Showing papers on "Silhouette published in 2022"

Prediction of geological characteristics from shield operational parameters using integrating grid search and K-fold cross validation into stacking classification algorithm

Abstract: This study presents a framework for predicting geological characteristics based on integrating a stacking classification algorithm (SCA) with a grid search (GS) and K-fold cross validation (K-CV). The SCA includes two learner layers: a primary learner's layer and meta-classifier layer. The accuracy of the SCA can be improved by using the GS and K-CV. The GS was developed to match the hyper-parameters and optimise complicated problems. The K-CV is commonly applied to changing the validation set in a training set. In general, a GS is usually combined with K-CV to produce a corresponding evaluation index and select the best hyper-parameters. The torque penetration index (TPI) and field penetration index (FPI) are proposed based on shield parameters to express the geological characteristics. The elbow method (EM) and silhouette coefficient (Si) are employed to determine the types of geological characteristics (K) in a K-means++ algorithm. A case study on mixed ground in Guangzhou is adopted to validate the applicability of the developed model. The results show that with the developed framework, the four selected parameters, i.e. thrust, advance rate, cutterhead rotation speed and cutterhead torque, can be used to effectively predict the corresponding geological characteristics.

Multiple Events Detection Using Context-Intelligence Features

Abstract: Event detection systems are mainly used to observe and monitor human behavior via red green blue (RGB) images and videos. Event detection using RGB images is one of the challenging tasks of the current era. Human detection, position and orientation of human body parts in RGB images is a critical phase for numerous systems models. In this research article, the detection of human body parts by extracting context-aware energy features for event recognition is described. For this, silhouette extraction, estimation of human body parts, and context-aware features are extracted. To optimize the context-intelligence vector, we applied an artificial intelligence-based self-organized map (SOM) while a genetic algorithm (GA) is applied for multiple event detection. The experimental results on challenging RGB images and video-based datasets were promising. Three datasets were used. Event recognition and body parts detection accuracy rates for the University of central Florida’s (UCF) dataset were 88.88% and 86.75% respectively. 90.0% and 87.37% for event recognition and body parts detection were achieved over the University of Texas (UT) dataset. 87.89% and 85.87% for event recognition and body parts detection were achieved for the sports videos in the wild (SVW) dataset. The proposed system performs better than other current state-of-the-art approaches in terms of body parts and event detection and recognition outcomes.

An unsupervised cluster-based feature grouping model for early diabetes detection

Abstract: Diabetes mellitus is often a hyperglycemic condition that poses a substantial threat to human health. Early diabetes detection decreases morbidity and mortality. Due to the scarcity of labeled data and the presence of oddities in diabetes datasets, it is exceedingly difficult to develop a trustworthy and accurate diabetes prognosis. The dataset and groupings of the features using the elbow and silhouette methods have been clustered using K-means. Various machine learning approaches have also been applied to the cluster-based dataset to predict diabetes. We propose an unsupervised cluster-based feature grouping model for early diabetes identification using an open-source dataset containing the data of 520 diabetic patients. On the cluster-based dataset and the complete dataset, the maximum Accuracy (ACC) is 99.57% and 99.03%, respectively. The best Precision, Recall, minimum mean squared error (MSE), maximum mean squared error (MSE), and F1-Score of 1.000 are obtained from multi-layer perceptron (MLP), random forest (RF), and k-Nearest Neighbors (KNN), 0.984 from random forest (RF) and support vector machine (SVM), 0.010 from RF, 0.067 from KNN, and 99.20% from RF, respectively. A comparison table displays the anticipated outcomes and highlights the aspects of this research that are most likely to occur as intended. The preprocessed data and codes are available on the GitHub repository to https://github.com/mhashiq/Early-stage-diabetes-risk-prediction.

Object Pose Estimation using Mid-level Visual Representations

Abstract: This work proposes a novel pose estimation model for object categories that can be effectively transferred to pre-viously unseen environments. The deep convolutional network models (CNN) for pose estimation are typically trained and evaluated on datasets specifically curated for object detection, pose estimation, or 3D reconstruction, which requires large amounts of training data. In this work, we propose a model for pose estimation that can be trained with small amount of data and is built on the top of generic mid-level represen-tations [33] (e.g. surface normal estimation and re-shading). These representations are trained on a large dataset without requiring pose and object annotations. Later on, the predictions are refined with a small CNN neural network that exploits object masks and silhouette retrieval. The presented approach achieves superior performance on the Pix3D dataset [26] and shows nearly 35 % improvement over the existing models when only 25 % of the training data is available. We show that the approach is favorable when it comes to generalization and transfer to novel environments. Towards this end, we introduce a new pose estimation benchmark for commonly encountered furniture categories on challenging Active Vision Dataset [1] and evaluated the models trained on the Pix3D dataset.

RFMask: A Simple Baseline for Human Silhouette Segmentation with Radio Signals

Abstract: Human silhouette segmentation, which is originally defined in computer vision, has achieved promising results for understanding human activities. However, the physical limitation makes existing systems based on optical cameras suffer from severe performance degradation under low illumination, smoke, and/or opaque obstruction conditions. To overcome such limitations, in this paper, we propose to utilize the radio signals, which can traverse obstacles and are unaffected by the lighting conditions to achieve silhouette segmentation. The proposed RFMask framework is composed of three modules. It first transforms RF signals captured by millimeter wave radar on two planes into spatial domain and suppress interference with the signal processing module. Then, it locates human reflections on RF frames and extract features from surrounding signals with human detection module. Finally, the extracted features from RF frames are aggregated with an attention based mask generation module. To verify our proposed framework, we collect a dataset containing 804,760 radio frames and 402,380 camera frames with human activities under various scenes. Experimental results show that the proposed framework can achieve impressive human silhouette segmentation even under the challenging scenarios (such as low light and occlusion scenarios) where traditional optical-camera-based methods fail. To the best of our knowledge, this is the first investigation towards segmenting human silhouette based on millimeter wave signals. We hope that our work can serve as a baseline and inspire further research that perform vision tasks with radio signals. The dataset and codes will be made in public.

Sex Differences in Body Image Perception and Ideals: Analysis of Possible Determinants

Abstract: The study analyzed the differences between sexes in body image perception and body ideals to assess possible dissatisfaction and misinterpretation in the body image considered attractive for the other sex. Moreover, the influence of anthropometric traits and sports practice on body dissatisfaction and misjudgment was evaluated. Using a cross-sectional design, 960 Italian university students were investigated. Anthropometric characteristics were measured directly. Assessment of body image perception was performed using Thompson and Gray’s silhouettes. We developed two new indexes to assess the possible discrepancy between (1) the perceived silhouette of one’s body and that of the same sex deemed attractive to the other sex (FAD); (2) the silhouette is deemed attractive to the opposite sex and the average attractive silhouette selected by the opposite sex (AMOAD). As expected, females showed greater dissatisfaction with their bodies than males concerning both their own ideal and the silhouette they considered attractive to the opposite sex. Although both sexes misjudged the attractive silhouette for the opposite sex, women were found to be more wrong. According to the outcomes of multivariate regression models, stature, body composition parameters, amount of sport, sex, and FAD were significant predictors of dissatisfaction and misjudgment. In addition to action aimed at correcting misperceptions, the study revealed the importance of sports participation in improving the perception and acceptance of one’s body image.

Self-Care Assessment for Daily Living Using Machine Learning Mechanism

Abstract: Nowadays, activities of daily living (ADL) recognition system has been considered an important field of computer vision. Wearable and optical sensors are widely used to assess the daily living activities in healthy people and people with certain disorders. Although conventional ADL utilizes RGB optical sensors but an RGB-D camera with features of identifying depth (distance information) and visual cues has greatly enhanced the performance of activity recognition. In this paper, an RGB-D-based ADL recognition system has been presented. Initially, human silhouette has been extracted from the noisy background of RGB and depth images to track human movement in a scene. Based on these silhouettes, full body features and point based features have been extracted which are further optimized with probability based incremental learning (PBIL) algorithm. Finally, random forest classifier has been used to classify activities into different categories. The n-fold cross-validation scheme has been used to measure the viability of the proposed model on the RGBD-AC benchmark dataset and has achieved an accuracy of 92.71% over other state-of-the-art methodologies.

A Multi-Modal Gait Analysis-Based Detection System of the Risk of Depression

Abstract: Currently, depression has become a common mental disorder, especially among postgraduates. It is reported that postgraduates have a higher risk of depression than the general public, and they are more sensitive to contact with others. Thus, a non-contact and effective method for detecting people at risk of depression becomes an urgent demand. In order to make the recognition of depression more reliable and convenient, we propose a multi-modal gait analysis-based depression detection method that combines skeleton modality and silhouette modality. Firstly, we propose a skeleton feature set to describe depression and train a Long Short-Term Memory (LSTM) model to conduct sequence strategy. Secondly, we generate Gait Energy Image (GEI) as silhouette features from RGB videos, and design two Convolutional Neural Network (CNN) models with a new loss function to extract silhouette features from front and side perspectives. Then, we construct a multi-modal fusion model consisting of fusing silhouettes from the front and side views at the feature level and the classification results of different modalities at the decision level. The proposed multi-modal model achieved accuracy at 85.45% in the dataset consisting of 200 postgraduate students (including 86 depressive ones), 5.17% higher than the best single-mode model. The multi-modal method also shows improved generalization by reducing the gender differences. Furthermore, we design a vivid 3D visualization of the gait skeletons, and our results imply that gait is a potent biometric for depression detection.

Towards a Deeper Understanding of Skeleton-based Gait Recognition

Abstract: Gait recognition is a promising biometric with unique properties for identifying individuals from a long distance by their walking patterns. In recent years, most gait recognition methods used the person’s silhouette to extract the gait features. However, silhouette images can lose fine-grained spatial information, suffer from (self) occlusion, and be challenging to obtain in real-world scenarios. Furthermore, these silhouettes also contain other visual clues that are not actual gait features and can be used for identification, but also to fool the system. Model-based methods do not suffer from these problems and are able to represent the temporal motion of body joints, which are actual gait features. The advances in human pose estimation started a new era for model-based gait recognition with skeleton-based gait recognition. In this work, we propose an approach based on Graph Convolutional Networks (GCNs) that combines higher-order inputs, and residual networks to an efficient architecture for gait recognition. Extensive experiments on the two popular gait datasets, CASIA-B and OUMVLP-Pose, show a massive improvement (3×) of the state-of-the-art (SotA) on the largest gait dataset OUMVLP-Pose and strong temporal modeling capabilities. Finally, we visualize our method to understand skeleton-based gait recognition better and to show that we model real gait features.

Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition

Abstract: Gait is considered the walking pattern of human body, which includes both shape and motion cues. However, the main-stream appearance-based methods for gait recognition rely on the shape of silhouette. It is unclear whether motion can be explicitly represented in the gait sequence modeling. In this paper, we analyzed human walking using the Lagrange's equation and come to the conclusion that second-order information in the temporal dimension is necessary for identification. We designed a second-order motion extraction module based on the conclusions drawn. Also, a light weight view-embedding module is designed by analyzing the problem that current methods to cross-view task do not take view itself into consideration explicitly. Experiments on CASIA-B and OU-MVLP datasets show the effectiveness of our method and some visualization for extracted motion are done to show the interpretability of our motion extraction module.

Analysis of Few-Shot Techniques for Fungal Plant Disease Classification and Evaluation of Clustering Capabilities Over Real Datasets

Abstract: Plant fungal diseases are one of the most important causes of crop yield losses. Therefore, plant disease identification algorithms have been seen as a useful tool to detect them at early stages to mitigate their effects. Although deep-learning based algorithms can achieve high detection accuracies, they require large and manually annotated image datasets that is not always accessible, specially for rare and new diseases. This study focuses on the development of a plant disease detection algorithm and strategy requiring few plant images (Few-shot learning algorithm). We extend previous work by using a novel challenging dataset containing more than 100,000 images. This dataset includes images of leaves, panicles and stems of five different crops (barley, corn, rape seed, rice, and wheat) for a total of 17 different diseases, where each disease is shown at different disease stages. In this study, we propose a deep metric learning based method to extract latent space representations from plant diseases with just few images by means of a Siamese network and triplet loss function. This enhances previous methods that require a support dataset containing a high number of annotated images to perform metric learning and few-shot classification. The proposed method was compared over a traditional network that was trained with the cross-entropy loss function. Exhaustive experiments have been performed for validating and measuring the benefits of metric learning techniques over classical methods. Results show that the features extracted by the metric learning based approach present better discriminative and clustering properties. Davis-Bouldin index and Silhouette score values have shown that triplet loss network improves the clustering properties with respect to the categorical-cross entropy loss. Overall, triplet loss approach improves the DB index value by 22.7% and Silhouette score value by 166.7% compared to the categorical cross-entropy loss model. Moreover, the F-score parameter obtained from the Siamese network with the triplet loss performs better than classical approaches when there are few images for training, obtaining a 6% improvement in the F-score mean value. Siamese networks with triplet loss have improved the ability to learn different plant diseases using few images of each class. These networks based on metric learning techniques improve clustering and classification results over traditional categorical cross-entropy loss networks for plant disease identification.

Antenatal diagnosis of congenital heart disease by 3D ultrasonography using spatiotemporal image correlation with HDlive Flow and HDlive Flow silhouette rendering modes

Abstract: This pictorial review describes the assessment of a great variety of types of congenital heart disease by three-dimensional ultrasonography with spatiotemporal image correlation using HDlive and the HDlive Flow silhouette rendering mode. These technologies provide fetal heart surface patterns by using a fixed virtual light source that propagates into the tissues, permitting a detailed reconstruction of the heart structures. In this scenario, ultrasound operators can freely select a better light source position to enhance the anatomical details of the fetal heart. HDlive and the HDlive Flow silhouette rendering mode improve depth perception and the resolution of anatomic cardiac details and blood vessel walls compared to standard two-dimensional ultrasonography.

Panicle-3D: a low-cost 3D-modeling method for rice panicles based on deep learning, shape from silhouette, and supervoxel clustering

Abstract: Self-occlusions are common in rice canopy images and strongly influence the calculation accuracies of panicle traits. Such interference can be largely eliminated if panicles are phenotyped at the 3D level. Research on 3D panicle phenotyping has been limited. Given that existing 3D modeling techniques do not focus on specified parts of a target object, an efficient method for panicle modeling of large numbers of rice plants is lacking. This paper presents an automatic and nondestructive method for 3D panicle modeling. The proposed method integrates shoot rice reconstruction with shape from silhouette, 2D panicle segmentation with a deep convolutional neural network, and 3D panicle segmentation with ray tracing and supervoxel clustering. A multiview imaging system was built to acquire image sequences of rice canopies with an efficiency of approximately 4 min per rice plant. The execution time of panicle modeling per rice plant using 90 images was approximately 26 min. The outputs of the algorithm for a single rice plant are a shoot rice model, surface shoot rice model, panicle model, and surface panicle model, all represented by a list of spatial coordinates. The efficiency and performance were evaluated and compared with the classical structure-from-motion algorithm. The results demonstrated that the proposed method is well qualified to recover the 3D shapes of rice panicles from multiview images and is readily adaptable to rice plants of diverse accessions and growth stages. The proposed algorithm is superior to the structure-from-motion method in terms of texture preservation and computational efficiency. The sample images and implementation of the algorithm are available online. This automatic, cost-efficient, and nondestructive method of 3D panicle modeling may be applied to high-throughput 3D phenotyping of large rice populations.

Augmented Humanity: A Systematic Mapping Review

Abstract: Augmented humanity (AH) is a term that has been mentioned in several research papers. However, these papers differ in their definitions of AH. The number of publications dealing with the topic of AH is represented by a growing number of publications that increase over time, being high impact factor scientific contributions. However, this terminology is used without being formally defined. The aim of this paper is to carry out a systematic mapping review of the different existing definitions of AH and its possible application areas. Publications from 2009 to 2020 were searched in Scopus, IEEE and ACM databases, using search terms “augmented human”, ”human augmentation” and “human 2.0”. Of the 16,914 initially obtained publications, a final number of 133 was finally selected. The mapping results show a growing focus on works based on AH, with computer vision being the index term with the highest number of published articles. Other index terms are wearable computing, augmented reality, human–robot interaction, smart devices and mixed reality. In the different domains where AH is present, there are works in computer science, engineering, robotics, automation and control systems and telecommunications. This review demonstrates that it is necessary to formalize the definition of AH and also the areas of work with greater openness to the use of such concept. This is why the following definition is proposed: “Augmented humanity is a human–computer integration technology that proposes to improve capacity and productivity by changing or increasing the normal ranges of human function through the restoration or extension of human physical, intellectual and social capabilities”.

Two components of body-image disturbance are differentially associated with distinct eating disorder characteristics in healthy young women

Abstract: Body-image disturbance comprises two components. The first is perceptual in nature, and is measured by a discrepancy between one’s actual body and perceived self-image (“perceived–actual discrepancy”). The other component is affective, and is measured by a discrepancy between one’s perceived self-image and ideal body image (“perceived–ideal discrepancy”). The present study evaluated the relationships between body-image disturbance and characteristics of eating disorders such as symptoms and related personality traits. In a psychophysiological experiment, female university students (mean ± SD age = 21.0 ± 1.38 years) were presented with silhouette images of their own bodies that were distorted in terms of width. The participants were asked whether each silhouette image was more overweight than their actual or ideal body images. Eating-disorder characteristics were assessed using six factors from the Japanese version of the Eating Disorder Inventory 2 (EDI2). We found that perceived–actual discrepancies correlated with negative self-evaluation (i.e., factor 3 of the EDI2), whereas perceived–ideal discrepancies correlated with dissatisfaction with one’s own body (i.e., factor 2 of EDI2). These results imply that distinct psychological mechanisms underlie the two components of body-image disturbance.

Clustering Techniques Selection for a Hybrid Regression Model: A Case Study Based on a Solar Thermal System

Abstract: Abstract This work addresses the performance comparison between four clustering techniques with the objective of achieving strong hybrid models in supervised learning tasks. A real dataset from a bio-climatic house named Sotavento placed on experimental wind farm and located in Xermade (Lugo) in Galicia (Spain) has been collected. Authors have chosen the thermal solar generation system in order to study how works applying several cluster methods followed by a regression technique to predict the output temperature of the system. With the objective of defining the quality of each clustering method two possible solutions have been implemented. The first one is based on three unsupervised learning metrics (Silhouette, Calinski-Harabasz and Davies-Bouldin) while the second one, employs the most common error measurements for a regression algorithm such as Multi Layer Perceptron.

Automated visual surveying of vehicle heights to help measure the risk of overheight collisions using deep learning and view geometry

Abstract: Overheight vehicle collisions continuously pose a serious threat to transportation infrastructure and public safety. This study proposed a vision‐based method for automatic vehicle height measurement using deep learning and view geometry. In this method, vehicle instances are first segmented from traffic surveillance video frames by exploiting mask region‐based convolutional neural network (Mask R‐CNN). Then, 3D bounding box on each vehicle instance is constructed using the obtained vehicle silhouette and three orthogonal vanishing points in the surveilled traffic scene. By doing so, the vertical edges of the constructed 3D bounding box are directly associated with the vehicle image height. Last, the vehicle's physical height is computed by referencing an object with a known height in the traffic scene using single view metrology. A field experiment was performed to evaluate the performance of the proposed method, leading to the mean and maximum errors of 3.6 and 6.6, 5.8 and 12.9, 4.4 and 8.1, and 9.2 and 18.5 cm for cars, buses, vans, and trucks, respectively. The experiment also demonstrated the ability of the method to overcome vehicle occlusion, shadow, and irregular appearance interferences in height estimation suffered by existing image‐based methods. The results signified the potential of the proposed method for overheight vehicle detection and collision warning in real traffic settings.

iRaPCA and SOMoC: Development and Validation of Web Applications for New Approaches for the Clustering of Small Molecules

Abstract: The clustering of small molecules implies the organization of a group of chemical structures into smaller subgroups with similar features. Clustering has important applications to sample chemical datasets or libraries in a representative manner (e.g., to choose, from a virtual screening hit list, a chemically diverse subset of compounds to be submitted to experimental confirmation, or to split datasets into representative training and validation sets when implementing machine learning models). Most strategies for clustering molecules are based on molecular fingerprints and hierarchical clustering algorithms. Here, two open-source in-house methodologies for clustering of small molecules are presented: iterative Random subspace Principal Component Analysis clustering (iRaPCA), an iterative approach based on feature bagging, dimensionality reduction, and K-means optimization; and Silhouette Optimized Molecular Clustering (SOMoC), which combines molecular fingerprints with the Uniform Manifold Approximation and Projection (UMAP) and Gaussian Mixture Model algorithm (GMM). In a benchmarking exercise, the performance of both clustering methods has been examined across 29 datasets containing between 100 and 5000 small molecules, comparing these results with those given by two other well-known clustering methods, Ward and Butina. iRaPCA and SOMoC consistently showed the best performance across these 29 datasets, both in terms of within-cluster and between-cluster distances. Both iRaPCA and SOMoC have been implemented as free Web Apps and standalone applications, to allow their use to a wide audience within the scientific community.

Rendering Neural Materials on Curved Surfaces

Abstract: Neural material reflectance representations address some limitations of traditional analytic BRDFs with parameter textures; they can theoretically represent any material data, whether a complex synthetic microgeometry with displacements, shadows and inter-reflections, or real measured reflectance. However, they still approximate the material on an infinite plane, which prevents them from correctly handling silhouette and parallax effects for viewing directions close to grazing. The goal of this paper is to design a neural material representation capable of correctly handling such silhouette effects. We extend the neural network query to take surface curvature information as input, while the query output is extended to return a transparency value in addition to reflectance. We train the new neural representation on synthetic data that contains queries spanning a variety of surface curvatures. We show an ability to accurately represent complex silhouette behavior that would traditionally require more expensive and less flexible techniques, such as on-the-fly geometry displacement or ray marching.

Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models

Abstract: Person identification is a problem that has received substantial attention, particularly in security domains. Gait recognition is one of the most convenient approaches enabling person identification at a distance without the need for high-quality images. There are several review studies addressing person identification such as the utilization of facial images, silhouette images, and wearable sensor. Despite skeleton-based person identification gaining popularity while overcoming the challenges of traditional approaches, existing survey studies lack the comprehensive review of skeleton-based approaches to gait identification. We present a detailed review of the human pose estimation and gait analysis that makes the skeleton-based approaches possible. The study covers various types of related datasets, tools, methodologies, and evaluation metrics with associated challenges, limitations, and application domains. Detailed comparisons are presented for each of these aspects with recommendations for potential research and alternatives. A common trend throughout this paper is the positive impact that deep learning techniques are beginning to have on topics such as human pose estimation and gait identification. The survey outcomes might be useful for the related research community and other stakeholders in terms of performance analysis of existing methodologies, potential research gaps, application domains, and possible contributions in the future.