Height Estimation Research Articles

Area extraction and growth monitoring of sugarcane from multi-source remote sensing images under a polarimetric SAR data compensation based on buildings

ABSTRACT Aiming at the issue of low accuracy in crop mapping and growth monitoring caused by imprecise calibration of radar time-series data, this paper proposed a Synthetic Aperture Radar (SAR) spatio-temporal error compensation method. By constructing a compensation reference image using the buildings with stable backscattering coefficients in the study area, the error correction of time-series SAR data was realized based on the compensation model. The compensated SAR data were used to establish the Sugarcane Growth Index (SGI) according to the growth curve of sugarcane. The sugarcane area was extracted after combining the compensated SGI and optical image, and the accuracy of F1 on sugarcane distribution extraction was 92.12%. There was an improvement of 4.11% compared with no compensation method. On this basis, the newly planted and ratoon sugarcane were further classified by the expectation maximization algorithm based on the compensated SAR image at the seedling stage. The newly planted sugarcane and the ratoon sugarcane could be accurately distinguished with area extraction accuracy of 82.06% and 80.59%, respectively. Moreover, the compensated SAR data of time series during the tillering to maturity stages were used to estimate the sugarcane height, yielding an R 2 value of 0.717 using a quadratic polynomial model. The Spatio-temporal error compensation method for distributed targets proposed in this study can reduce the loss of SAR data across various times and regions, and achieve accurate results of sugarcane distribution extraction and plant height estimation.

Application of the Length of Index and Ring Fingers to Estimate the Stature.

Stature contributes as a crucial element of an individual's physical appearance and can be instrumental in establishing their identity.In cases where the body is extensively mutilated, decomposed, or reduced to skeletal remains, stature becomes an essential component in identifying the unknown by means of measuring the skeletal remains. Its estimation relies on the principle that an individual's height has a definite and linear relationship with specific body parts and long bones. This process, together with assessing age, sex, and race constitutes the essential components of the anthropological protocol. Stature estimation can be accomplished through both anatomical and mathematical approaches. The present study clearly defines regression models for height estimation from finger lengths. The formula derived can proveparticularly valuable in Medico-legal scenarios, as it can be applied effectively even when only a portion of the body is accessible. The purpose of the present study is to estimate the stature of individuals by measuring the length of the index and ring fingers. The current study acquired three measurements, such as stature, right/left index finger length (RIFL/LIFL), and ring finger length (RFL), from 220 samples, including 110 males and 110 females, respectively, between the age groups of 20 and 60 years. The application of the length of the index and ring finger in forensic investigations holds significance due to their potential as reliable predictors of an individual's height. According to the findings of the study, males showed significantly higher stature than females. A statistically significant correlation was also observed (p-value = 0) between stature and finger lengths (IFL, RFL) in both hands. The highest correlation coefficients were found for the left RFL (r = 0.688) in females and the LIFL (r = 0.552) in males. Additionally, males showed significantly longer index and RFL than females. Linear regression models for the estimation of stature from ring and index finger length were also derived successfully. The results obtained from the present study exhibit potential use to evaluate the utility of measuring index and RFLs for determining stature and predicting the precision of regression models by employing those parameters. The models derived from this study can serve as corroborative evidence for identifying mutilated body parts or unknown remains.

Experimental characterization of littoral atmospheric acoustics: Concurrent meteorological and acoustic observations.

The aim of this work is to describe a rich set of acoustic transmission loss observations that were completed in a coastal environment. The data library, enumerated in detail and publicly posted, is comprised of pitch-catch acoustic transmission loss measurements along with concurrent high spatial resolution meteorological observations. The meteorological parameters include near-surface temperature profiles, vertical wind speed profiles in the acoustic propagation direction, and significant wave height estimates. The acoustic source is positioned on an anchored vessel such that the first several hundred meters of the acoustic range is over open water with one microphone array positioned at the shore. A second microphone array is placed several hundred meters inland along the same source-to-receiver heading. The path between the two acoustic arrays is uniform salt marsh vegetation. Observations were made during seven sessions, which represent a variety of atmospheric conditions. That variety of conditions allows for some experimental generalizations about transmission loss as a function of meteorological observations. These include (1) the relationship between vertical effective sound speed profile and transmission loss, and (2) the variability of acoustic pressure with turbulence over time and elevation.

Probabilistic reconstruction of sea-level changes and their causes since 1900

Abstract. Coastal communities around the world are increasingly exposed to extreme events that have been exacerbated by rising sea levels. Sustainable adaptation strategies to cope with the associated threats require a comprehensive understanding of past and possible future changes. Yet, many coastlines lack accurate long-term sea-level observations. Here, we introduce a novel probabilistic near-global reconstruction of relative sea-level changes and their causes over the period from 1900 to 2021. The reconstruction is based on tide gauge records and incorporates prior knowledge about physical processes from ancillary observations and geophysical model outputs, allowing us, for the first time, to resolve individual processes and their uncertainties. We demonstrate good agreement between the reconstruction and satellite altimetry and tide gauges (if local vertical land motion is considered). Validation against steric height estimates based on independent temperature and salinity observations over their overlapping periods shows moderate to good agreement in terms of variability, though with larger reconstructed trends in three out of six regions. The linear long-term trend in the resulting global-mean sea-level (GMSL) record is 1.5 ± 0.19 mm yr−1 since 1900, a value consistent with central estimates from the 6th Assessment Report of the Intergovernmental Panel on Climate Change. Multidecadal trends in GMSL have varied; for instance, there were enhanced rates in the 1930s and near-zero rates in the 1960s, although a persistent acceleration (0.08 ± 0.04 mm yr−2) has occurred since then. As a result, most recent rates have exceeded 4 mm yr−1 since 2019. The largest regional rates (>10 mm yr−1) over the same period have been detected in coastal areas near western boundary currents and the larger tropical Indo-Pacific region. Barystatic mass changes due to ice-melt and terrestrial-water-storage variations have dominated the sea-level acceleration at global scales, but sterodynamic processes are the most crucial factor locally, particularly at low latitudes and away from major melt sources. These results demonstrate that the new reconstruction provides valuable insights into historical sea-level change and its contributing causes, complementing observational records in areas where they are sparse or absent. The Kalman smoother sea-level reconstruction dataset can be accessed at https://doi.org/10.5281/zenodo.10621070 (Dangendorf, 2024).

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.

Tree Height Estimation of Chinese Fir Forests Based on Geographically Weighted Regression and Forest Survey Data

Tree Height Estimation of Chinese Fir Forests Based on Geographically Weighted Regression and Forest Survey Data

Accurate height and length estimation in hospitalized children not fulfilling WHO criteria for standard measurement: a multicenter prospective study

In hospitalized children, height should be measured. When world health organization (WHO) height measurement gold standards is impossible, the ideal height estimation technique is still unclear. We conducted an international prospective study in eight different pediatric intensive care units to assess the accuracy, precision, practicability, safety, and inter-rater reliability of 12 different height estimation techniques, based on body segment measurement extrapolation, or other calculations using previous or projected heights. All extrapolation techniques were performed on each child, and later compared to their WHO gold standard heights. A total of 476 patients were enrolled. In the < 2-year subgroup, board length use and growth chart extrapolation performed best. In the ≥ 2-year subgroup, growth chart extrapolation and parents’ report were the most accurate, followed by height measurement alongside the body with a tape measure. In both groups, body segment extrapolations were poorly predictive and showed mean bias and limits of agreement that varied a lot with age. Most body segment-based techniques presented with frequent measurement difficulties, but children’s safety was rarely compromised. The inter-rater reliability of body segment measurement was low in the < 2-year subgroup.Conclusions: To accurately estimate height in hospitalized children, health care professionals should integrate the accuracy, precision, practicability, and reliability of each measurement technique to select the most appropriate one. Body segment-based techniques were the least accurate and should probably not be used. Simple techniques like growth chart extrapolation, or measurement alongside the body (and length board measurement in the youngest) should be implemented in daily practice.Trial Registration: The study protocol was registered (12th April 2019) on the clinical-trial.gov website (NCT03913247).What is Known:• Height should be measured in hospitalized children to assess nutritional status and calculate various clinical parameters. • Many hospitalized children cannot be measured using WHO conventional height measurement methods. The ideal height estimation method has not been identified yet. What is New:• Most estimation methods based on body segment measurement extrapolation fail to accurately predict height.• Board length use and growth chart extrapolation performed best in young children (≥2 years). Growth chart extrapolation and parents’ report were the most accurate, followed by height measurement alongside the body with a tape measure in older children.

Repeated drone photogrammetry surveys demonstrate that reconstructed canopy heights are sensitive to wind speed but relatively insensitive to illumination conditions

ABSTRACT Unoccupied aerial vehicle (UAV) based structure-from-motion (SfM) photogrammetry surveys are becoming a standard tool for ecologists to measure plant structure and biomass in non-forest ecosystems. The reproducibility of SfM survey results under different operational conditions, namely wind speed, sun elevation, and cloud condition, is poorly understood. It is also unclear to what extent commonly applied point-to-grid interpolation of derived point clouds affects inference of vegetation structure. These knowledge gaps limit the use of these methods for measuring and monitoring detection. We captured 61 UAV SfM surveys at the same study area under a range of wind/sun/cloud conditions over a 24-day period during 2021 and used generalized linear mixed effects models to test how the structural reconstructions varied with environmental conditions. Wind speed significantly influenced the canopy height reconstructions, with greater wind speeds reducing mean canopy height. Different plant species exhibited varying sensitivities to wind that are likely related to leaf attributes (size, structure, and density), growth form of the canopy, and physical properties such as limb flexibility. The movement of plants can reduce canopy height estimates derived from photogrammetric surveys, even under relatively low wind speeds. Reconstructed canopy heights were comparatively insensitive to solar elevation variations. Cloud conditions and illumination by direct sunlight had a weak, non-significant effect on reconstructed canopy height, with sunny conditions (generating shadows) resulting in a measurable but marginal reduction in mean canopy heights. When comparing canopy heights of interpolated and discontinuous derived canopy height models the results highlighted that these were insensitive to interpolation in this specific setting. We recommend measuring mean wind speeds throughout surveys where comparisons are to be made between different drone-based SfM surveys of vegetation over either time or space. Care should be taken to ensure that the effects of wind are controlled for so that inferences are valid.

Modeling dominant height with USGS 3DEP LiDAR to determine site index in even-aged loblolly pine (Pinus taeda L.) plantations in the southeastern US

Abstract Accurate quantification and mapping of forest productivity are critical to understanding and managing forest ecosystems. Local LiDAR or photogrammetric surveys have been used to obtain reliable estimates of canopy heights, yet these acquisitions can entail substantial expenses. Therefore, we developed models using freely available US Geological survey (USGS) LiDAR data for prediction of dominant height to map site index across loblolly pine (Pinus taeda L.) plantations in the southeastern US. We used 2017–2020 national USGS 3D Elevation Program LiDAR acquisitions and explored how different height percentiles, grid output resolutions, time difference between LiDAR and ground acquisitions, tree height, and dominant height definition affected the proposed model. We built the dominant height models using 1301 ground plots. The final regression model was constructed with the 95th percentile of the height distribution of the first returns above-ground and had values of R2 = 0.89, RMSE = 1.55 m, and RRMSE = 7.66 per cent at a 20-m pixel grid, yet all the examined percentile-resolution combinations were acceptable. No effect evidence was found for time difference when the flight was less than 4 months in advance or after the ground measurement, and it was also found independent of pulse density when this variable was lower than 9.5 pulses m−2. Using the recorded age of the plantations, we assessed the error propagation when translating dominant height to site index in two site index models, obtaining an RRMSE lower than 10 per cent in both. We found that USGS LiDAR acquisitions can be reliably used to map dominant height at a large scale, and consequently used to map forest productivity when age is known. This ability adds more value to a tool proven widely applicable in time and space and offers a great opportunity for stakeholders in different fields of use.

An Improved Remote Sensing Retrieval Method for Elevated Duct in the South China Sea

Elevated duct is an atmospheric structure characterized by abnormal refractive index gradients, which can significantly affect the performance of radar, communication, and other systems by capturing a portion of electromagnetic waves. The South China Sea (SCS) is a high-incidence area for elevated duct, so conducting detection and forecasts of the elevated duct in the SCS holds important scientific significance and practical value. This paper attempts to utilize remote sensing techniques for extracting elevated duct information. Based on GPS sounding data, a lapse rate formula (LRF) model and an empirical formula (EF) model for the estimation of the cloud top height of Stratocumulus were obtained, and then remote sensing retrieval methods of elevated duct were established based on the Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing data. The results of these two models were compared with results from the elevated duct remote sensing retrieval model developed by the United States Naval Postgraduate School. It is shown that the probability of elevated duct events was 79.1% when the presence of Stratocumulus identified using GPS sounding data, and the trapping layer bottom height of elevated duct well with the cloud top height of Stratocumulus, with a correlation coefficient of 0.79, a mean absolute error of 289 m, and a root mean square error of 598 m. Among the different retrieval models applied to MODIS satellite data, the LRF model emerged as the optimal remote sensing retrieval method for elevated duct in the SCS, showing a correlation coefficient of 0.51, a mean absolute error of 447 m, and a root mean square error of 658 m between the trapping layer bottom height and the cloud top height. Consequently, the encouraging validation results demonstrate that the LRF model proposed in this paper offers a novel method for diagnosing and calculating elevated ducts information over large-scale marine areas from remote sensing data.

Design and Experiment of Ordinary Tea Profiling Harvesting Device Based on Light Detection and Ranging Perception

Due to the complex shape of the tea tree canopy and the large undulation of a tea garden terrain, the quality of fresh tea leaves harvested by existing tea harvesting machines is poor. This study proposed a tea canopy surface profiling method based on 2D LiDAR perception and investigated the extraction and fitting methods of canopy point clouds. Meanwhile, a tea profiling harvester prototype was developed and field tests were conducted. The tea profiling harvesting device adopted a scheme of sectional arrangement of multiple groups of profiling tea harvesting units, and each unit sensed the height information of its own bottom canopy area through 2D LiDAR. A cross-platform communication network was established, enabling point cloud fitting of tea plant surfaces and accurate estimation of cutter profiling height through the RANSAC algorithm. Additionally, a sensing control system with multiple execution units was developed using rapid control prototype technology. The results of field tests showed that the bud leaf integrity rate was 84.64%, the impurity rate was 5.94%, the missing collection rate was 0.30%, and the missing harvesting rate was 0.68%. Furthermore, 89.57% of the harvested tea could be processed into commercial tea, with 88.34% consisting of young tea shoots with one bud and three leaves or fewer. All of these results demonstrated that the proposed device effectively meets the technical standards for machine-harvested tea and the requirements of standard tea processing techniques. Moreover, compared to other commercial tea harvesters, the proposed tea profiling harvesting device demonstrated improved performance in harvesting fresh tea leaves.

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.

Quick Estimation of Seepage Discharge and Water Level Height Out Of the Central Core in the Zoned Earth-fill Dam

This paper relates to the investigation of the amount of seepage discharge and the water level height out of the central core in the zoned earth-fill dam using the finite element procedure by Geo Studio-SEEP/W software. The investigation models were carried out in two shapes of the central core, the rectangular and the wedge shapes, by 200 miscellaneous models. For each model, seepage discharge and height of water level out were determined. Investigation results were examined using the artificial neural network technique (ANN) to demonstrate the influence weight of each independent variable (geometry and characteristics) on the output-dependent variables results using the statistical software SPSS. Core material hydraulic conductivity had the highest impact on seepage discharge and water level height while dam upstream slope had the least impact on them. Two statistical empirical equations were developed using multiple nonlinear regression for both the seepage discharge and the height of water level out using the SPSS software. The recommended equations were also verified by comparing their results with the results of 25% of the models analyzed by Geo Studio software. They showed great agreement that the correlation coefficient (r2) was 97.3% for the seepage discharge equation and 96.6% for the height of the water level-out equation.

Human degradation of tropical moist forests is greater than previously estimated

Tropical forest degradation from selective logging, fire and edge effects is a major driver of carbon and biodiversity loss1–3, with annual rates comparable to those of deforestation4. However, its actual extent and long-term impacts remain uncertain at global tropical scale5. Here we quantify the magnitude and persistence of multiple types of degradation on forest structure by combining satellite remote sensing data on pantropical moist forest cover changes4 with estimates of canopy height and biomass from spaceborne6 light detection and ranging (LiDAR). We estimate that forest height decreases owing to selective logging and fire by 15% and 50%, respectively, with low rates of recovery even after 20 years. Agriculture and road expansion trigger a 20% to 30% reduction in canopy height and biomass at the forest edge, with persistent effects being measurable up to 1.5 km inside the forest. Edge effects encroach on 18% (approximately 206 Mha) of the remaining tropical moist forests, an area more than 200% larger than previously estimated7. Finally, degraded forests with more than 50% canopy loss are significantly more vulnerable to subsequent deforestation. Collectively, our findings call for greater efforts to prevent degradation and protect already degraded forests to meet the conservation pledges made at recent United Nations Climate Change and Biodiversity conferences.

Estimation of human height using ulnar length in the Muslim community of Golbazar Municipality, Siraha, Nepal

Calculating an individual's height based on bone measurements is critical in identifying unknown bodies, body parts, or skeletal remains. Anthropologists, anatomists, and forensic experts have used a variety of anthropometric approaches to forecast stature from skeletal remains. Although few studies have been conducted to understand ulnar length and height, it has not been conducted in a few ethnic communities of Nepal. This study aimed to analyze the relationship between human height and ulnar length in Muslim communities of Golbazar Municipality, Siraha, Nepal. Two hundred people (male 100 and female 100) aged 20 to 40 years were purposively selected from Golbazaar, Siraha, Nepal. Ulnar length was measured as the distance between the tip of the Olecranon process and the styloid process with the elbow fully flexed. Height was measured from the top of the head to the floor while the participants stood upright in the anatomical position with their heads in the Frankfort plane. Statistical techniques, such as linear regression analysis and correlation coefficients, were used to determine a correlation between ulna length and height. The population's mean ulna length was 26.53 cm (SD = 2.06), and the mean height was 159.59 cm (SD = 9.72). The correlation between ulna length and height was stronger in males (0.46) than in females (0.36). The study established regression equations for height estimation based on ulna length for different age groups, with the strongest correlations found in the 31–35 years age group and weaker ones in the 20–25 years and 26–30 years age groups. The study suggests that ulna length could be a reliable predictor of height, especially when direct measurement is challenging or impossible. However, additional study is required to explore potential differences based on age, ethnicity, and gender and to validate the findings in more extensive and more diverse populations.

PREPs: An Open-Source Software for High-Throughput Field Plant Phenotyping.

An open-source software for field-based plant phenotyping, Precision Plots Analyzer (PREPs), was developed using Window.NET. The software runs on 64-bit Windows computers. This software allows the extraction of phenotypic traits on a per-microplot basis from orthomosaic and digital surface model (DSM) images generated by Structure-from-Motion/Multi-View-Stereo (SfM-MVS) tools. Moreover, there is no need to acquire skills in geographical information system (GIS) or programming languages for image analysis. Three use cases illustrated the software's functionality. The first involved monitoring the growth of sugar beet varieties in an experimental field using an unmanned aerial vehicle (UAV), where differences among varieties were detected through estimates of crop height, coverage, and volume index. Second, mixed varieties of potato crops were estimated using a UAV and varietal differences were observed from the estimated phenotypic traits. A strong correlation was observed between the manually measured crop height and UAV-estimated crop height. Finally, using a multicamera array attached to a tractor, the height, coverage, and volume index of the 3 potato varieties were precisely estimated. PREPs software is poised to be a useful tool that allows anyone without prior knowledge of programming to extract crop traits for phenotyping.

Streaming Instability and Turbulence: Conditions for Planetesimal Formation

The streaming instability (SI) is a leading candidate for planetesimal formation, which can concentrate solids through two-way aerodynamic interactions with the gas. The resulting concentrations can become sufficiently dense to collapse under particle self-gravity, forming planetesimals. Previous studies have carried out large parameter surveys to establish the critical particle to gas surface density ratio (Z), above which SI-induced concentration triggers planetesimal formation. The threshold Z depends on the dimensionless stopping time (τ s , a proxy for dust size). However, these studies neglected both particle self-gravity and external turbulence. Here, we perform 3D stratified shearing box simulations with both particle self-gravity and turbulent forcing, which we characterize via a turbulent diffusion parameter, α D. We find that forced turbulence, at amplitudes plausibly present in some protoplanetary disks, can increase the threshold Z by up to an order of magnitude. For example, for τ s = 0.01, planetesimal formation occurs when Z ≳ 0.06, ≳0.1, and ≳0.2 at α D = 10−4, 10−3.5, and 10−3, respectively. We provide a single fit to the critical Z required for the SI to work as a function of α D and τ s (although limited to the range τ s = 0.01–0.1). Our simulations also show that planetesimal formation requires a mid-plane particle-to-gas density ratio that exceeds unity, with the critical value being largely insensitive to α D. Finally, we provide an estimation of particle scale height that accounts for both particle feedback and external turbulence.

Estimation of runoff height to analyze the flood production potential of the watershed overlooking Malayer City

Estimation of runoff height to analyze the flood production potential of the watershed overlooking Malayer City

An automated platform for measuring infant formula powder rehydration quality using a collaborative robot integrated with computer vision

Current methods used for testing the rehydration quality of infant formula (IF) are mainly subjective. For a better understanding of rehydration, objective measurements are required. A computer vision (CV) system was synchronized with a collaborative robot (cobot) to automatically estimate foam height, sediment height, and the number of white particles after IF powder rehydration. Two different robotic agitations were used to prepare the mixtures in a commercially available baby bottle. To evaluate the platform, twenty-four stage-1 IF powders were rehydrated. Cobot-captured images were processed by CV algorithms and independently rated by eight participants. The participants' and platform's estimates of foam height, sediment height, and white particles score, respectively, showed agreements of 2.1 mm, 3.4 mm, and 1.7 scores, and correlation coefficients of 0.82, 0.77, and 0.68. The results show that the platform has the potential to enable objective rehydration tests and to monitor changes in visible foam and sediment over time.

Monocular Depth and Ego-motion Estimation with Scale Based on Superpixel and Normal Constraints

3D perception in intelligent VR/AR and autonomous vehicles (AV) applications is critical and attracting significant attention. The self-supervised monocular depth and ego-motion estimation serves as a more intelligent learning approach that provides the required scene depth and location for 3D perception. However, the existing self-supervised learning methods suffer from scale ambiguity, boundary blur and imbalanced depth distribution, limiting the practical applications of VR/AR and AV. In this paper, we propose a new self-supervised learning framework based on superpixel and normal constraints to address these problems. Specifically, we formulate a novel 3D edge structure consistency loss to alleviate the boundary blur of depth estimation. To address the scale ambiguity of estimated depth and ego-motion, we propose a novel surface normal network for efficient camera height estimation. The surface normal network is composed of a deep fusion module and a full-scale hierarchical feature aggregation module. Meanwhile, to realize the global smoothing and boundary discriminability of the predicted normal map, we introduce a novel fusion loss which is based on the consistency constraints of the normal in edge domains and superpixel regions. Experiments are conducted on several benchmarks, and the results illustrate that the proposed approach outperforms the state-of-the-art methods in depth, ego-motion and surface normal estimation.