ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications

Hwang, Hochul; Jang, Cheongjae; Park, Geonwoo; Cho, Junghyun; Kim, Ig-Jae

doi:10.48550/arxiv.2010.14742

Cited by 5 publications

(4 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies did not conduct testing on widely used public datasets but instead utilized self-built, non-public datasets, which poses challenges in terms of reproducibility. For example, the authors in [56] merged AI Hub dataset collected by Korean government and the Kist SynADL [154] datasets to train/test their systems. Similarly, [43], [128] chose to use their own dataset to evaluate their methods.…”

Section: ) Issue Of Different Evaluation Settingsmentioning

confidence: 99%

Advances in Skeleton-Based Fall Detection in RGB Videos: From Handcrafted to Deep Learning Approaches

Hoang,

Lee,

Piran

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In the elderly population, falls are one of the leading causes of fatal and non-fatal injuries. Fall detection and early alarms play an important role in mitigating the negative effects of falls, especially given the growing proportion of the elderly population. Due to their non-intrusive nature, data availability, and low deployment costs, RGB videos have been used in many previous studies to detect falls. The RGB data, however, can be affected by background environment changes, resulting in non-recognition. To overcome these challenges, many researchers propose extracting skeleton data from RGB videos and using it for fall detection. Although there have been multiple surveys on fall detection, most of them focus on assessing fall detection systems using different kinds of sensors, and a comprehensive evaluation of skeleton-based fall detection in RGB videos is lacking. In this paper, we examine the most recent advances in skeleton-based fall detection in RGB videos, from handcrafted feature-based methods to advanced deep learning algorithms. Further, we present several skeleton-based fall detection techniques and their performance results on various benchmark datasets, along with challenges and future directions in this field.

show abstract

Section: ) Issue Of Different Evaluation Settingsmentioning

confidence: 99%

Advances in Skeleton-Based Fall Detection in RGB Videos: From Handcrafted to Deep Learning Approaches

Hoang,

Lee,

Piran

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…ElderSim, a synthetic data generation platform for human action recognition was implemented by Hwang et al [49]. The authors used Autodesk Maya and Unreal Engine to model and simulate virtual scenes for eldercare applications.…”

Section: Simulationmentioning

confidence: 99%

“…Several simulator tools able to generate synthetic images for object detection dataset augmentation (e.g., the Unreal Engine 4 plugin "NVIDIA Deep learning Dataset Synthesizer (NDDS)" [66]) already exists, but their randomisation routines do not usually take into consideration time dependency for the creation of simulated video sequences. Some of the reviewed papers are starting to move in that direction (e.g., ElderSim, a synthetic data generation platform for human action recognition [49]).…”

Section: From Static Image To Video Data Augmentationmentioning

confidence: 99%

Survey on Videos Data Augmentation for Deep Learning Models

Cauli

Recupero

2022

Future Internet

View full text Add to dashboard Cite

In most Computer Vision applications, Deep Learning models achieve state-of-the-art performances. One drawback of Deep Learning is the large amount of data needed to train the models. Unfortunately, in many applications, data are difficult or expensive to collect. Data augmentation can alleviate the problem, generating new data from a smaller initial dataset. Geometric and color space image augmentation methods can increase accuracy of Deep Learning models but are often not enough. More advanced solutions are Domain Randomization methods or the use of simulation to artificially generate the missing data. Data augmentation algorithms are usually specifically designed for single images. Most recently, Deep Learning models have been applied to the analysis of video sequences. The aim of this paper is to perform an exhaustive study of the novel techniques of video data augmentation for Deep Learning models and to point out the future directions of the research on this topic.

show abstract

“…The use of synthetic data is very appealing in other areas as well, such as for deep reinforcement learning [30]. Multiple synthetic datasets [28,19,40] or engines [15,11,10] to generate them are now available for AI research. Until recently the domain gap between the synthetic dataset and the real one usually made synthetic-only training non-competitive, but with today's rendering programs the generalization error is becoming comparable to that between two similar real-life datasets [25].…”

Section: Introductionmentioning

confidence: 99%

Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery

Jareño

Helden

Mirkes

et al. 2021

Entropy

View full text Add to dashboard Cite

In this article, we consider a version of the challenging problem of learning from datasets whose size is too limited to allow generalisation beyond the training set. To address the challenge, we propose to use a transfer learning approach whereby the model is first trained on a synthetic dataset replicating features of the original objects. In this study, the objects were smartphone photographs of near-complete Roman terra sigillata pottery vessels from the collection of the Museum of London. Taking the replicated features from published profile drawings of pottery forms allowed the integration of expert knowledge into the process through our synthetic data generator. After this first initial training the model was fine-tuned with data from photographs of real vessels. We show, through exhaustive experiments across several popular deep learning architectures, different test priors, and considering the impact of the photograph viewpoint and excessive damage to the vessels, that the proposed hybrid approach enables the creation of classifiers with appropriate generalisation performance. This performance is significantly better than that of classifiers trained exclusively on the original data, which shows the promise of the approach to alleviate the fundamental issue of learning from small datasets.

show abstract

ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications

Cited by 5 publications

References 61 publications

Advances in Skeleton-Based Fall Detection in RGB Videos: From Handcrafted to Deep Learning Approaches

Advances in Skeleton-Based Fall Detection in RGB Videos: From Handcrafted to Deep Learning Approaches

Survey on Videos Data Augmentation for Deep Learning Models

Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery

Contact Info

Product

Resources

About