Visual recognition of gymnastic exercise sequences. Application to supervision and robot learning by demonstration

Domingo, Jaime Duque; Gómez-García-Bermejo, Jaime; Zalama, Eduardo

doi:10.1016/j.robot.2021.103830

Cited by 8 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OpenPose can directly identify the position of human bones (Kim et al, 2021;Xu et al, 2020), actions (Domingo et al, 2021;Nose et al, 2019;Vasconez et al, 2021), hand gestures (Mazhar et al, 2019), etc. Therefore, this research is OpenPose-based HAR, which is applied to the clothing fitting of the DCU.…”

Section: Computer Vision For Recommended Uniformsmentioning

confidence: 99%

“…It uses optical equipment to capture information on human activity and is applied in the related research of HAR. For example, after capturing images through cameras, mobile phones, webcams, OpenPose can directly identify the position of human bones (Kim et al , 2021; Xu et al , 2020), actions (Domingo et al , 2021; Nose et al , 2019; Vasconez et al , 2021), hand gestures (Mazhar et al , 2019), etc. Therefore, this research is OpenPose-based HAR, which is applied to the clothing fitting of the DCU.…”

Section: Related Workmentioning

confidence: 99%

“…OpenPose in artificial intelligence does not require background settings or pre-labeling. Instead, after capturing images through cameras, mobile phones, webcams, etc., it can directly identify the position of human bones (Kim et al , 2021; Xu et al , 2020), actions (Domingo et al , 2021; Nose et al , 2019; Vasconez et al , 2021) and hand gestures (Mazhar et al , 2019). Related research also compares OpenPose with other sophisticated measurement equipment (Clark et al , 2019; Kim et al , 2021; Ota et al , 2020, 2021), in which, the results show that OpenPose's 2D analysis can provide valid values for humans with frontal and non-moving postures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence technologies for more flexible recommendation in uniforms

Wen

Cheng

Shih

2022

DTA

View full text Add to dashboard Cite

PurposeThis research aims to collect human body variables via 2D images captured by digital cameras. Based on those human variables, the forecast and recommendation of the Digital Camouflage Uniforms (DCU) for Taiwan's military personnel are made.Design/methodology/approachA total of 375 subjects are recruited (male: 253; female: 122). In this study, OpenPose converts the photographed 2D images into four body variables, which are compared with those of a tape measure and 3D scanning simultaneously. Then, the recommendation model of the DCU is built by the decision tree. Meanwhile, the Euclidean distance of each size of the DCU in the manufacturing specification is calculated as the best three recommendations.FindingsThe recommended size established by the decision tree is only 0.62 and 0.63. However, for the recommendation result of the best three options, the DCU Fitting Score can be as high as 0.8 or more. The results of OpenPose and 3D scanning have the highest correlation coefficient even though the method of measuring body size is different. This result confirms that OpenPose has significant measurement validity. That is, inexpensive equipment can be used to obtain reasonable results.Originality/valueIn general, the method proposed in this study is suitable for applications in e-commerce and the apparel industry in a long-distance, non-contact and non-pre-labeled manner when the world is facing Covid-19. In particular, it can reduce the measurement troubles of ordinary users when purchasing clothing online.

show abstract

Section: Computer Vision For Recommended Uniformsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence technologies for more flexible recommendation in uniforms

Wen

Cheng

Shih

2022

DTA

View full text Add to dashboard Cite

show abstract

“…Another example could be the skeleton tracking integrated with the Multilayer Perceptron (MLP) and HMM used in the work developed by Domingo, J.D. et al [ 38 ], in which the authors manage to recognise exercises performed during gymnastics sessions. Their system is able to recognise a total of 19 postures through computer vision by means of frame analysis, reaching a recognition success rate of 98.05% in the best of situations.…”

Section: Related Workmentioning

confidence: 99%

SDHAR-HOME: A Sensor Dataset for Human Activity Recognition at Home

Ramos

Domingo

Zalama

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Nowadays, one of the most important objectives in health research is the improvement of the living conditions and well-being of the elderly, especially those who live alone. These people may experience undesired or dangerous situations in their daily life at home due to physical, sensorial or cognitive limitations, such as forgetting their medication or wrong eating habits. This work focuses on the development of a database in a home, through non-intrusive technology, where several users are residing by combining: a set of non-intrusive sensors which captures events that occur in the house, a positioning system through triangulation using beacons and a system for monitoring the user’s state through activity wristbands. Two months of uninterrupted measurements were obtained on the daily habits of 2 people who live with a pet and receive sporadic visits, in which 18 different types of activities were labelled. In order to validate the data, a system for the real-time recognition of the activities carried out by these residents was developed using different current Deep Learning (DL) techniques based on neural networks, such as Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM) or Gated Recurrent Unit networks (GRU). A personalised prediction model was developed for each user, resulting in hit rates ranging from 88.29% to 90.91%. Finally, a data sharing algorithm has been developed to improve the generalisability of the model and to avoid overtraining the neural network.

show abstract

“…The choice of the hidden neurons and the number of hidden layers was made by a batch grid search, testing different configurations and keeping the best one. A value of hidden neurons was initially calculated following some rule of thumb, such as 2/3 size of input and output layer [38], or some used in previous works [39] that also related to the number of samples. However, taking as input 78,858 elements of the LOMO vector and as output four as the number of elements to be compared, the hidden neurons represented a value too high that caused our model to fail to load into the memory of our GPUs.…”

Section: Siamese Neural Networkmentioning

confidence: 99%

Improvement of One-Shot-Learning by Integrating a Convolutional Neural Network and an Image Descriptor into a Siamese Neural Network

2021

Self Cite

View full text Add to dashboard Cite

Over the last few years, several techniques have been developed with the aim of implementing one-shot learning, a concept that allows classifying images with only a single image per training category. Conceptually, these methods seek to reproduce certain behavior that humans have. People are able to recognize a person they have only seen once, but they are probably not able to do the same with certain animals, such as a monkey. This is because our brains have been trained for years with images of people but not so much of animals. Among the one-shot learning techniques, some of them have used data generation, such as Generative Adversarial Networks (GAN). Other techniques have been based on the matching of descriptors traditionally used for object detection. Finally, one of the most prominent techniques involves using Siamese neural networks. Siamese networks are usually implemented with two convolutional nets that share their weights. They receive two images as input and can detect whether they belong to the same category or not. In the field of grocery products, there has been a lot of research on the one-shot learning problem but not so much on the use of Siamese networks. In this paper, several classifiers are firstly evaluated to decide on a convolutional model to be used with the Siamese and to improve the baseline results obtained in the dataset used. Then, two existing techniques are integrated within the Siamese model: a convolutional net and a Local Maximal Occurrence (LOMO) descriptor. The latter was initially used for the re-identification of people although it has shown its effectiveness to improve the values of a traditional Siamese with only convolutional sisters. The whole network is trained on categories and responds to different categories, showing its strong capacity to deal with the problem of having only one image per category.

show abstract

Visual recognition of gymnastic exercise sequences. Application to supervision and robot learning by demonstration

Cited by 8 publications

References 37 publications

Artificial intelligence technologies for more flexible recommendation in uniforms

Artificial intelligence technologies for more flexible recommendation in uniforms

SDHAR-HOME: A Sensor Dataset for Human Activity Recognition at Home

Improvement of One-Shot-Learning by Integrating a Convolutional Neural Network and an Image Descriptor into a Siamese Neural Network

Contact Info

Product

Resources

About