Optimized training of deep neural network for image analysis using synthetic objects and augmented reality

Lu, Tingting; Huyen, Alexander; Nguyen, Luan Viet; Osborne, Joseph; Eldin, Sarah; Yun, Kyongsik

doi:10.1117/12.2522198

Cited by 7 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptability and reusability of this method is exemplified by the ability to train networks to detect specific items or people in very challenging circumstances. So, the use of powerful graphics engines that are able to reproduce reality, or a scenario to be represented, in a very realistic way is, therefore, becoming a particularly crucial practice for increasing or balancing the recognition classes in a dataset for CNNs [40][41][42].…”

Section: Related Workmentioning

confidence: 99%

Synthetic Data Generation to Speed-Up the Object Recognition Pipeline

2021

View full text Add to dashboard Cite

This paper provides a methodology for the production of synthetic images for training neural networks to recognise shapes and objects. There are many scenarios in which it is difficult, expensive and even dangerous to produce a set of images that is satisfactory for the training of a neural network. The development of 3D modelling software has nowadays reached such a level of realism and ease of use that it seemed natural to explore this innovative path and to give an answer regarding the reliability of this method that bases the training of the neural network on synthetic images. The results obtained in the two proposed use cases, that of the recognition of a pictorial style and that of the recognition of men at sea, lead us to support the validity of the approach, provided that the work is conducted in a very scrupulous and rigorous manner, exploiting the full potential of the modelling software. The code produced, which automatically generates the transformations necessary for the data augmentation of each image, and the generation of random environmental conditions in the case of Blender and Unity3D software, is available under the GPL licence on GitHub. The results obtained lead us to affirm that through the good practices presented in the article, we have defined a simple, reliable, economic and safe method to feed the training phase of a neural network dedicated to the recognition of objects and features to be applied to various contexts.

show abstract

Section: Related Workmentioning

confidence: 99%

Synthetic Data Generation to Speed-Up the Object Recognition Pipeline

2021

View full text Add to dashboard Cite

show abstract

“…The adaptability and reusability of this method is exemplified by the ability to train networks to detect specific items or people in very challenging circumstances. So, the use of powerful graphics engines that are able to reproduce reality, or a scenario to be represented, in a very realistic way is therefore becoming a particularly crucial practise for increasing or balancing the recognition classes in a dataset for CNNs [40][41][42].…”

Section: Related Workmentioning

confidence: 99%

Synthetic Data Generation to Speed-up the Object Recognition Pipeline

Perri¹,

Simonetti²,

Gervasi³

2021

Preprint

View full text Add to dashboard Cite

This paper provides a methodology for the production of synthetic images for training neural networks to recognise shapes and objects. There are many scenarios in which it is difficult, expensive and even dangerous to produce a set of images that is satisfactory for the training of a neural network. The development of 3D modelling software has nowadays reached such a level of realism and ease of use that it seemed natural to explore this innovative path and to give an answer regarding the reliability of this method that bases the training of the neural network on synthetic images. The results obtained in the two proposed use cases, that of the recognition of a pictorial style and that of the recognition of migrants at sea, leads us to support the validity of the approach, provided that the work is conducted in a very scrupulous and rigorous manner, exploiting the full potential of the modelling software. The code produced, which automatically generates the transformations necessary for the data augmentation of each image, and the generation of random environmental conditions in the case of Blender and Unity3D software, is available under the GPL licence on GitHub. The results obtained lead us to affirm that through the good practices presented in the article, we have defined a simple, reliable, economic and safe method to feed the training phase of a neural network dedicated to the recognition of objects and features, to be applied to various contexts.

show abstract

“…The Department of Homeland Security (DHS) Science and Technology Directorate (S&T) partnered with Canada's Department of National Defence Science and Technology Organization, Defence Research and Development Canada Centre for Security Science (DRDC CSS) to support this experiment to examine whether artificial intelligence could be used to improve the information overload. The experiment was part of the Next Generation First Responder Program by DHS [1][2][3][4][5] .…”

Section: Introductionmentioning

confidence: 99%

Transforming unstructured voice and text data into insight for paramedic emergency service using recurrent and convolutional neural networks

Yun

Huyen

2020

Pattern Recognition and Tracking XXXI

View full text Add to dashboard Cite

A BSTRACTParamedics often have to make lifesaving decisions within a limited time in an ambulance. They sometimes ask the doctor for additional medical instructions, during which valuable time passes for the patient. This study aims to automatically fuse voice and text data to provide tailored situational awareness information to paramedics. To train and test speech recognition models, we built a bidirectional deep recurrent neural network (long short-term memory (LSTM)). Then we used convolutional neural networks on top of custom-trained word vectors for sentence-level classification tasks. Each sentence is automatically categorized into four classes, including patient status, medical history, treatment plan, and medication reminder. Subsequently, incident reports were automatically generated to extract keywords and assist paramedics and physicians in making decisions. The proposed system found that it could provide timely medication notifications based on unstructured voice and text data, which was not possible in paramedic emergencies at present. In addition, the automatic incident report generation provided by the proposed system improves the routine but error-prone tasks of paramedics and doctors, helping them focus on patient care.

show abstract

Optimized training of deep neural network for image analysis using synthetic objects and augmented reality

Cited by 7 publications

References 5 publications

Synthetic Data Generation to Speed-Up the Object Recognition Pipeline

Synthetic Data Generation to Speed-Up the Object Recognition Pipeline

Synthetic Data Generation to Speed-up the Object Recognition Pipeline

Transforming unstructured voice and text data into insight for paramedic emergency service using recurrent and convolutional neural networks

Contact Info

Product

Resources

About