Depth Image Analysis Research Articles

Skin and Scalp Health Benefits of a Specific Botanical Extract Blend: Results from a Double-Blind Placebo-Controlled Study in Urban Outdoor Workers

Environmental pollution is increasingly recognized as a significant contributor to skin and scalp damage. Oral supplementation with a specific blend of four standardized botanical extracts (Rosmarinus officinalis, Lippia citriodora, Olea europaea leaf, and Sophora japonica) has been previously demonstrated to enhance skin health in individuals exposed to high environmental stress. Thus, it might represent a convenient strategy to also improve their scalp health aspect, particularly in subjects with sensitive scalps. To support these effects, a 12-week double-blind, randomized, placebo-controlled trial was performed in 66 women working outdoors in urban areas with high particulate matter (PM) levels and taking 250 mg of the botanical blend daily. Product efficacy was measured as follows: skin antioxidant status (FRAP); skin and scalp moisturization (corneometer), transepidermal water loss (tewameter), and oiliness (sebumeter); skin radiance and colour (spectrophotometer), elasticity and firmness (cutometer) and wrinkle depth (image analysis); and scalp clinical evaluation. Despite constant exposure to increased levels of PM, the tested product positively influenced all monitored parameters compared to both baseline and the placebo-treated group, in as early as 4 weeks. At the end of the study, key improvements included increased skin FRAP (21.9%), moisturization (9.5%), radiance (24.9%) and reduced wrinkle depth (−16.5%), dark spot pigmentation (−26.2%), and skin oiliness (−19.3%). For the scalp, moisturization increased (14.1%), TEWL decreased (−13.8%), and sebum content reduced by 16.2%. Additionally, 71% of subjects with sensitive scalps experienced reduced redness. These findings highlight the extensive benefits of the ingredient, expanding its application beyond conventional skin treatments to also alleviate scalp issues.

Unsupervised Grouped Axial Data Modeling via Hierarchical Bayesian Nonparametric Models With Watson Distributions.

This paper aims at proposing an unsupervised hierarchical nonparametric Bayesian framework for modeling axial data (i.e., observations are axes of direction) that can be partitioned into multiple groups, where each observation within a group is sampled from a mixture of Watson distributions with an infinite number of components that are allowed to be shared across different groups. First, we propose a hierarchical nonparametric Bayesian model for modeling grouped axial data based on the hierarchical Pitman-Yor process mixture model of Watson distributions. Then, we demonstrate that by setting the discount parameters of the proposed model to 0, another hierarchical nonparametric Bayesian model based on hierarchical Dirichlet process can be derived for modeling axial data. To learn the proposed models, we systematically develop a closed-form optimization algorithm based on the collapsed variational Bayes (CVB) inference. Furthermore, to ensure the convergence of the proposed learning algorithm, an annealing mechanism is introduced to the framework of CVB inference, leading to an averaged collapsed variational Bayes inference strategy. The merits of the proposed models for modeling grouped axial data are demonstrated through experiments on both synthetic data and real-world applications involving gene expression data clustering and depth image analysis.

313 Estimating Body Condition Score of Dairy Cows from Color Depth Images Using a Mobile Device

Abstract Body condition score (BCS) is a commonly used tool to monitor body tissue mobilization in dairy cows and manage potential health issues associated with negative energy balance. However, BCS is a subjective measurement that requires a trained evaluator and is time-consuming. Consequently, the development of a computer vision system to assess BCS in real-time can have a crucial role to optimize management decisions. Recently, smartphones started to be equipped with depth sensors, which allow the acquisition and analysis of depth images in real-time. In this study, our objective was to estimate BCS of dairy cows using color depth images collected from a mobile device. A total of 276 images were collected from 31 Holstein dairy cows containing, acquired at the UW-Madison Dairy Cattle Research Center (Madison, WI). The images were collected with an iPhone 13 Pro using the advanced Dual-camera system from a rear view of the animal. The distance between the animal and the evaluator was kept constant. Two trained evaluators were asked to assess BCS of each cow. The score provided by each evaluator was used to train a deep learning algorithm. The analysis was implemented in Python, and Keras and TensorFlow were used to train the deep neural network. A pre-trained network based on the Xception architecture was used, and transfer learning was adopted by extracting the weights trained on Imagenet. A leave-one-out cross-validation strategy was used to split the data into training and testing sets. Our results showed that the model presented an average accuracy of 60% and 40% for color and color depth images, respectively, in the testing set. Our results indicate that it is possible to use a mobile device to develop computer vision tools to predict BCS of dairy cows.

A Novel, Automated, and Real-Time Method for the Analysis of Non-Human Primate Behavioral Patterns Using a Depth Image Sensor

By virtue of their upright locomotion, similar to that of humans, motion analysis of non-human primates has been widely used in order to better understand musculoskeletal biomechanics and neuroscience problems. Given the difficulty of conducting a marker-based infrared optical tracking system for the behavior analysis of primates, a 2-dimensional (D) video analysis has been applied. Distinct from a conventional marker-based optical tracking system, a depth image sensor system provides 3-D information on movement without any skin markers. The specific aim of this study was to develop a novel algorithm to analyze the behavioral patterns of non-human primates in a home cage using a depth image sensor. The behavioral patterns of nine monkeys in their home cage, including sitting, standing, and pacing, were captured using a depth image sensor. Thereafter, these were analyzed by observers’ manual assessment and the newly written automated program. We confirmed that the measurement results from the observers’ manual assessments and the automated program with depth image analysis were statistically identical.

Contactless Monitoring of Breathing Pattern and Thoracoabdominal Asynchronies in Preterm Infants Using Depth Cameras: A Feasibility Study

Objective: Monitoring infants’ breathing activity is crucial in research and clinical applications but remains a challenge. This study aims to develop a contactless method to monitor breathing patterns and thoracoabdominal asynchronies in infants inside the incubator, using depth cameras. Methods: We proposed an algorithm to extract the 3D displacements of the ribcage and abdomen from the analysis of depth images. We evaluated the accuracy of the system in-vitro vs. a reference motion capture analyzer. We also conducted a feasibility study on 12 patients receiving non-invasive respiratory support to estimate the mean and the variability of the chest wall displacements in preterm infants and evaluate the suitability of the proposed system in the clinical setting. Results: In-vitro, the mean (95% CI) error in the measurement of amplitude, frequency and phase shift between compartmental displacements was −0.14 (−0.57, 0.28) mm, 0.02 (−0.99, 1.03) bpm, and −0.40 (−1.76, 0.95)°, respectively. In-vivo, the mean (95% CI) amplitude of the ribcage and abdomen displacements were 0.99 (0.34, 2.67) mm and 1.20 (0.40, 2.15) mm, respectively. Conclusions: The developed system proved accurate in-vitro and was suitable for the clinical environment. Clinical Impact: The proposed method has value for evaluating infants’ breathing patterns in research applications and, after further development, may represent a simple monitoring tool for infants’ respiratory activity inside the incubator.

Recognition of Manual Welding Positions from Depth Hole Image Remotely Sensed by RGB-D Camera

The proportion of welding work in total man-hours required for shipbuilding processes has been perceived to be significant, and welding man-hours are greatly affected by working posture. Continuous research has been conducted to identify the posture in welding by utilizing the relationship between man-hours and working posture. However, the results that reflect the effect of the welding posture on man-hours are not available. Although studies on posture recognition based on depth image analysis are being positively reviewed, welding operation has difficulties in image interpretation because an external obstacle caused by arcs exists. Therefore, any obstacle element must be removed in advance. This study proposes a method to acquire work postures using a low-cost RGB-D camera and recognize the welding position through image analysis. It removes obstacles that appear as depth holes in the depth image and restores the removed part to the desired state. The welder’s body joints are extracted, and a convolution neural network is used to determine the corresponding welding position. The restored image showed significantly improved recognition accuracy. The proposed method acquires, analyzes, and automates the recognition of welding positions in real-time. It can be applied to all areas where image interpretation is difficult due to obstacles.

Determination of Foam Stability in Lager Beers Using Digital Image Analysis of Images Obtained Using RGB and 3D Cameras

Foam stability and retention is an important indicator of beer quality and freshness. A full, white head of foam with nicely distributed small bubbles of CO2 is appealing to the consumers and the crown of the production process. However, raw materials, production process, packaging, transportation, and storage have a big impact on foam stability, which marks foam stability monitoring during all these stages, from production to consumer, as very important. Beer foam stability is expressed as a change of foam height over a certain period. This research aimed to monitor the foam stability of lager beers using image analysis methods on two different types of recordings: RGB and depth videos. Sixteen different commercially available lager beers were subjected to analysis. The automated image analysis method based only on the analysis of RGB video images proved to be inapplicable in real conditions due to problems such as reflection of light through glass, autofocus, and beer lacing/clinging, which make it impossible to accurately detect the actual height of the foam. A solution to this problem, representing a unique contribution, was found by introducing the use of a 3D camera in estimating foam stability. According to the results, automated analysis of depth images obtained from a 3D camera proved to be a suitable, objective, repeatable, reliable, and sufficiently sensitive method for measuring foam stability of lager beers. The applied model proved to be suitable for predicting changes in foam retention of lager beers.

SEMBLANCE RESIDUAL MOVEOUT ANALYSIS TO FIND ERORRS AND UPDATING THE INTERVAL VELOCITY MODEL MODE IN THE HORIZON BASED TOMOGRAPHY METHOD

The tomography method requires an excellent initial velocity model. On the horizon based tomography, it will correct the travel time error of seismic waves along the horizon which is analysed using input results from the analysis of residual depth moveout. In this study, a semblance residual moveout analysis will be conducted after the interval velocity model has applied to the SBI field seismic data (CDP Gathers and RMS velocity). Based on the imaging results generated by the PSDM running process, an aperture value of 550 for inline and 800 for crossline is selected. PSDM generated from the initial interval velocity model has an acoustic impedance value between 1000 kg/m2s to 14339.2 kg/m2s. The PSDM process, residual moveout analysis, and horizon-based tomography are carried out iteratively until the error in the interval velocity model approaches zero. In this study, five iterations were performed. The resulting residual moveout is increasingly oscillating around zero after the 5th iteration, which indicates that the error in the interval velocity model is getting smaller. There are two types of residual moveout, namely residuals moveout positively and residuals moveout negatively. Residual moveout positive indicates that the velocity used is too high, while the residual moveout negative indicates that the velocity used is too low. The identification of interval velocity model errors with analysis of residual moveout semblance is calculated from depth gathers. The semblance residual moveout analysis is used for the Pre Stack Depth Migration (PSDM) depth image analysis stage along with the marker (well data). .

Automatic body condition scoring system for dairy cows based on depth-image analysis

Body condition score (BCS) is an important management tool in the modern dairy industry, and one of the basic techniques for animal welfare and precision dairy farming. The objective of this study was to use a vision system to evaluate the fat cover on the back of cows and to automatically determine BCS. A 3D camera was used to capture the depth images of the back of cows twice a day as each cow passed beneath the camera. Through background subtraction, the back area of the cow was extracted from the depth image. The thurl, sacral ligament, hook bone, and pin bone were located via depth image analysis and evaluated by calculating their visibility and curvature, and those four anatomical features were used to measure fatness. A dataset containing 4820 depth images of cows with 7 BCS levels was built, among which 952 images were used as training data. Taking four anatomical features as input and BCS as output, decision tree learning, linear regression, and BP network were calibrated on the training dataset and tested on the entire dataset. On average, the BP network model scored each cow within 0.25 BCS points compared to their manual scores during the study period. The measured values of visibility and curvature used in this study have strong correlations with BCS and can be used to automatically assess BCS with high accuracy. This study demonstrates that the automatic body condition scoring system has the possibility of being more accurate than human scoring. Keywords: body condition score, depth-image processing, curvature analysis, machine learning, precision dairy farming DOI: 10.25165/j.ijabe.20201304.5655 Citation: Zhao K X, Shelley A N, Lau D L, Dolecheck K A, Bewley J M. Automatic body condition scoring system for dairy cows based on depth-image analysis. Int J Agric & Biol Eng, 2020; 13(4): 45–54.

Automatic body condition scoring system for dairy cows based on depth-image analysis

Automatic body condition scoring system for dairy cows based on depth-image analysis

Detection of aggressive behaviours in pigs using a RealSence depth sensor

The aim of this study is to develop a depth image analysis method to automatically detect aggressive behaviours of group-housed pigs. In this work 2 experiments were performed. In each experiment, 8 pigs from 3 pens were mixed for 3 days and then 8 h of video was recorded in each day. In the 24 h data of the first experiment, all the 883 aggressive 3 s-units and manually selected 883 non-aggressive 3 s-units were used as training set. In the 24 h data of the second experiment, all the 856 aggressive 3 s-units and manually selected 856 non-aggressive 3 s-units were used as test set. Firstly, frame-to-frame distance was set and then frame difference method was used to obtain moving pixels. Secondly, moving pixels caused by non-aggressive behaviours were removed by setting threshold of connected area. Number of filtered moving pixels were summed and defined as motion shape index (MSI) in each frame. After dividing all videos into 3 s-units, the maximum, mean, variance and standard deviation of MSI in each unit were extracted as features. Finally, support vector machine (SVM) was used to classify these features in order to detect aggression. Using the proposed algorithm, aggressive behaviours could be detected with an accuracy of 97.5%, a sensitivity of 98.2%, specificity of 96.7% and precision of 96.8%. The results indicate that this algorithm can be used to detect aggressive behaviours of pigs.

A novel depth image analysis for sleep posture estimation

Recognition of sleep posture and its changes are related to information monitoring in a number of health-related applications such as apnea prevention and elderly care. This paper uses a less privacy-invading approach to classify sleep postures of a person in various configurations including side and supine postures. In order to accomplish this, a single depth sensor has been utilized to collect selective depth signals and populated a dataset associated with the depth data. The data is then analyzed by a novel frequency-based feature selection approach. These extracted features were then correlated in order to rank their information content in various 2D scans from the 3D point cloud in order to train a support vector machine (SVM). The data of subjects are collected under two conditions. First when they were covered with a thin blanket and second without any blanket. In order to reduce the dimensionality of the feature space, a T-test approach is employed to determine the most dominant set of features in the frequency domain. The proposed recognition approach based on the frequency domain is also compared with an approach using feature vector defined based on skeleton joints. The comparative studies are performed given various scenarios and by a variety of datasets. Through our study, it is shown that our proposed method offers better performance to that of the joint-based method.

Action recognition from point cloud patches using discrete orthogonal moments

3D sensors such as standoff Light Detection and Ranging (LIDAR) generate partial 3D point clouds that resemble patches of irregularly-shaped, coarse groups of points. 3D modeling of this type of data for human action recognition has been rarely studied. Although 2D---based depth image analysis is an option, its effectiveness on this type of low-resolution data hasn't been well answered. This paper investigates a new multi-scale 3D shape descriptor, based on the discrete orthogonal Tchebichef Moments, for the characterization of 3D action pose shapes made of low-resolution point cloud patches. Our shape descriptor consists of low-order 3D Tchebichef moments computed with respect to a new point cloud voxelization scheme that normalizes translation, scale, and resolution. The action recognition is built on the Naive Bayes classifier using temporal statistics of a `bag of pose shapes'. For performance evaluation, a synthetic LIDAR pose shape baseline was developed with 62 human subjects performing three actions - digging, jogging, and throwing. Our action classification experiments demonstrated that the 3D Tchebichef moment representation of point clouds achieves excellent action and viewing direction predictions with superb consistency across a large range of scale and viewing angle variations.

A novel medical human-computer interaction platform based on Kinect depth image analysis refactoring and neural network

The high level of progress in science and technology has escalated the use of medical surgical products, equipped the modern medical operating room with all kinds of high-tech digital and intelligent development and these new technologies have introduced the traditional surgeons to new types of surgeries and helped them become more sensitive to changes in the body. More and more state-of-the-art technologies have been proposed to assist the doctors to optimise the operation environment. It is the purpose of the man-machine interface design to make the computer more intelligent so that it can do a wider range of work. For better capturing the gesture and inner information based on Kinect, we revise the traditional methodologies on depth image analysis refactoring and neural network to construct a new systematic implementation paradigm. The experiment shows that our idea outperforms the other latest methodologies.

A novel medical human-computer interaction platform based on Kinect depth image analysis refactoring and neural network

The high level of progress in science and technology has escalated the use of medical surgical products, equipped the modern medical operating room with all kinds of high-tech digital and intelligent development and these new technologies have introduced the traditional surgeons to new types of surgeries and helped them become more sensitive to changes in the body. More and more state-of-the-art technologies have been proposed to assist the doctors to optimise the operation environment. It is the purpose of the man-machine interface design to make the computer more intelligent so that it can do a wider range of work. For better capturing the gesture and inner information based on Kinect, we revise the traditional methodologies on depth image analysis refactoring and neural network to construct a new systematic implementation paradigm. The experiment shows that our idea outperforms the other latest methodologies.

Automatic recognition of lactating sow behaviors through depth image processing

Manual observation and classification of animal behaviors is laborious, time-consuming, and of limited ability to process large amount of data. A computer vision-based system was developed that automatically recognizes sow behaviors (lying, sitting, standing, kneeling, feeding, drinking, and shifting) in farrowing crate. The system consisted of a low-cost 3D camera that simultaneously acquires digital and depth images and a software program that detects and identifies the sow’s behaviors. This paper describes the computational algorithm for the analysis of depth images and presents its performance in recognizing the sow’s behaviors as compared to manual recognition. The images were acquired at 6s intervals on three days of a 21-day lactation period. Based on analysis of the 6s interval images, the algorithm had the following accuracy of behavioral classification: 99.9% in lying, 96.4% in sitting, 99.2% in standing, 78.1% in kneeling, 97.4% in feeding, 92.7% in drinking, and 63.9% in transitioning between behaviors. The lower classification accuracy for the transitioning category presumably stemmed from insufficient frequency of the image acquisition which can be readily improved. Hence the reported system provides an effective way to automatically process and classify the sow’s behavioral images. This tool is conducive to investigating behavioral responses and time budget of lactating sows and their litters to farrowing crate designs and management practices.

3D depth image analysis for indoor fall detection of elderly people

This paper presents a new fall detection method of elderly people in a room environment based on shape analysis of 3D depth images captured by a Kinect sensor. Depth images are pre-processed by a median filter both for background and target. The silhouette of moving individual in depth images is achieved by a subtraction method for background frames. The depth images are converted to disparity map, which is obtained by the horizontal and vertical projection histogram statistics. The initial floor plane information is obtained by V disparity map, and the floor plane equation is estimated by the least square method. Shape information of human subject in depth images is analyzed by a set of moment functions. Coefficients of ellipses are calculated to determine the direction of individual. The centroids of the human body are calculated and the angle between the human body and the floor plane is calculated. When both the distance from the centroids of the human body to the floor plane and the angle between the human body and the floor plane are lower than some thresholds, fall incident will be detected. Experiments with different falling direction are performed. Experimental results show that the proposed method can detect fall incidents effectively.

Skin photoprotective and antiageing effects of a combination of rosemary (Rosmarinus officinalis) and grapefruit (Citrus paradisi) polyphenols

BackgroundPlant polyphenols have been found to be effective in preventing ultraviolet radiation (UVR)-induced skin alterations. A dietary approach based of these compounds could be a safe and effective method to provide a continuous adjunctive photoprotection measure. In a previous study, a combination of rosemary (Rosmarinus officinalis) and grapefruit (Citrus paradisi) extracts has exhibited potential photoprotective effects both in skin cell model and in a human pilot trial.ObjectiveWe investigated the efficacy of a combination of rosemary (R. officinalis) and grapefruit (C. paradisi) in decreasing the individual susceptibility to UVR exposure (redness and lipoperoxides) and in improving skin wrinkledness and elasticity.DesignA randomised, parallel group study was carried out on 90 subjects. Furthermore, a pilot, randomised, crossover study was carried out on five subjects. Female subjects having skin phototype from I to III and showing mild to moderate chrono- or photoageing clinical signs were enrolled in both studies. Skin redness (a* value of CIELab colour space) after UVB exposure to 1 minimal erythemal dose (MED) was assessed in the pilot study, while MED, lipoperoxides (malondialdehyde) skin content, wrinkle depth (image analysis), and skin elasticity (suction and elongation method) were measured in the main study.ResultsTreated subjects showed a decrease of the UVB- and UVA-induced skin alterations (decreased skin redness and lipoperoxides) and an improvement of skin wrinkledness and elasticity. No differences were found between the 100 and 250 mg extracts doses, indicating a plateau effect starting from 100 mg extracts dose. Some of the positive effects were noted as short as 2 weeks of product consumption.ConclusionsThe long-term oral intake of Nutroxsun™ can be considered to be a complementary nutrition strategy to avoid the negative effects of sun exposure. The putative mechanism for these effects is most likely to take place through the inhibition of UVR-induced reactive oxygen species and the concomitant inflammatory markers (lipoperoxides and cytokines) together with their direct action on intracellular signalling pathways.

Model-based hierarchical clustering with Bregman divergences and Fishers mixture model: application to depth image analysis

Model-based clustering is a method that clusters data with an assumption of a statistical model structure. In this paper, we propose a novel model-based hierarchical clustering method for a finite statistical mixture model based on the Fisher distribution. The main foci of the proposed method are: (a) provide efficient solution to estimate the parameters of a Fisher mixture model (FMM); (b) generate a hierarchy of FMMs and (c) select the optimal model. To this aim, we develop a Bregman soft clustering method for FMM. Our model estimation strategy exploits Bregman divergence and hierarchical agglomerative clustering. Whereas, our model selection strategy comprises a parsimony-based approach and an evaluation graph-based approach. We empirically validate our proposed method by applying it on simulated data. Next, we apply the method on real data to perform depth image analysis. We demonstrate that the proposed clustering method can be used as a potential tool for unsupervised depth image analysis.

What you see is not always what you get: A qualitative, comparative analysis of ex ante visualizations with ex post photography of landscape and architectural projects

This study presents a qualitative, comparative analysis of ex ante visualizations, created during planning and design phases, with ex post photography of landscape and architectural projects. Visualizations play an increasingly important role as decision-making tools in the planning process and are expected to successfully communicate proposals to both experts and laypersons. Outside of the wind farm industry there is a lack of detailed guidance for those creating landscape visualizations and currently no method of analyzing the accuracy of visualizations exists. In a world where we increasingly rely on information communicated in a visual manner it is imperative that potential viewers are provided with clues to enable them to distinguish between what is real and what is not. This study analyses a selection of visualizations from a cross section of landscape and architectural projects and reveals reoccurring patterns of inconsistencies in the depiction of content elements. The control of production through agreed guidelines proposed by previously published research could have both positive and negative effects for the future of visualization production. This research proposes that the starting point for honest communication lies in transparency, in both production techniques and presentation to clients, stakeholders and the public. There is scope for more in depth image analysis of a larger body of projects that may reveal more detailed findings that could contribute to future guideline discussions.