Clothing Variations Research Articles

Stacked-gait: A human gait recognition scheme based on stacked autoencoders.

Human gait recognition (HGR) is the mechanism of biometrics that authors extensively employ to recognize an individuals based on their walking traits. HGR has been prominent for the past few years due to its surveillance capability. In HGR, an individual's walking attributes are utilized for identification. HGR is considered a very effective technique for recognition but faces different problematic factors that degrade its performance. The major factors are variations in clothing, carrying, walking, etc. In this paper, a new hybrid method for the classification of HGR is designed called Stacked-Gait. The system is based on six major steps; initially, image resizing is performed to overcome computation problems. In the second step, these images are converted into grey-scale to extract better features. After that, the dataset division is performed into train and test set. In the next step, the training of the autoencoders and feature extraction of the dataset are performed using training data. In the next step, the stacking of two autoencoders is also performed. After that, the stacked encoders are employed to extract features from the test data. Finally, the feature vectors are given as input to various machine learning classifiers for final classification. The method assessment is performed using the CASIA-B dataset and achieved the accuracy of 99.90, 98.10, 97.20, 97.20, 96.70, and 100 percent on 000, 180, 360, 540, 720, and 900 angles. It is pragmatic that the system gives promising results compared to recent schemes.

Comparing the efficacy of different climate indices for prediction of labor loss, body temperatures, and thermal perception in a wide variety of warm and hot climates.

The purpose of this study was to investigate which climate/heat indices perform best in predicting heat-induced loss of physical work capacity (PWCloss). Integrating data from earlier studies, data from 982 exposures (75 conditions) exercising at a fixed cardiovascular load of 130 beats·min-1, in varying temperatures (15-50°C), humidities (20-80%), solar radiation (0-800 W·m-2), wind (0.2-3.5 m·s-1), and two clothing levels, were used to model the predictive power of ambient temperature, universal thermal climate index (UTCI), wet bulb globe temperature (WBGT), modified physiologically equivalent temperature (mPET), heat index, apparent temperature (AT), and wet bulb temperature (Twb) for the calculation of PWCloss, skin temperature (Tskin) and core-to-skin temperature gradient, and thermal perception (thermal sensation vote, TSV) in the heat. R2, RMSE, and Akaike information criterion were used indicating model performance. Indices not including wind/radiation in their calculation (Ta, heat index, AT, and Twb) struggled to provide consistent predictions across variables. For PWCloss and TSV, UTCI and WBGT had the highest predictive power. For Tskin, and core-to-skin temperature gradient, the physiological models UTCI and mPET worked best in seminude conditions, but clothed, AT, WBGT, and UTCI worked best. For all index predictions, Ta, vapor pressure, and Twb were shown to be the worst heat strain predictors. Although UTCI and WBGT had similar model performance using the full dataset, WBGT did not work appropriately in windy, hot-dry, conditions where WBGT predicted lower strain due to wind, whereas the empirical data, UTCI and mPET indicated that wind in fact increased the overall level of thermal strain. The findings of the current study highlight the advantages of using a physiological model-based index like UTCI when evaluating heat stress in dynamic thermal environments.NEW & NOTEWORTHY There is an urgent need to determine the optimal heat stress metric when forecasting the impact of heat stress on human performance, physiological stress, and perception. We analyzed a wealth of laboratory data, simulating heart rate (HR)-paced work with wide variations in air temperature, humidity, wind speed, solar radiation, and clothing. We conclude that the universal thermal climate index (UTCI) [followed by wet-bulb globe temperature (WBGT)] is the optimal heat index to reliably predict reductions in performance, and elevations in physiological and perceptual stress.

Emerging trends in gait recognition based on deep learning: a survey.

Gait recognition, a biometric identification method, has garnered significant attention due to its unique attributes, including non-invasiveness, long-distance capture, and resistance to impersonation. Gait recognition has undergone a revolution driven by the remarkable capacity of deep learning to extract complicated features from data. An overview of the current developments in deep learning-based gait identification methods is provided in this work. We explore and analyze the development of gait recognition and highlight its uses in forensics, security, and criminal investigations. The article delves into the challenges associated with gait recognition, such as variations in walking conditions, viewing angles, and clothing as well. We discuss about the effectiveness of deep neural networks in addressing these challenges by providing a comprehensive analysis of state-of-the-art architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and attention mechanisms. Diverse neural network-based gait recognition models, such as Gate Controlled and Shared Attention ICDNet (GA-ICDNet), Multi-Scale Temporal Feature Extractor (MSTFE), GaitNet, and various CNN-based approaches, demonstrate impressive accuracy across different walking conditions, showcasing the effectiveness of these models in capturing unique gait patterns. GaitNet achieved an exceptional identification accuracy of 99.7%, whereas GA-ICDNet showed high precision with an equal error rate of 0.67% in verification tasks. GaitGraph (ResGCN+2D CNN) achieved rank-1 accuracies ranging from 66.3% to 87.7%, whereas a Fully Connected Network with Koopman Operator achieved an average rank-1 accuracy of 74.7% for OU-MVLP across various conditions. However, GCPFP (GCN with Graph Convolution-Based Part Feature Polling) utilizing graph convolutional network (GCN) and GaitSet achieves the lowest average rank-1 accuracy of 62.4% for CASIA-B, while MFINet (Multiple Factor Inference Network) exhibits the lowest accuracy range of 11.72% to 19.32% under clothing variation conditions on CASIA-B. In addition to an across-the-board analysis of recent breakthroughs in gait recognition, the scope for potential future research direction is also assessed.

HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations

Existing gait recognition benchmarks mostly include minor clothing variations in the laboratory environments, but lack persistent changes in appearance over time and space. In this paper, we propose the first in-the-wild benchmark CCGait for cloth-changing gait recognition, which incorporates diverse clothing changes, indoor and outdoor scenes, and multi-modal statistics over 92 days. To further address the coupling effect of clothing and viewpoint variations, we propose a hybrid approach HybridGait that exploits both temporal dynamics and the projected 2D information of 3D human meshes. Specifically, we introduce a Canonical Alignment Spatial-Temporal Transformer (CA-STT) module to encode human joint position-aware features, and fully exploit 3D dense priors via a Silhouette-guided Deformation with 3D-2D Appearance Projection (SilD) strategy. Our contributions are twofold: we provide a challenging benchmark CCGait that captures realistic appearance changes over expanded time and space, and we propose a hybrid framework HybridGait that outperforms prior works on CCGait and Gait3D benchmarks. Our project page is available at https://github.com/HCVLab/HybridGait.

We are all exposed, but some are more exposed than others

ABSTRACT This paper defines functional cold exposure zones that illustrate whether a person is at risk of developing physical performance loss or cold weather injuries. Individual variation in body characteristics, activity level, clothing and protective equipment all contribute to variation in the effective exposure. Nevertheless, with the right education, training, and cold-adapted behaviours the exposure differences might not necessarily lead to increased risk for cold injury. To support the preparation process for cold weather operations, this paper presents a biophysical analysis explaining how much cold exposure risk can vary between individuals in the same environment. The results suggest that smaller persons are prone to be underdressed for moderate activity levels and larger persons are prone to be overdressed. The consequences of these discrepancies place people at different risks for performance loss or cold weather injuries. Nonetheless, even if all are well-dressed at the whole-body level, variation in hand morphology is also expected to influence hand skin temperatures that can be maintained; with smaller hands being more prone to reach skin temperatures associated with dexterity loss or cold weather injuries. In conclusion, this work focusses on bringing cold science to the Arctic warrior, establishing that combating cold stress is not a one size fits all approach.

Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data

Walking gait data acquired with force platforms may be used for person re-identification (re-ID) in various authentication, surveillance, and forensics applications. Current force platform-based re-ID systems classify a fixed set of identities (IDs), which presents a problem when IDs are added or removed from the database. We formulated force platform-based re-ID as a deep metric learning (DML) task, whereby a deep neural network learns a feature representation that can be compared between inputs using a distance metric. The force platform dataset used in this study is one of the largest and the most comprehensive of its kind, containing 193 IDs with significant variations in clothing, footwear, walking speed, and time between trials. Several DML model architectures were evaluated in a challenging setting where none of the IDs were seen during training (i.e., zero-shot re-ID) and there was only one prior sample per ID to compare with each query sample. The best architecture was 85% accurate in this setting, though an analysis of changes in walking speed and footwear between measurement instances revealed that accuracy was 28% higher on same-speed, same-footwear comparisons, compared to cross-speed, cross-footwear comparisons. These results demonstrate the potential of DML algorithms for zero-shot re-ID using force platform data, and highlight challenging cases.

Sistem Rekomendasi Pakaian Muslim Toko Al-Fath Semarang Dengan Collaborative Filtering

The many variations of Muslim clothing make customers confused in determining which clothes to buy. One solution is to use a recommendation system that can help customers find clothes according to their wants and needs. This study aims to create a product recommendation system that can provide product recommendations to Muslim clothing stores using the collaborative filtering method. The recommendation results will only display a maximum of 6 Muslim clothes that have been seen or purchased based on the similarity value of the highest Muslim clothing to the recommendation level with the lowest similarity. The results of Muslim clothing recommendations from customer A are Queen Dress (P0007) with a similarity value of 2.00, Trimuji Toyobo (P0006) with a similarity value of 1.40, Wonder Set 3in1 (P0008) with a similarity value of 1.00, Afnan Atasan Tunik (P0009 ) with a similarity value of 1.00 and Abaya Embroidery Maxi (P0010) with a similarity value of 1.00

A Lightweight System Towards Viewing Angle and Clothing Variation in Gait Recognition

In this paper, the authors have proposed a computationally efficient, robust, and lightweight system for gait recognition. The proposed system contains two main stages: In the first stage, a classification network identifies optical flow corners in the normalized silhouette and calculates the distances traveled in every viewpoint which is further used by a regression model to identify the viewing angle. In the second stage, a feature extraction network computes the gait energy image (GEI) for every viewpoint and then uses principal component analysis (PCA) to extract low dimensional feature vectors from these GEI images. Finally, a multi-layer perceptron model is trained using the extracted principal components for every viewing angle. The performance of a system is comprehensively evaluated on the CASIA B and OULP gait dataset. The experimental results demonstrate the superior performance of a proposed system in viewing angle classification (100% accuracy), gait recognition (100% accuracy in normal walk), computational efficiency, robustness to clothing, and viewing angle variation.

Deep Full-Body HPE for Activity Recognition from RGB Frames Only

Human Pose Estimation (HPE) is defined as the problem of human joints’ localization (also known as keypoints: elbows, wrists, etc.) in images or videos. It is also defined as the search for a specific pose in space of all articulated joints. HPE has recently received significant attention from the scientific community. The main reason behind this trend is that pose estimation is considered as a key step for many computer vision tasks. Although many approaches have reported promising results, this domain remains largely unsolved due to several challenges such as occlusions, small and barely visible joints, and variations in clothing and lighting. In the last few years, the power of deep neural networks has been demonstrated in a wide variety of computer vision problems and especially the HPE task. In this context, we present in this paper a Deep Full-Body-HPE (DFB-HPE) approach from RGB images only. Based on ConvNets, fifteen human joint positions are predicted and can be further exploited for a large range of applications such as gesture recognition, sports performance analysis, or human-robot interaction. To evaluate the proposed deep pose estimation model, we apply it to recognize the daily activities of a person in an unconstrained environment. Therefore, the extracted features, represented by deep estimated poses, are fed to an SVM classifier. To validate the proposed architecture, our approach is tested on two publicly available benchmarks for pose estimation and activity recognition, namely the J-HMDBand CAD-60datasets. The obtained results demonstrate the efficiency of the proposed method based on ConvNets and SVM and prove how deep pose estimation can improve the recognition accuracy. By means of comparison with state-of-the-art methods, we achieve the best HPE performance, as well as the best activity recognition precision on the CAD-60 dataset.

Gait-based person identification using 3D LiDAR and long short-term memory deep networks

Gait recognition is one measure of biometrics, which also includes facial, fingerprint, and retina recognition. Although most biometric methods require direct contact between a device and a subject, gait recognition has unique characteristics whereby interaction with the subjects is not required and can be performed from a distance. Cameras are commonly used for gait recognition, and a number of researchers have used depth information obtained using an RGB-D camera, such as the Microsoft Kinect. Although depth-based gait recognition has advantages, such as robustness against light conditions or appearance variations, there are also limitations. For instance, the RGB-D camera cannot be used outdoors and the measurement distance is limited to approximately 10 meters. The present paper describes a long short-term memory-based method for gait recognition using a real-time multi-line LiDAR. Very few studies have dealt with LiDAR-based gait recognition, and the present study is the first attempt that combines LiDAR data and long short-term memory for gait recognition and focuses on dealing with different appearances. We collect the first gait recognition dataset that consists of time-series range data for 30 people with clothing variations and show the effectiveness of the proposed approach.

A Machine Learning Method with Threshold Based Parallel Feature Fusion and Feature Selection for Automated Gait Recognition

Gait is a vital biometric process for human identification in the domain of machine learning. In this article, a new method is implemented for human gait recognition based on accurate segmentation and multi-level features extraction. Four major steps are performed including: a) enhancement of motion region in frame by the implementation of linear transformation with HSI color space; b) Region of Interest (ROI) detection based on parallel implementation of optical flow and background subtraction; c) shape and geometric features extraction and parallel fusion; d) Multi-class support vector machine (MSVM) utilization for recognition. The presented approach reduces error rate and increases the CCR. Extensive experiments are done on three data sets namely CASIA-A, CASIA-B and CASIA-C which present different variations in clothing and carrying conditions. The proposed method achieved maximum recognition results of 98.6% on CASIA-A, 93.5% on CASIA-B and 97.3% on CASIA-C, respectively.

Impact of Various Clothing Variations on Firefighter Mobility: A Pilot Study

Firefighter clothing is known to restrict movement and increase the risk of musculoskeletal injury. The aim of this study was to investigate differences between clothing variations and firefighter mobility. Data were collected from eight firefighters using a randomized counterbalanced, repeated measures, design. Three different clothing variants (V1–V3) in addition to current station wear (S) were trialed. Combinations of S and V1 (SV1) and V2 (SV2) were also trialed. Outcome measures included: standing reach height; the Functional Movement Screen [FMS]; vertical jump; a visual analogue scale [VAS] for the FMS, vertical jump, step ups and crawl; and a mannequin sketch to mark areas of discomfort. V3 was preferred over S in all tasks and performed better both objectively (FMS and vertical jump) and subjectively (VAS scores). While V1 was typically associated with poorer performance, the impacts of V1 and V2 when compared to each other and S varied depending on the tasks performed. This variation was greater when V1 or V2 were worn with S (SV1 and SV2). Areas of discomfort across all variations was the knees, followed by the thighs. Clothing that has the least impact on, or improves, mobility (especially around the lower limbs) may help reduce firefighter injury and limit subjective discomfort.

A model-based gait recognition method with body pose and human prior knowledge

We propose in this paper a novel model-based gait recognition method, PoseGait. Gait recognition is a challenging and attractive task in biometrics. Early approaches to gait recognition were mainly appearance-based. The appearance-based features are usually extracted from human body silhouettes, which are easy to compute and have shown to be efficient for recognition tasks. Nevertheless silhouettes shape is not invariant to changes in clothing, and can be subject to drastic variations, due to illumination changes or other external factors. An alternative to silhouette-based features are model-based features. However, they are very challenging to acquire especially for low image resolution. In contrast to previous approaches, our model PoseGait exploits human 3D pose estimated from images by Convolutional Neural Network as the input feature for gait recognition. The 3D pose, defined by the 3D coordinates of joints of the human body, is invariant to view changes and other external factors of variation. We design spatio-temporal features from the 3D pose to improve the recognition rate. Our method is evaluated on two large datasets, CASIA B and CASIA E. The experimental results show that the proposed method can achieve state-of-the-art performance and is robust to view and clothing variations.

Evaluation of gait recognition using dynamics of feature points and local shape features under clothing variation conditions

Evaluation of gait recognition using dynamics of feature points and local shape features under clothing variation conditions

Covariate Conscious Approach for Gait Recognition Based Upon Zernike Moment Invariants

Gait recognition, i.e., identification of an individual from his/her walking pattern is an emerging field. While existing gait recognition techniques perform satisfactorily in normal walking conditions, their performance tend to suffer drastically with variations in clothing and carrying conditions. In this paper, we propose a novel covariate cognizant framework to deal with the presence of such covariates. We describe gait motion by forming a single 2-D spatio-temporal template from video sequence, called average energy silhouette image (AESI). Zernike moment invariants are then computed to screen the parts of AESI infected with covariates. Following this, features are extracted from spatial distribution of oriented gradients and novel mean of directional pixels methods. The obtained features are fused together to form the final well-endowed feature set. Experimental evaluation of the proposed framework on three publicly available datasets, i.e., CASIA Dataset B, OU-ISIR Treadmill Dataset B, and USF Human-ID challenge dataset with recently published gait recognition approaches, prove its superior performance.

Retrieving real world clothing images via multi-weight deep convolutional neural networks

Clothing images are abundantly available from the Internet, especially from the e-commercial platform. Retrieving those images is of importance for commercial and social applications and has recently been received tremendous attention from communities, such as multimedia processing and computer vision. However, the large variations in clothing of their appearance and style, and even the large quantity of multiple categories and attributes make those problems challenging. Furthermore, for real world images their labels provided by shop retailers from webpages are largely erroneous or incomplete. And the imbalance among those image categories prevents the effective learning. To overcome those problems, in this paper, we adopt a multi-task deep learning framework to learn the representation. And we propose multi-weight deep convolutional neural networks for imbalance learning. The topology of this network contains two groups of layers, shared layers at the bottom and task dependent ones at the top. Furthermore, category-relevant parameters are incorporated to regularize the backward gradients for categories. Mathematical proof shows its relationship to regulating the learning rates. Experiments demonstrate that our proposed joint framework and multi-weight neural networks can effectively learn robust representations and achieve better performance.

Human gait recognition based on Haralick features

This paper proposes a supervised feature extraction approach that is capable of selecting distinctive features for the recognition of human gait under clothing and carrying conditions, thus improving the recognition performances. The principle of the suggested approach is based on the Haralick features extracted from gait energy image (GEI). These features are extracted locally by dividing vertically or horizontally the GEI locally into two or three equal regions of interest, respectively. RELIEF feature selection algorithm is then employed on the extracted features in order to select only the most relevant features with a minimum redundancy. The proposed method is evaluated on CASIA gait database (Dataset B) under variations of clothing and carrying conditions for different viewing angles, and the experimental results using k-NN classifier have yielded attractive results of up to 80% in terms of highest identification rate at rank-1 when compared to existing and similar state-of-the-art methods.

Part-based clothing image annotation by visual neighbor retrieval

With the advent and popularity of e-commerce and clothing image-sharing websites, clothing image search and annotation become active research topics in recent years. Clothing image annotation is a challenging task due to large variations in clothing appearance, human body pose and background. In this paper, we explore part-based clothing image annotation in a search and mining framework. Similar image search is first conducted to discover visual neighbors for a query image. The impact of large variations of clothing is alleviated by pose detection and part-based feature alignment. Tag relevance and tag saliency are taken into consideration to obtain the candidate tags. The relevance of candidate tags is identified by mining visual neighbors of a query image, while the saliency is determined according to the relationship between query image parts and part clusters on the whole training set. Experiments on a dataset with 1.1 million clothing images demonstrate the effectiveness and efficiency of the proposed approach.

Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis

This paper proposes an arbitrary view gait recognition method where the gait recognition is performed in 3-dimensional (3D) to be robust to variation in speed, inclined plane and clothing, and in the presence of a carried item. 3D parametric gait models in a gait period are reconstructed by an optimized 3D human pose, shape and simulated clothes estimation method using multi-view gait silhouettes. The gait estimation involves morphing a new subject with constant semantic constraints using silhouette cost function as observations. Using a clothes-independent 3D parametric gait model reconstruction method, gait models of different subjects with various postures in a cycle are obtained and used as galleries to construct 3D gait dictionary. Using a carrying-items posture synthesized model, virtual gait models with different carrying-items postures are synthesized to further construct an over-complete 3D gait dictionary. A self-occlusion optimized simultaneous sparse representation model is also introduced to achieve high robustness in limited gait frames. Experimental analyses on CASIA B dataset and CMU MoBo dataset show a significant performance gain in terms of accuracy and robustness.

Clothing and carrying condition invariant gait recognition based on rotation forest

This paper proposes a gait recognition method which is invariant to maximum number of challenging factors of gait recognition mainly unpredictable variation in clothing and carrying conditions. The method introduces an averaged gait key-phase image (AGKI) which is computed by averaging each of the five key-phases of the gait periods of a gait sequence. It analyses the AGKIs using high-pass and low-pass Gaussian filters, each at three cut-off frequencies to achieve robustness against unpredictable variation in clothing and carrying conditions in addition to other covariate factors, e.g., walking speed, segmentation noise, shadows under feet and change in hair style and ground surface. The optimal cut-off frequencies of the Gaussian filters are determined based on an analysis of the focus values of filtered human subject’s silhouettes. The method applies rotation forest ensemble learning recognition to enhance both individual accuracy and diversity within the ensemble for improved identification rate. Extensive experiments on public datasets demonstrate the efficacy of the proposed method.