. Estimation models were established based on the UAV variables and field measurements with cross validation, during which the performance of the UAV variables was quantified. Finally, the following results were achieved: (1) the spatial patterns of maize Hcanopy and AGB were predicted by a multiple stepwise linear (SWL) regression model (R2=0.88, rRMSE=6.40%) and a random forest regression (RF) model (R2=0.78, rRMSE=16.66%), respectively. (2) The UAV-estimated maize parameters were proved to be comparable to the field measurements with a mean error (ME) of 0.11m for Hcanopy, and 0.05kg/m2 for AGB. (3) The SfM point metrics, especially the mean point height (Hmean) greatly contributed to the estimation model of maize Hcanopy and AGB, which can be promising indicators in the detection of maize biophysical parameters. To conclude, the variations in spectral and structural attributes for maize canopy should be simultaneously considered when only simple RGB images are available for estimating maize AGB. This study provides some suggestions on how to make full use of the low-cost and high-resolution UAV stereo images in precision agro-ecological applications and management.

Supporting the annual international black-faced spoonbill census with a low-cost unmanned aerial vehicle

The black-faced spoonbill (BFS) is a globally endangered species. The annual international BFS census (IBFSC) thus serves as an important initiative to manage and protect the population of this bird. This work attempts to investigate the feasibility of supporting the annual IBFSC with a low-cost unmanned aerial vehicle system (UAVS). A total of six missions were completed to investigate various locations and areas from November 2012 to April 2013, when BFS transited at Taijiang National Park. The flight plan for each mission was made through the automatic mission planning system. All photographs taken in one mission were stitched to a seamless and color-balanced mosaic that can be geo-referenced and displayed on a Web-based platform, such as Google Earth. A close-up photograph of a few BFSs was acquired at a low altitude of 50m to validate the proposed approach of image processing, including unsupervised classification, hit or miss transform and binary large object analysis. The results show that the selection of one statistical attribute (maximum value in red channel) and two geometrical attributes (size and circularity) is appropriate for identifying BFS without ambiguity. The success of this work encourages us to conduct a large-scale deployment of UAVS in the coming IBFSC.

A Survey and Categorization of Small Low-Cost Unmanned Aerial Vehicle System Identification

Remote sensing has traditionally be done with satellites and manned aircraft. While these methods can yield useful scientific data, satellites and manned aircraft have limitations in data frequency...

UAV-based multi-sensor data fusion processing

This article presents a mathematical model for an Unmanned Aerial Vehicle (UAV)-based, multi-sensor data integration. As background, this article first discusses the design and the implementation of a low-cost civilian UAV system, including its field flight validation, system calibration and mapping accuracy evaluation. Then, the photogrammetry-based mathematical model is developed. This multi-sensor, mathematical model reveals that the boresight matrix in a low-cost UAV system does not remain constant. This contradicts the practice in traditional airborne mapping systems where the boresight matrix is assumed to be a constant over an entire mission. Thus, to achieve highly accurate mapping, exterior orientation parameters (EOPs) for each video frame in a low-cost UAV mapping system have to be estimated. This model can achieve a planimetric mapping accuracy using 1-2 pixels when compared with the United States Geological Survey digital orthophoto quadrangles (USGS DOQ) orthophoto.