Autors: Kolker, Aleksey., Ivanov, V. V., Dimitrov, L. V., Rashid, A., Bdiwi, M., Oshchepkova, S., Pershina, Z.
Title: The ray tracing based tool for generation artificial images and neural network training
Keywords: POV-Ray, Ray Tracing, COCO-style Annotation, Instance Segmentation, Convolutional Neural Network, Robotics, Computer Vision.

Abstract: Creating quality-annotated dataset is one of the main tasks in the field of deep learning technologies for pattern recognition. However, in the real world, collecting a sufficient number of detailed images of an object is difficult and time-consuming. The article considers an approach to creating synthetic datasets based on the ray tracing method. This paper also presents the results of success tests of real object image segmentation by convolutional neural networks, trained entirely on synthetic data and data of different nature.

References

    Issue

    , 2020, Portugal, ISBN 978-989-758-474-9; ISSN 2184-3228, DOI: 10.5220/0010168102570264

    Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus и Web of Science