Height Estimation Model Research Articles

Body heigth prediction model from foot measurement in a Chilean population of university student athletes

In forensic research, it is important to identify human remains. Body height is an essential aspect in anthropometric characterization. This is the first study in a Chilean population and aimed to develop a height estimation model for a young adult population of athletes from foot measurements. Central Chilean subjects were included (n=139). Height (H), Foot Length (FL), Foot Breadth (FB), and Heel Foot Breadth (HFB) were measured. For both sex and feet, FL was the most correlated with H (Females r > .8, p < .001; Males r > .7, p < .001). When only FL is used in the equation, similar values are obtained as when using FL + FB + HFB in females (R2 > 65%) and males (R2 > 51%). It was possible to appreciate that the mean of the data obtained from the equations is equal to the mean of the actual data. However, the minimum values tend to be overestimated, and the maximum values tend to be underestimated. It was possible to develop a mathematical model that allows predicting height from the anthropometric measurements of the feet of young adult athletes from the Metropolitan Region of Chile. Furthermore, it was shown that foot length was the measurement most correlated with height and can be used independently in the equations. This study provides valuable information in the forensic medical field, specifically in the identification of bodies in which it is impossible to determine the height directly because they are dismembered or incomplete.

Pano2Geo: An efficient and robust building height estimation model using street-view panoramas

Building height serves as a crucial parameter in characterizing urban vertical structure, which has a profound impact on urban sustainable development. The emergence of street-view data offers the opportunity to observe urban 3D scenarios from the human perspective, benefiting the estimation of building height. In this paper, we propose an efficient and robust building height estimation model, which we call the Pano2Geo model, by precisely projecting street-view panorama (SVP) coordinates to geospatial coordinates. Firstly, an SVP refinement stratagem is designed, incorporating NENO rules for observation quality assessment from four aspects: number of buildings, extent of the buildings, number of nodes, and orthogonal observations, followed by the application of the art gallery theorem to further refine the SVPs. Secondly, the Pano2Geo model is constructed, which provides a pixel-level projection transformation from SVP coordinates to 3D geospatial coordinates for locating the height features of buildings in the SVP. Finally, the valid building height feature points in the SVP are extracted based on a slope mutation test, and the 3D geospatial coordinates of the building height feature points are projected using the Pano2Geo model, so as to obtain the building height. The proposed model was evaluated in the city of Wuhan in China, and the results indicate that the Pano2Geo model can accurately estimate building height, with an average error of 1.85 m. Furthermore, compared with three state-of-the-art methods, the Pano2Geo model shows superior performance, with only 10.2 % of buildings have absolute errors exceeding 2 m, compared to the Map-image-based (27.2 %), Corner-based (16.8 %), and Single-view-based (13.9 %) height estimation methods. The SVP refinement method achieves optimal observation quality with less than 50 % of existing SVPs, leading to highly efficient building height estimation, particularly in areas of a high building density. Moreover, the Pano2Geo model exhibits robustness in building height estimation, maintaining errors within 2 m even as building shape complexity and occlusion degree increase within the SVP. Our source dataset and code are available at https://github.com/Giser317/Pano2Geo.git.

A detailed study on human height estimation model that combines video surveillance systems with 3D laser scanning.

The increase of video surveillance systems has highlighted the interest in forensic anthropometric analysis of subjects who commit crimes and are captured by cameras during their criminal activities. There are different methodologies for human height estimation. Forensic researchers developed a methodological approach that allows the height of a subject to be estimated through a combined model of 3D laser scanning acquisition and video images acquired by video surveillance systems. The proposed study had highlighted three limits: not assessments had been made for image correction to limit the distortion effect, the method had been tested by only one laboratory and probably height assessment was dependent on the ergonomics. To overcome these limitations, in this paper the analysis was repeated by correcting the images to compare the new results obtained with the previous ones. Furthermore, the same methodological approach was applied by estimating the height of a mannequin, to limit the ergonomic effects, and proposing the same study to three different forensic laboratories to compare the results. The presented study demonstrates the reliability and repeatability of the system, as the results obtained by the three laboratories are very similar. They have obtained the same trend and the maximum estimate distance is approximately 6 cm. Furthermore, it has showed that the accuracy of results is dependent on image correction, which has little impact (approximately 1 cm more accurate on the corrected frame than the normal frame) on the height evaluation and they are not dependent to the ergonomics of the subject captured.

Estimation of canopy height based on multi-source remote sensing data using forest structure aided sample selection

ABSTRACT Forest canopy height data are crucial for estimating forest carbon storage and assessing forest ecology. By utilizing satellite imagery, canopy height data obtained from airborne or spaceborne LiDAR have been expanded from footprint and plot levels to spatially continuous elevation mapping of forests. However, current research suggests that estimating forest canopy height without forest type data presents a challenge in how to effectively integrate multi-source LiDAR data and ensure the samples adequately represent various forest types for higher estimation accuracy. Therefore, this study proposes a forest canopy height estimation method that considers forest structure and integrates multi-source LiDAR data to overcome the challenge. First, a stratified sampling method based on forest structure (SSMFS) was proposed to select training samples and enhance their representativeness. Second, we combined GEDI and ATL08 data to create a multi-source spaceborne LiDAR dataset, enhancing geographic coverage and increasing canopy height samples. Third, the spaceborne LiDAR-based canopy height estimation model incorporates previously unconsidered canopy openness features and uses SSMFS to select training samples. Finally, we improved spaceborne LiDAR canopy height accuracy by creating a residual correction model that adjusts for differences between airborne scanner (ALS) and spaceborne LiDAR estimates. This study, conducted in Zhangwu County, achieved an accuracy of R2 = 0.71, MAE = 1.20 m, and RMSE = 1.71 m. These results show a 51.06% increase in R2, a 26.38% decrease in MAE, and a 24.00% decrease in RMSE compared to recent research. In summary, this study profoundly amplifies predictive accuracy, providing a clear advantage in the delineation of regional forest canopy maps.

Sat2Map: Reconstructing 3D Building Roof from 2D Satellite Images

Three-dimensional (3D) urban models have gained interest because of their applications in many use cases, such as disaster management, energy management, and solar potential analysis. However, generating these 3D representations of buildings require lidar data, which is usually expensive to collect. Consequently, the lidar data are not frequently updated and are not widely available for many regions in the US. As such, 3D models based on these lidar data are either outdated or limited to those locations where the data is available. In contrast, satellite images are freely available and frequently updated. We propose sat2Map , a novel deep learning-based approach that predicts building roof geometries and heights directly from a single 2D satellite image. Our method first uses sat2pc to predict the point cloud by integrating two distinct loss functions, Chamfer Distance and Earth Mover’s Distance, resulting in a 3D point cloud output that balances overall structure and finer details. Additionally, we introduce sat2height , a height estimation model that estimates the height of the predicted point cloud to generate the final 3D building structure for a given location. We extensively evaluate our model on a building roof dataset and conduct ablation studies to analyze its performance. Our results demonstrate that sat2Map consistently outperforms existing baseline methods by at least 18.6%. Furthermore, we show that our refinement module significantly improves the overall performance, yielding more accurate and fine-grained 3D outputs. Our sat2height model demonstrates a high accuracy in predicting height parameters with a low error rate. Furthermore, our evaluation results show that we can estimate building heights with a median mean absolute error of less than 30 cm while still preserving the overall structure of the building.

A Linear Variable Parameter Observer-Based Road Profile Height Estimation for Suspension Nonlinear Dynamics Improvements

The accuracy of road profile height estimation has a significant impact on suspension control quality, which in turn influences handling, stability of vehicle motion and occupants' comfort. Based on our previous published work, this article designs and proposes a novel method for road profile estimation that is based on suspension nonlinear dynamics. The proposed approach first establishes the road profile height estimation model considering a real suspension design, including nonlinear characteristics of the shock absorber, bushing stiffness and damping, actual geometry of the control arms, and positioning of absorber. Unlike the conventional sprung-unsprung mass model, the real nonlinear suspension model provides much higher output prediction accuracy as computational and experimental results demonstrated. Moreover, the established estimation method and model require only two easily measurable parameters, which are the acceleration of the sprung mass and the travel of the shock absorber. While considering nonlinearity and hysteretic characteristics of the damping force, the proposed approach is based on the estimation framework of linear parameter-varying systems and establishes a sliding mode observer for estimating the road profile height. The stability of estimation error dynamics of the observer is guaranteed by the Lyapunov stability analysis. As bench-test experiments of a hardware implementation of the suspension-wheel unit validated the computational results. The tests demonstrated that the proposed method allows for real-time estimating of the road profile height in different road conditions and electric currents of the suspension damper and is robust to uncertainty of the payload.

Real-time layer height estimation during multi-layer directed energy deposition using domain adaptive neural networks

Metal additive manufacturing (AM), such as laser direct energy deposition (DED), is gaining popularity because of its capability in manufacturing near-net-shaped complex components for various industrial applications. However, the geometry control during the DED process, especially at corners with sharp turns, remains a daunting task. To achieve geometry control, geometry estimation to identify the relationship between the process parameters and geometry attributes is vital. In this study, a real-time layer height estimation technique is developed for DED using a laser line scanner, vision camera, and domain adaptive neural networks (DaNN). An emphasis is placed on layer height estimation at sharp corners during multi-layer deposition. First, multi-layer straight-line deposition data is collected using laser line scanner and an initial layer height estimation model is constructed. Then, to efficiently achieve layer height estimation during corner deposition, an DaNN model is established using the multi-layer straight-line deposition data and the constructed initial model. The actual traverse speed at the corners is measured using a vision camera and fed into the DaNN model as one of input features. Finally, the DaNN model is updated online to further improve estimation accuracy during corner deposition. The proposed technique has been validated by DED experiments and the results show that the layer height can be estimated in 0.018 s with an average accuracy of 25.7 µm when multiple layers with an average height of 250 µm are deposited at corners with different angles.

Combining ICESat-2 photons and Google Earth Satellite images for building height extraction

Building heights are one of the crucial data for comprehending the functions of urban systems. Employing optical remote sensing imagery, the shadow-based method is one of the most promising methods which have been proposed for estimating building height. However, the existing shadow-based studies for building height estimation are restricted to a small area due to the lack of building height annotations and ignorance of building azimuth variations. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) allows large-scale building height retrieval in the along-track direction and thus can be taken as ground truth building height annotations to support the shadow-based algorithms for large-scale building height extraction. Here, we proposed an approach for extracting building height by combining Google Earth Satellite (GES) images and ICESat-2 photons. Building and shadow instances were first extracted using a U-Net deep learning framework. Based on the building height annotations retrieved from ICESat-2 photons, an improved shadow-based building height estimation model by minimizing the global error across all sample buildings was developed. A typical urban area located in the city center of Shanghai, China with an area of around 90 km2 was selected to validate the proposed method. In total 15,966 buildings were successfully extracted and the results indicated that the estimated building heights have high accuracy with an absolute mean error of 4.08 m. Moreover, the proposed method shows a better performance compared to the existing shadow-based method and existing building height datasets. The method holds great potential for large-scale building-level height retrieval which contributes to further studies of urban morphologies.

Canopy height estimation using drone-based RGB images

Canopy height is an important crop biophysical parameter. It provides information about the crop growth as well as act as an input parameter for biomass and crop yield models. Considering the importance of this parameter, a novel semi-automatic canopy height estimation model has been developed which can work with both georeferenced or non-georeferenced top-of-canopy aerial images. The model employs a Structure-from-Motion algorithm followed by dense point cloud reconstruction and polygon triangulation to obtain polygon meshes which are used for height estimation. The process has been tested on drone-based data collected from a maize crop over the 2018-19 Rabi season from a semi-arid area in central-south India. The ground truth canopy height was measured by manually measuring height of plants using a meter scale. The ground elevation has been modelled using a linear best fit plane and the estimated canopy height was found to have the best R2 value of 0.85 and RMSE values of 14.17 cm.

Wave Height Estimation and Validation Based on the UFS Mode Data of Gaofen-3 in South China Sea

The ultrafinestrip (UFS) of the Gaofen-3 (GF-3) satellite provides extensive ocean wave details due to the high spatial resolution of 3 m. In this article, a new empirical model is developed to estimate wave height from GF-3 UFS mode data in South China Sea (SCS). Traditional methods either have more input parameters or complex forms or complex transformations, and most of them depend on the visible wave pattern. The model has the advantages of fewer input parameters and unnecessary visual wave patterns. The wave height estimation model is developed based on the collated data pairs between GF-3 UFS data in horizontal-horizontal polarization and the ERA5 reanalysis dataset from 2018 to 2021. The datasets are randomly divided into two groups. One group (about 80%) is used to develop the empirical relation; the other group (about 20%) and some altimeter data are used for significant wave height (SWH) verification. The comparison of the model data with the remaining ERA5 (ECMWF Reanalysis v5) data and the altimeter shows that the root-mean-square error is 0.41 and 0.47 m, the scatter index is 29.24% and 29.79%, and the correlation coefficient is 0.90 and 0.82, respectively. These statistical indices suggest that the developed model is suitable for SWH retrievals. So, the study results indicate that the GF-3 UFS mode data provide valuable information about wave conditions in the SCS.

Estimating average tree height in Xixiaoshan Forest Farm, Northeast China based on Sentinel-1 with Sentinel-2A data

Forest resource survey is important for the sustainable development of forest ecosystem in China. The average tree height is a main structural parameter of forest resource survey, and also one of the key parameters with greatest difficulty to obtain. The purpose of this study was to explore the potential of joint active and passive remote sensing technology in estimating forest average height. Taking Xixiaoshan Forest Farm in Linjiang City of Jilin Province as the research area, we used Sentinel-1 SAR and Sentinel-2A data, extracted two backscatter coefficients and eight texture information of Sentinel-1, ten spectral bands and texture information of Sentinel-2A and eleven vegetation index variables, constructed five groups of average tree height estimation models based on above variables and fusion of four variables by multiple linear regression method. We further evaluated the influence of each variable on the inversion accuracy. The results showed that the texture information extracted from the Sentinel-2A spectral band of a single data source variable had a better modeling effect and could be used as effective data to estimate the average tree height. The height estimation model of the integrated four variables was optimal, with a R2 vaule of 0.56, a root mean square error of leave-one-out cross-validation of 2.92 m, and a relative root mean square error of leave-one-out cross-validation of 21.5%. The forest average height model based on Sentinel-1 and Sentinel-2a characteristic variables could improve the estimation accuracy of forest height, which could be used for regional forest average height estimation and mapping.

Forest Canopy Height Estimation Using Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) Technology Based on Full-Polarized ALOS/PALSAR Data

Forest canopy height is a basic metric characterizing forest growth and carbon sink capacity. Based on full-polarized Advanced Land Observing Satellite/Phased Array type L-band Synthetic Aperture Radar (ALOS/PALSAR) data, this study used Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) technology to estimate forest canopy height. In total the four methods of differential DEM (digital elevation model) algorithm, coherent amplitude algorithm, coherent phase-amplitude algorithm and three-stage random volume over ground algorithm (RVoG_3) were proposed to obtain canopy height and their accuracy was compared in consideration of the impacts of coherence coefficient and range slope levels. The influence of the statistical window size on the coherence coefficient was analyzed to improve the estimation accuracy. On the basis of traditional algorithms, time decoherence was performed on ALOS/PALSAR data by introducing the change rate of Landsat NDVI (Normalized Difference Vegetation Index). The slope in range direction was calculated based on SRTM (Shuttle Radar Topography Mission) DEM data and then introduced into the s-RVoG (sloped-Random Volume over Ground) model to optimize the canopy height estimation model and improve the accuracy. The results indicated that the differential DEM algorithm underestimated the canopy height significantly, while the coherent amplitude algorithm overestimated the canopy height. After removing the systematic coherence, the overestimation of the RVoG_3 model was restrained, and the absolute error decreased from 23.68 m to 4.86 m. With further time decoherence, the determination coefficient increased to 0.2439. With the introduction of range slope, the s-RVoG model shows improvement compared to the RVoG model. Our results will provide a reference for the appropriate algorithm selection and optimization for forest canopy height estimation using full-polarized L-band synthetic aperture radar (SAR) data for forest ecosystem monitoring and management.

IM2ELEVATION: Building Height Estimation from Single-View Aerial Imagery

Estimation of the Digital Surface Model (DSM) and building heights from single-view aerial imagery is a challenging inherently ill-posed problem that we address in this paper by resorting to machine learning. We propose an end-to-end trainable convolutional-deconvolutional deep neural network architecture that enables learning mapping from a single aerial imagery to a DSM for analysis of urban scenes. We perform multisensor fusion of aerial optical and aerial light detection and ranging (Lidar) data to prepare the training data for our pipeline. The dataset quality is key to successful estimation performance. Typically, a substantial amount of misregistration artifacts are present due to georeferencing/projection errors, sensor calibration inaccuracies, and scene changes between acquisitions. To overcome these issues, we propose a registration procedure to improve Lidar and optical data alignment that relies on Mutual Information, followed by Hough transform-based validation step to adjust misregistered image patches. We validate our building height estimation model on a high-resolution dataset captured over central Dublin, Ireland: Lidar point cloud of 2015 and optical aerial images from 2017. These data allow us to validate the proposed registration procedure and perform 3D model reconstruction from single-view aerial imagery. We also report state-of-the-art performance of our proposed architecture on several popular DSM estimation datasets.

Development of a height estimation method based on the diameter at breast height of Prosopis alba Grisebach selected populations from a progeny trial in Santiago del Estero, Argentina

The main objective of this work was to develop a height estimation method of Prosopis alba based on the diameter at breast height (DBH) of populations with superior characteristics selected through a progeny trial located in the INTA Experimental Agricultural Station, Province of Santiago del Estero, Argentina. The progeny trial was established in 2008 and consists of 3,671 individuals (202 families). The registered variables were DBH and total height (TH) of 123 individuals, taken at random from the three blocks that make up the trial. Linear regressions were performed to develop the model that best fits height estimation with all the sampled individuals (AI model) and, also using the data of 7 individuals - the three trees of greater diameter, the three of smaller diameter and an individual of intermediate diameter-, called the reduced height estimation model (RHEM model). AI model and RHEM model were satisfactory to estimate height of the trees based on their DBH in the trial of progenies in Santiago del Estero. However, the RHEM model offers an important saving of time and effort, simplifying the field activity.

Improvement of forest canopy height estimation model by combining Geoscience Laser Altimetry System full waveform and multispectral remote sensing data over sloping terrain

Light detection and ranging (LiDAR) technology can provide accurate data for the vertical structure of a forest. Such data are fundamental for the study of aboveground biomass in the global carbon cycle. Most studies to date have used Geoscience Laser Altimetry System (GLAS) waveforms and terrain parameters as raw data in creating forest canopy height estimation models. Whether other parameters can be introduced to improve the accuracy of these models remain to be studied. In this study, we introduce parameters for forest texture to augment the topographic index model. Texture parameters were combined with field observations of canopy height to increase the accuracy of canopy height estimates over sloping terrain in the Lushuihe Forest District, a typical forest in the Changbai Mountains, Jilin Province, China. The study area consists mainly of broadleaf forest, coniferous forest, and mixed forest. Fifty-five sample plots covering different terrain reliefs and forest types were selected. The study areas were divided into high and low relief areas (i.e., hills and plains) using four different terrain relief thresholds (5, 10, 15, and 20 m) to select the best partition value. The results showed that the most accurate estimate of canopy height was given by the improved model using a 20-m threshold. Compared with the baseline topographic index model, R2 for leave-one-out cross-validation between the estimates given by the improved model and observed data increased from 0.777 to 0.952 and RMSE decreased from 2.90 to 1.35 m. The increased accuracy of canopy height estimates is due to the correction of GLAS waveform parameters by introducing texture parameters to incorporate changes in canopy structure because of forest aging and different forest types.

Forest canopy height mapping over China using GLAS and MODIS data

The Geoscience Laser Altimeter System (GLAS) accurately detects the vertical structural information of a target within its laser spot and is a promising system for the inversion of structural features and other biophysical parameters of forest ecosystems. Since the GLAS footprints are discontinuously distributed with a relativity low density, continuous vegetation height distributions cannot be mapped with a high accuracy using GLAS data alone. The MODIS BRDF product provides more forest structural information than other optical remote sensing data. This study aimed to map forest canopy heights over China from the GLAS and MODIS BRDF data. Firstly, the waveform characteristic parameters were extracted from the GLAS data by the method of wavelet analysis, and the terrain index was calculated using the ASTER GDEM data. Secondly, the model reducing the topographic influence was constructed from the waveform characteristic parameters and terrain index. Thirdly, the final canopy height estimation model was constructed from the neural network combining the canopy height estimated with the GLAS point and the MODIS BRDF data, and applied to get the continuous canopy height map over China. Finally, the map was validated by the measured data and the airborne LiDAR data, and the validation results indicated that forest canopy heights can be estimated with high accuracy from combined GLAS and MODIS data.

Online estimation of workpiece height by least squares support vector machines in wire electrical discharge machining

When machining workpieces with complicated and intricate shapes by wire electrical discharge machining, the workpiece height usually varies along a machining path. To ensure a stable and efficient machining, the machining parameters must be appropriately tuned based on the estimated workpiece height. Though an offline workpiece height estimation model can be established by traditional support vector regression with a satisfactory accuracy, the offline model is unable to cover all possible machining conditions. In this paper, least squares support vector machine is proposed to build up online a workpiece height estimation model. Due to the use of equality constraints in the formulation of least squares support vector machine, all data points are treated as support vectors, thus sparsity is lost as compared with traditional support vector machine. For online applications, a low computational load as well as a limited memory storage are required for an online algorithm. To meet the requirements of online workpiece height estimation, two measures are thus adopted. One is the use of a projection method which measures the relevance of a new data point with existing basic vectors by calculating its residue. The residue is used as criteria for admission of the new data point as a new member of the basic vector set. The other is the restriction on the size of the basic vector set. Removal of an insignificant basic vector is determined by its contribution to the model, which is measured by its coefficient in the model (or support value). Experimental results show that, by online learning, the estimation model can achieve an estimation error less than 2 mm at smooth parts of a workpiece. Based on the estimated workpiece height, proper machining parameters can be set and a stable machining can be achieved.

A model to estimate mixing height and its effects on ozone modeling

A mixing height estimation model (PMH) whose output can be used in air quality models, especially the Urban Airshed Model (UAM-IV), is developed. The evaluation of the performance of the PMH shows that the predictions match the observations very well. The average geometric mean of the predicted to observed hourly mixing height ratios is equal to 0.99. The outputs of the PMH along with those of the mixing height model incorporated in the UAM-IV package (RAMMETX) are used in the UAM-IV to simulate hourly average concentrations of tropospheric ozone (O 3) in the Indianapolis metropolitan statistical area (MSA). A comparative study performed to assess the effects of mixing height shows that the UAM-IV performs better when the mixing height fields are from the PMH. For example, the episodic mean of the average normalized bias and the average normalized absolute bias of predicted to observed O 3 concentrations are 1.2% and 18.6%, respectively, when the mixing height fields are from the PMH. They are 6.6% and 20.1%, respectively, when the mixing height fields are from RAMMETX.

Computer Vision System for Automatic Vehicle Classification

In the present paper, a computer vision system composed of five models is proposed for vehicle classification. The five models are: (1) The perspective projection model; (2) the length measurement model; (3) the width and height estimation model; (4) the profile character extraction model; and (5) the tree‐type classification model. As a significant feature, the third model provides an effective way to estimate width and height of vehicles from video images. This capability is not available in loop detector systems at present. The fourth model provides an approach to obtain two important profile characters of vehicle namely: (1) The front shape of a vehicle: flat front of projecting front; and (2) the number of units of which a vehicle is composed. With these characters, not only can buses be differentiated from trucks, but also vans can be separated from cars. Therefore, common drawbacks of present vehicle‐classification systems are remedied. Experimental results and suggestions for the future improvemen...