Precision Evaluation and Fusion of Topographic Data Based on UAVs and TLS Surveys of a Loess Landslide

Mao, Zhonglei; Hu, Sheng; Wang, Ninglian; Long, Yongqing

doi:10.3389/feart.2021.801293

Cited by 15 publications

(6 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, an enhanced in terms of spatial coverage and point density point cloud was extracted. Similar studies have recently been conducted, focusing mainly on the correct implementation of fusion algorithms [12,16].…”

Section: Discussionmentioning

confidence: 88%

“…To carry out the measurement, as well as to integrate the measurement data with UAV and TLS, customized targets and numbered reference spheres were used [15]. To overpass the fact that some of the point cloud data were missing in the blind area of TLS measurement, authors used the iterative closest point (ICP) algorithm in the Cloud Compare software to conduct data fusion between the point clouds obtained using the DJI Phantom 4 RTK and TLS [16]. It was proved that after the data fusion, the point clouds not only retained the high-precision characteristics of the original point clouds of the TLS, but also filled in the blind area of the TLS data [16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Point cloud density enhancement within PROION project

Kyriou,

Nikolakopoulos

2023

Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023)

View full text Add to dashboard Cite

Over the past few years Unmanned Aerial Vehicle (UAV) and Terrestrial Laser Scanner (TLS) have emerged as paramount remote sensing approaches for the generation of exceptional three-dimensional models. The current study aims to examine the synergistic use of UAV and TLS point clouds created in the context of "PROION" project. In particular, the project co-funded by the European Union and the Hellenic government, combines in situ measurements, remote sensing data and soft computing methods aiming at evaluating the possible deformation on national infrastructure located in Western Greece. 3D representations of the observation sites derived from UAV and TLS sensors constitute a key part of the validation procedure. In light of this, the spatial reconstruction of the observed infrastructure should be implemented in the best possible spatial resolution. Hence, each observation site was surveyed twice in a regular basis, i.e. a UAV flight was performed to collect points on the roof while a scanning was executed for the acquisition of facades. Afterwards the generated UAV and TLS 3D representations were fused in order to produce a more comprehensive 3D model of each infrastructure. The point clouds generated at the different processing stages were compared in terms of their density.

show abstract

Section: Discussionmentioning

confidence: 88%

Section: Introductionmentioning

confidence: 99%

Point cloud density enhancement within PROION project

Kyriou,

Nikolakopoulos

2023

Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023)

View full text Add to dashboard Cite

show abstract

“…Precision positioning information plays an important role in the accuracy and quality of a DSM [137]. As a result, georeferenced correction is highly recommended for improving PH results, particularly when dealing with UAS systems that have less accurate internal GPS.…”

Section: Plant Height Accuracymentioning

confidence: 99%

Digital Phenotyping in Plant Breeding: Evaluating Relative Maturity, Stand Count, and Plant Height in Dry Beans (Phaseolus vulgaris L.) via RGB Drone-Based Imagery and Deep Learning Approaches

Volpato

Wright

Gomez

2023

Preprint

View full text Add to dashboard Cite

Background Significant effort has been made in manually tracking plant maturity and to measure early-stage plant density, and crop height in experimental breeding plots. Agronomic traits such as relative maturity (RM), stand count (SC) and plant height (PH) are essential to cultivar development, production recommendations and management practices. The use of RGB images collected via drones may replace traditional measurements in field trials with improved throughput, accuracy, and reduced cost. Recent advances in deep learning (DL) approaches have enabled the development of automated high-throughput phenotyping (HTP) systems that can quickly and accurately measure target traits using low-cost RGB drones. In this study, a time series of drone images was employed to estimate dry bean relative maturity (RM) using a hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) for features extraction and capturing the sequential behavior of time series data. The performance of the Faster-RCNN object detection algorithm was also examined for stand count (SC) assessment during the early growth stages of dry beans. Various factors, such as flight frequencies, image resolution, and data augmentation, along with pseudo-labeling techniques, were investigated to enhance the performance and accuracy of DL models. Traditional methods involving pre-processing of images were also compared to the DL models employed in this study. Moreover, plant architecture was analyzed to extract plant height (PH) using digital surface model (DSM) and point cloud (PC) data sources. Results The CNN-LSTM model demonstrated high performance in predicting the RM of plots across diverse environments and flight datasets, regardless of image size or flight frequency. The DL model consistently outperformed the pre-processing images approach using traditional analysis (LOESS and SEG models), particularly when comparing errors using mean absolute error (MAE), providing less than two days of error in prediction across all environments. When growing degree days (GDD) data was incorporated into the CNN-LSTM model, the performance improved in certain environments, especially under unfavorable environmental conditions or weather stress. However, in other environments, the CNN-LSTM model performed similarly to or slightly better than the CNN-LSTM + GDD model. Consequently, incorporating GDD may not be necessary unless weather conditions are extreme. The Faster R-CNN model employed in this study was successful in accurately identifying bean plants at early growth stages, with correlations between the predicted SC and ground truth (GT) measurements of 0.8. The model performed consistently across various flight altitudes, and its accuracy was better compared to traditional segmentation methods using pre-processing images in OpenCV and the watershed algorithm. An appropriate growth stage should be carefully targeted for optimal results, as well as precise boundary box annotations. On average, the PC data source marginally outperformed the CSM/DSM data to estimating PH, with average correlation results of 0.55 for PC and 0.52 for CSM/DSM. The choice between them may depend on the specific environment and flight conditions, as the PH performance estimation is similar in the analyzed scenarios. However, the ground and vegetation elevation estimates can be optimized by deploying different thresholds and metrics to classify the data and perform the height extraction, respectively. Conclusions The results demonstrate that the CNN-LSTM and Faster R-CNN deep learning models outperforms other state-of-the-art techniques to quantify, respectively, RM and SC. The subtraction method proposed for estimating PH in the absence of accurate ground elevation data yielded results comparable to the difference-based method. In addition, open-source software developed to conduct the PH and RM analyses can contribute greatly to the phenotyping community.

show abstract

“…With enough GCPs, a highly accurate terrain model can be obtained. In terms of accuracy verification, we proposed an error quantification analysis method based on the iterative closest point (ICP) algorithm [50][51][52]. In this method, the target point cloud is divided into multiple blocks, and ICP registration is performed with the reference point cloud for each block, indirectly obtaining the centroid displacement error in each block based on the block centroid displacement in each registration process.…”

Section: Introductionmentioning

confidence: 99%

A High-Precision Modeling and Error Analysis Method for Mountainous and Canyon Areas Based on TLS and UAV Photogrammetry

Luo,

Jiang,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Obtaining comprehensive and accurate terrain data is important for engineering construction. Unmanned aerial vehicle (UAV) photogrammetry and terrestrial laser scanning (TLS) are two widely used terrain modeling techniques. In mountainous areas, both techniques suffer limitations. These limitations occur in uninhabited areas, primarily caused by the steep terrain and inconvenient transportation conditions, resulting in poor data integrity and inadequate accuracy in UAV and TLS terrain mapping. In this article, we proposed a fusion modeling method based on UAV photogrammetry and TLS for high-precision terrain mapping in mountainous and canyon areas. The proposed method entails the use of TLS data to provide additional control points for UAV modeling, resulting in an improved accuracy of the modeling results. In addition, to quantify the optimization effect of this method, we proposed a 3D model deviation comparison method based on the iterative closest point (ICP) algorithm. This method can be employed to accurately depict the differences in distance and rotation angle between multiple terrain models. We applied this method to the Yebatan hydropower station in Southwest China, which increased the accuracy of the terrain data by 26% and expanded the effective range by over 100%.

show abstract

Precision Evaluation and Fusion of Topographic Data Based on UAVs and TLS Surveys of a Loess Landslide

Cited by 15 publications

References 58 publications

Point cloud density enhancement within PROION project

Point cloud density enhancement within PROION project

Digital Phenotyping in Plant Breeding: Evaluating Relative Maturity, Stand Count, and Plant Height in Dry Beans (Phaseolus vulgaris L.) via RGB Drone-Based Imagery and Deep Learning Approaches

A High-Precision Modeling and Error Analysis Method for Mountainous and Canyon Areas Based on TLS and UAV Photogrammetry

Contact Info

Product

Resources

About