Development, evaluation and application of a novel markerless motion analysis system to understand push-start technique in elite skeleton athletes.

This study describes the development, evaluation and application of a computer vision and deep learning system capable of capturing sprinting and skeleton push start step characteristics and mass centre velocities (sled and athlete). Movement data were captured concurrently by a marker-based motion capture system and a custom markerless system. High levels of agreement were found between systems, particularly for spatial based variables (step length error 0.001 ± 0.012 m) while errors for temporal variables (ground contact time and flight time) were on average within ± 1.5 frames of the criterion measures. Comparisons of sprinting and pushing revealed decreased mass centre velocities as a result of pushing the sled but step characteristics were comparable to sprinting when aligned as a function of step velocity. There were large asymmetries between the inside and outside leg during pushing (e.g. 0.22 m mean step length asymmetry) which were not present during sprinting (0.01 m step length asymmetry). The observed asymmetries suggested that force production capabilities during ground contact were compromised for the outside leg. The computer vision based methods tested in this research provide a viable alternative to marker-based motion capture systems. Furthermore, they can be deployed into challenging, real world environments to non-invasively capture data where traditional approaches are infeasible.

Skeleton interoception regulates bone and fat metabolism through hypothalamic neuroendocrine NPY.

The central nervous system regulates activity of peripheral organs through interoception. In our previous study, we have demonstrated that PGE2/EP4 skeleton interception regulate bone homeostasis. Here, we show that ascending skeleton interoceptive signaling downregulates expression of hypothalamic neuropeptide Y (NPY) and induce lipolysis of adipose tissue for osteoblastic bone formation. Specifically, the ascending skeleton interoceptive signaling induces expression of small heterodimer partner-interacting leucine zipper protein (SMILE) in the hypothalamus. SMILE binds to pCREB as a transcriptional heterodimer on Npy promoters to inhibit NPY expression. Knockout of EP4 in sensory nerve increases expression of NPY causing bone catabolism and fat anabolism. Importantly, inhibition of NPY Y1 receptor (Y1R) accelerated oxidation of free fatty acids in osteoblasts and rescued bone loss in AvilCre:Ptger4fl/fl mice. Thus, downregulation of hypothalamic NPY expression lipolyzes free fatty acids for anabolic bone formation through a neuroendocrine descending interoceptive regulation.

Long lasting effects of early temperature exposure on the swimming performance and skeleton development of metamorphosing Gilthead seabream (Sparus aurata L.) larvae.

Temperatures experienced during early ontogeny significantly influence fish phenotypes, with clear consequences for the wild and reared stocks. We examined the effect of temperature (17, 20, or 23 °C) during the short embryonic and yolk-sac larval period, on the swimming performance and skeleton of metamorphosing Gilthead seabream larvae. In the following ontogenetic period, all fish were subjected to common temperature (20 °C). The critical swimming speed of metamorphosing larvae was significantly decreased from 9.7 ± 0.6 TL/s (total length per second) at 17 °C developmental temperature (DT) to 8.7 ± 0.6 and 8.8 ± 0.7 TL/s at 20 and 23 °C DT respectively (p < 0.05). Swimming performance was significantly correlated with fish body shape (p < 0.05). Compared with the rest groups, fish of 17 °C DT presented a slender body shape, longer caudal peduncle, terminal mouth and ventrally transposed pectoral fins. Moreover, DT significantly affected the relative depth of heart ventricle (VD/TL, p < 0.05), which was comparatively increased at 17 °C DT. Finally, the incidence of caudal-fin abnormalities significantly decreased (p < 0.05) with the increase of DT. To our knowledge, this is the first evidence for the significant effect of DT during the short embryonic and yolk-sac larval period on the swimming performance of the later stages.

Hypergraph Neural Network for Skeleton-Based Action Recognition.

Recently, skeleton-based human action recognition has attracted a lot of research attention in the field of computer vision. Graph convolutional networks (GCNs), which model the human body skeletons as spatial-temporal graphs, have shown excellent results. However, the existing methods only focus on the local physical connection between the joints, and ignore the non-physical dependencies among joints. To address this issue, we propose a hypergraph neural network (Hyper-GNN) to capture both spatial-temporal information and high-order dependencies for skeleton-based action recognition. In particular, to overcome the influence of noise caused by unrelated joints, we design the Hyper-GNN to extract the local and global structure information via the hyperedge (i.e., non-physical connection) constructions. In addition, the hypergraph attention mechanism and improved residual module are induced to further obtain the discriminative feature representations. Finally, a three-stream Hyper-GNN fusion architecture is adopted in the whole framework for action recognition. The experimental results performed on two benchmark datasets demonstrate that our proposed method can achieve the best performance when compared with the state-of-the-art skeleton-based methods.

Craniofacial and Long Bone Development in the Context of Distraction Osteogenesis.

BACKGROUND: Bone retains regenerative potential into adulthood, and surgeons harness this plasticity during distraction osteogenesis. The underlying biology governing bone development, repair, and regeneration is divergent between the craniofacial and appendicular skeleton. Each type of bone formation is characterized by unique molecular signaling and cellular behavior. Recent discoveries have elucidated the cellular and genetic processes underlying skeletal development and regeneration, providing an opportunity to couple biological and clinical knowledge to improve patient care. METHODS: A comprehensive literature review of basic and clinical literature regarding craniofacial and long bone development, regeneration, and distraction osteogenesis was performed. RESULTS: The current understanding in craniofacial and long bone development and regeneration is discussed, and clinical considerations for the respective distraction osteogenesis procedures are presented. CONCLUSIONS: Distraction osteogenesis is a powerful tool to regenerate bone and thus address a number of craniofacial and appendicular skeletal deficiencies. The molecular mechanisms underlying bone regeneration, however, remain elusive. Recent work has determined that embryologic morphogen gradients constitute important signals during regeneration. In addition, striking discoveries have illuminated the cellular processes underlying mandibular regeneration during distraction osteogenesis, showing that skeletal stem cells reactivate embryologic neural crest transcriptomic processes to carry out bone formation during regeneration. Furthermore, innovative adjuvant therapies to complement distraction osteogenesis use biological processes active in embryogenesis and regeneration. Additional research is needed to further characterize the underlying cellular mechanisms responsible for improved bone formation through adjuvant therapies and the role skeletal stem cells play during regeneration.

Early evidence for mounted horseback riding in northwest China.

Horseback riding was a transformative force in the ancient world, prompting radical shifts in human mobility, warfare, trade, and interaction. In China, domestic horses laid the foundation for trade, communication, and state infrastructure along the ancient Silk Road, while also stimulating key military, social, and political changes in Chinese society. Nonetheless, the emergence and adoption of mounted horseback riding in China is still poorly understood, particularly due to a lack of direct archaeological data. Here we present a detailed osteological study of eight horse skeletons dated to ca. 350 BCE from the sites of Shirenzigou and Xigou in Xinjiang, northwest China, prior to the formalization of Silk Road trade across this key region. Our analyses reveal characteristic osteological changes associated with equestrian practices on all specimens. Alongside other relevant archaeological evidence, these data provide direct evidence for mounted horseback riding, horse equipment, and mounted archery in northwest China by the late first millennium BCE. Most importantly, our results suggest that this region may have played a crucial role in the spread of equestrian technologies from the Eurasian interior to the settled civilizations of early China, where horses facilitated the rise of the first united Chinese empires and the emergence of transcontinental trade networks.

Skeletal Phenotypes Due to Abnormalities in Mitochondrial Protein Homeostasis and Import.

Mitochondrial disease represents a collection of rare genetic disorders caused by mitochondrial dysfunction. These disorders can be quite complex and heterogeneous, and it is recognized that mitochondrial disease can affect any tissue at any age. The reasons for this variability are not well understood. In this review, we develop and expand a subset of mitochondrial diseases including predominantly skeletal phenotypes. Understanding how impairment ofdiverse mitochondrial functions leads to a skeletal phenotype will help diagnose and treat patients with mitochondrial disease and provide additional insight into the growing list of human pathologies associated with mitochondrial dysfunction. The underlying disease genes encode factors involved in various aspects of mitochondrial protein homeostasis, including proteases and chaperones, mitochondrial protein import machinery, mediators of inner mitochondrial membrane lipid homeostasis, and aminoacylation of mitochondrial tRNAs required for translation. We further discuss a complex of frequently associated phenotypes (short stature, cataracts, and cardiomyopathy) potentially explained by alterations to steroidogenesis, a process regulated by mitochondria. Together, these observations provide novel insight into the consequences of impaired mitochondrial protein homeostasis.

Enhanced Spatial and Extended Temporal Graph Convolutional Network for Skeleton-Based Action Recognition.

In the skeleton-based human action recognition domain, the spatial-temporal graph convolution networks (ST-GCNs) have made great progress recently. However, they use only one fixed temporal convolution kernel, which is not enough to extract the temporal cues comprehensively. Moreover, simply connecting the spatial graph convolution layer (GCL) and the temporal GCL in series is not the optimal solution. To this end, we propose a novel enhanced spatial and extended temporal graph convolutional network (EE-GCN) in this paper. Three convolution kernels with different sizes are chosen to extract the discriminative temporal features from shorter to longer terms. The corresponding GCLs are then concatenated by a powerful yet efficient one-shot aggregation (OSA) + effective squeeze-excitation (eSE) structure. The OSA module aggregates the features from each layer once to the output, and the eSE module explores the interdependency between the channels of the output. Besides, we propose a new connection paradigm to enhance the spatial features, which expand the serial connection to a combination of serial and parallel connections by adding a spatial GCL in parallel with the temporal GCLs. The proposed method is evaluated on three large scale datasets, and the experimental results show that the performance of our method exceeds previous state-of-the-art methods.

GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition.

Skeleton-based action recognition has achieved great advances with the development of graph convolutional networks (GCNs). Many existing GCNs-based models only use the fixed hand-crafted adjacency matrix to describe the connections between human body joints. This omits the important implicit connections between joints, which contain discriminative information for different actions. In this paper, we propose an action-specific graph convolutional module, which is able to extract the implicit connections and properly balance them for each action. In addition, to filter out the useless and redundant information in the temporal dimension, we propose a simple yet effective operation named gated temporal convolution. These two major novelties ensure the superiority of our proposed method, as demonstrated on three large-scale public datasets: NTU-RGB + D, Kinetics, and NTU-RGB + D 120, and also shown in the detailed ablation studies.

Real-Time Human Action Recognition with a Low-Cost RGB Camera and Mobile Robot Platform.

Human action recognition is an important research area in the field of computer vision that can be applied in surveillance, assisted living, and robotic systems interacting with people. Although various approaches have been widely used, recent studies have mainly focused on deep-learning networks using Kinect camera that can easily generate data on skeleton joints using depth data, and have achieved satisfactory performances. However, their models are deep and complex to achieve a higher recognition score; therefore, they cannot be applied to a mobile robot platform using a Kinect camera. To overcome these limitations, we suggest a method to classify human actions in real-time using a single RGB camera, which can be applied to the mobile robot platform as well. We integrated two open-source libraries, i.e., OpenPose and 3D-baseline, to extract skeleton joints on RGB images, and classified the actions using convolutional neural networks. Finally, we set up the mobile robot platform including an NVIDIA JETSON XAVIER embedded board and tracking algorithm to monitor a person continuously. We achieved an accuracy of 70% on the NTU-RGBD training dataset, and the whole process was performed on an average of 15 frames per second (FPS) on an embedded board system.

A Game-Based Rehabilitation System for Upper-Limb Cerebral Palsy: A Feasibility Study.

Game-based rehabilitation systems provide an effective tool to engage cerebral palsy patients in physical exercises within an exciting and entertaining environment. A crucial factor to ensure the effectiveness of game-based rehabilitation systems is to assess the correctness of the movements performed by the patient during the game-playing sessions. In this study, we propose a game-based rehabilitation system for upper-limb cerebral palsy that includes three game-based exercises and a computerized assessment method. The game-based exercises aim to engage the participant in shoulder flexion, shoulder horizontal abduction/adduction, and shoulder adduction physical exercises that target the right arm. Human interaction with the game-based rehabilitation system is achieved using a Kinect sensor that tracks the skeleton joints of the participant. The computerized assessment method aims to assess the correctness of the right arm movements during each game-playing session by analyzing the tracking data acquired by the Kinect sensor. To evaluate the performance of the computerized assessment method, two groups of participants volunteered to participate in the game-based exercises. The first group included six cerebral palsy children and the second group included twenty typically developing subjects. For every participant, the computerized assessment method was employed to assess the correctness of the right arm movements in each game-playing session and these computer-based assessments were compared with matching gold standard evaluations provided by an experienced physiotherapist. The results reported in this study suggest the feasibility of employing the computerized assessment method to evaluate the correctness of the right arm movements during the game-playing sessions.

The structural origins of brittle star arm kinematics: An integrated tomographic, additive manufacturing, and parametric modeling-based approach.

Brittle stars are known for the high flexibility of their arms, a characteristic required for locomotion, food grasping, and for holding onto a great diversity of substrates. Their high agility is facilitated by the numerous discrete skeletal elements (ossicles) running through the center of each arm and embedded in the skin. While much has been learned regarding the structural diversity of these ossicles, which are important characters for taxonomic purposes, their impact on the arms' range of motion, by contrast, is poorly understood. In the present study, we set out to investigate how ossicle morphology and skeletal organization affect the flexibility of brittle star arms. Here, we present the results of an in-depth analysis of three brittle star species (Ophioplocus esmarki, Ophiopteris papillosa, and Ophiothrix spiculata), chosen for their different ranges of motion, as well as spine size and orientation. Using an integrated approach that combines behavioral studies with parametric modeling, additive manufacturing, micro-computed tomography, scanning electron microscopy, and finite element simulations, we present a high-throughput workflow that provides a fundamental understanding of 3D structure-kinematic relationships in brittle star skeletal systems.

External skeletal robustness and adiposity in adolescents of low socioeconomic status: A cross-sectional analysis of body composition.

OBJECTIVES: External skeletal robustness has been decreasing in children, potentially due to a lack of physical activity and the increased prevalence of obesity. However, whether socioeconomic status (SES) influences external skeletal robustness in adolescents has not yet been examined. METHODS: A cross-sectional study was performed to examine 370 Chilean adolescents (16.15 ± 1.01 years old) recruited from distinct educational establishments. Body fat percentage (BF%) was evaluated using Ellis' equations for Hispanic children. Obesity was defined as ≥25 BF% in males and ≥ 30 BF% in females. External skeletal robustness was obtained by measuring the humerus biepicondylar width and height (Frame-Index). SES was obtained through the ESOMAR survey. RESULTS: Females exhibited significantly greater BF% and lower Frame-Index values than males (P < .001). Obese adolescents (by BF%) had greater Frame-Index values than non-obese adolescents (P < .001). Females of medium-high SES had significantly lower BF% and Frame-Index values than females of medium and medium-low SES. BF% had a positive correlation with Frame-Index values in all SES groups studied, except in males of medium-high SES. As SES decreased, the correlation increased in both sexes, but overall, the correlation was greater in females than males. CONCLUSIONS: The results of this investigation suggest that obesity increases external skeletal robustness in adolescents. Additionally, lower SES corresponded to higher BF% and Frame-Index values. Therefore, modern conditions that influence the prevalence of obesity in adolescence could be affecting bone health in adolescents, primarily in females of medium-low SES.

Radiographic assessment of pectoral flipper bone maturation in bottlenose dolphins (Tursiops truncatus), as a novel technique to accurately estimate chronological age.

Accurate age estimation in wildlife conservation is an important diagnostic tool in the interpretation of biological data, necropsy examination, reproductive status and population demographics. The most frequently utilized methods to age bottlenose dolphins (Tursiops truncatus) include tooth extraction; counting dental growth layer groups and dental radiography. These methods are inaccurate in dolphins > 13 years old, due to overlapping of the growth layer groups in dolphins and worn teeth. Establishing a non-invasive method of accurately aging bottlenose dolphins across the entire age range is important to long term conservation efforts to understand health status, lifespan, reproduction and survivability. A database of 126 radiographs from 94 dolphins of known chronological age was utilized to establish the stages of skeletal ossification over time. A numerical score from -1 to 8 was assigned to 16 anatomic locations on the pectoral radiograph, to create a formula to estimate age. The most informative areas to evaluate morphologically were the metaphyseal regions of the radius and ulna, and the proximal and distal epiphysis of metacarpals II and III. Third order polynomial regression calculated separate age predictor formulas for male and female dolphins, with females reaching sexual maturity earlier than males. Completion of epiphyseal closure of the long bones correlated with average sexual maturity. Managed care dolphin ages could be properly estimated with decreasing precision from within 3 months in animals < 5 years old, to within 5 years in animals > 30 years old. This diagnostic tool could also be applied to diagnose atypical ossification patterns consistent with nutritional, developmental or growth abnormalities, and identifying subclinical health issues. In conclusion, knowledge of the lifespan and the onset of sexual maturity for each species will allow this model to be applied to other cetaceans, facilitating age estimation via pectoral radiography in future research.

The structure, composition and mechanical properties of the skeleton of the naked mole-rat (Heterocephalus glaber).

The naked mole-rat (NMR) is a small rodent with a remarkable array of properties, such as unique physiology, extremely long life-span and unusual social life. However, very little is known regarding its skeleton. The aim of this study was to describe the structure, composition and mechanical properties in an ontogenetic series of naked mole-rat bones. Since common small rodents like mice and rats have an unusual structure of cortical bone, which includes a central region of non-lamellar (disordered) bone, mineralized cartilaginous islands and total lack of remodeling, this study could also determine if these are features of all small rodents. Sixty-one NMRs were included in the study and were divided into the following four age groups: 0-0.5 years old (n = 17), 0.5-3 years old (n = 25), 3-10 years old (n = 13), and >10 years (n = 6). Femora, vertebrae and mandibulae were examined using micro-CT, light microscopy, polarized light microscopy and scanning electron microscopy, thermogravimetric analysis was used to determine their dry ash content and their derived elastic modulus and hardness were determined using micro-indentation. Our findings show that NMR bones are similar in composition and mechanical properties to those of other small rodents. However, in contrast to other small rodents, the cortical bone of NMRs is entirely circumferential-lamellar and lacks mineralized cartilage islands. Furthermore, despite their long life-span, their bones did not show evidence of remodeling at any of the age groups, thus proving that lack of cortical remodeling in small rodents is not caused by their short life-span, but characteristic of this order of mammals.

Rol de la osteocalcina más allá del hueso / Role of osteocalcin beyond bone

Los hallazgos osteológicos se intensi!caron en los últimos años. Se demostró que el esqueleto se comporta, además de sus funciones clásicas, como un órgano de secreción endocrina que sintetiza al menos dos hormonas: el factor de crecimiento de !broblastos 23 (FGF-23) y la osteocalcina (Ocn). La Ocn es un péptido pequeño que contiene 3 residuos de ácido glutámico. Estos residuos se carboxilan postraduccionalmente, quedando retenida en la matriz ósea. La forma decarboxilada en el primer residuo de ácido glutámico (GluOcn) fue reportada por poseer efectos biológicos; la resorción ósea es el mecanismo clave para su bioactivación. La presente revisión se centra en los conocimientos actuales sobre la función hormonal de la Ocn. A la fecha se reporta que la Ocn regularía el metabolismo energético aumentando la proliferación de células ` pancreáticas, y la secreción de insulina y de adiponectina. Sobre el músculo esquelético actuaría favoreciendo la absorción y el catabolismo de nutrientes. La función reproductiva masculina estaría regulada mediante el estímulo a las células de Leydig para sintetizar testosterona; en el desarrollo cerebral y la cognición, la Ocn aumentaría la síntesis de neurotransmisores monoaminados y disminuiría el neurotransmisor inhibidor GABA. Si bien son indispensables mayores evidencias para dilucidar los mecanismos reguladores por medio de los cuales actuaría la Ocn, los resultados enumerados en los distintos estudios experimentales establecen la importancia de este novedoso integrante molecular. Dilucidar su rol dentro de estos procesos interrelacionados en seres humanos abriría la posibilidad de utilizar a la Ocn en el tratamiento de enfermedades endocrino-metabólicas. (AU)

Osteological !ndings have intensi!ed in recent years. The skeleton behaves as an endocrine secretion organ that synthesizes at least two hormones: osteocalcin (Ocn) and !broblast growth factor 23 (FGF-23). Ocn is a small peptide that contains 3 glutamic acid residues. After translation, these residues are carboxylated to make possible its retention into the bone matrix. Decarboxylation on the !rst glutamic acid residue (GluOcn) has been reported to have biological effects. Bone resorption is the key mechanism for its bioactivation. This review focuses on current knowledge on Ocn hormonal function. It has been reported that Ocn regulates energy metabolism by increasing the proliferation of pancreatic ` cells, and the secretion of insulin and adiponectin. On the skeletal muscle, it may act by favoring the absorption and catabolism of nutrients. Male reproductive function might be regulated by stimulating Leydig cells to synthesize testosterone. Regarding brain development and cognition, Ocn would increase monoamine neurotransmitters synthesis and decrease inhibitory neurotransmitter GABA. Although more evidence is needed to elucidate the regulatory mechanisms of Ocn, different experimental studies establish the importance of this novel molecular mediator. Clarifying its role within interrelated processes in humans, might open the possibility of using Ocn in different treatments of endocrine-metabolic diseases. (AU)

Using Step Size and Lower Limb Segment Orientation from Multiple Low-Cost Wearable Inertial/Magnetic Sensors for Pedestrian Navigation.

This paper demonstrates the use of multiple low-cost inertial/magnetic sensors as a pedestrian navigation system for indoor positioning. This research looks at the problem of pedestrian navigation in a practical manner by investigating dead-reckoning methods using low-cost sensors. This work uses the estimated sensor orientation angles to compute the step size from the kinematics of a skeletal model. The orientations of limbs are represented by the tilt angles estimated from the inertial measurements, especially the pitch angle. In addition, different step size estimation methods are compared. A sensor data logging system is developed in order to record all motion data from every limb segment using a single platform and similar types of sensors. A skeletal model of five segments is chosen to model the forward kinematics of the lower limbs. A treadmill walk experiment with an optical motion capture system is conducted for algorithm evaluation. The mean error of the estimated orientation angles of the limbs is less than 6 degrees. The results show that the step length mean error is 3.2 cm, the left stride length mean error is 12.5 cm, and the right stride length mean error is 9 cm. The expected positioning error is less than 5% of the total distance travelled.

GWAS for Meat and Carcass Traits Using Imputed Sequence Level Genotypes in Pooled F2-Designs in Pigs.

In order to gain insight into the genetic architecture of economically important traits in pigs and to derive suitable genetic markers to improve these traits in breeding programs, many studies have been conducted to map quantitative trait loci. Shortcomings of these studies were low mapping resolution, large confidence intervals for quantitative trait loci-positions and large linkage disequilibrium blocks. Here, we overcome these shortcomings by pooling four large F2 designs to produce smaller linkage disequilibrium blocks and by resequencing the founder generation at high coverage and the F1 generation at low coverage for subsequent imputation of the F2 generation to whole genome sequencing marker density. This lead to the discovery of more than 32 million variants, 8 million of which have not been previously reported. The pooling of the four F2 designs enabled us to perform a joint genome-wide association study, which lead to the identification of numerous significantly associated variant clusters on chromosomes 1, 2, 4, 7, 17 and 18 for the growth and carcass traits average daily gain, back fat thickness, meat fat ratio, and carcass length. We could not only confirm previously reported, but also discovered new quantitative trait loci. As a result, several new candidate genes are discussed, among them BMP2 (bone morphogenetic protein 2), which we recently discovered in a related study. Variant effect prediction revealed that 15 high impact variants for the traits back fat thickness, meat fat ratio and carcass length were among the statistically significantly associated variants.

Ultraviolet light illuminates the avian nature of the Berlin Archaeopteryx skeleton.

The question of whether the iconic avialan Archaeopteryx was capable of active flapping flight or only passive gliding is still unresolved. This study contributes to this debate by reporting on two key aspects of this fossil that are visible under ultraviolet (UV) light. In contrast to previous studies, we show that most of the vertebral column of the Berlin Archaeopteryx possesses intraosseous pneumaticity, and that pneumatic structures also extend beyond the anterior thoracic vertebrae in other specimens of Archaeopteryx. With a minimum Pneumaticity Index (PI) of 0.39, Archaeopteryx had a much more lightweight skeleton than has been previously reported, comprising an air sac-driven respiratory system with the potential for a bird-like, high-performance metabolism. The neural spines of the 16th to 22nd presacral vertebrae in the Berlin Archaeopteryx are bridged by interspinal ossifications, and form a rigid notarium-like structure similar to the condition seen in modern birds. This reinforced vertebral column, combined with the extensive development of air sacs, suggests that Archaeopteryx was capable of flapping its wings for cursorial and/or aerial locomotion.

A Comprehensive Survey of Vision-Based Human Action Recognition Methods.

Although widely used in many applications, accurate and efficient human action recognition remains a challenging area of research in the field of computer vision. Most recent surveys have focused on narrow problems such as human action recognition methods using depth data, 3D-skeleton data, still image data, spatiotemporal interest point-based methods, and human walking motion recognition. However, there has been no systematic survey of human action recognition. To this end, we present a thorough review of human action recognition methods and provide a comprehensive overview of recent approaches in human action recognition research, including progress in hand-designed action features in RGB and depth data, current deep learning-based action feature representation methods, advances in human⁻object interaction recognition methods, and the current prominent research topic of action detection methods. Finally, we present several analysis recommendations for researchers. This survey paper provides an essential reference for those interested in further research on human action recognition.