Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Распознавание объектов, как Ñ‚Ñ€Ñ‘Ñ Ð¼ÐµÑ€Ð½Ñ‹Ñ , с помощью Ð½ÐµÐ¹Ñ€Ð¾ÑÐµÑ‚ÐµÐ²Ñ‹Ñ Ñ‚ÐµÑ Ð½Ð¾Ð»Ð¾Ð³Ð¸Ð¹

выпускная квалификационная работа магистра

Распознавание объектов, как Ñ‚Ñ€Ñ‘Ñ Ð¼ÐµÑ€Ð½Ñ‹Ñ , с помощью Ð½ÐµÐ¹Ñ€Ð¾ÑÐµÑ‚ÐµÐ²Ñ‹Ñ Ñ‚ÐµÑ Ð½Ð¾Ð»Ð¾Ð³Ð¸Ð¹

Abstract

В результате были изучены формы представления трехмерных данных и в качестве результирующей выбрана воксельная. Разработана архитектура нейросети с использованием сверточных и рекуррентных технологий. Спроектирована и составлена структурная схема нейросетевой модели. В качестве инструментария для разработки использован язык программирования Python и фреймворк Tensorflow. Приведены программные алгоритмы для реализации фундаментальных и основных блоков сети. Проведена оценка качества отработки созданной модели на базе анализа графиков для потерь при обучении и валидации, а также трех метрик: Accuracy, RMS и IOU. Представлены результаты работы сети в виде выходных реконструированных трехмерных объектов.

As a result, the forms of representation of three-dimensional data were studied and voxel was chosen as the result. The neural network architecture has been developed using convolutional and recurrent technologies. A struct diagram of the neural network model was designed and compiled. The Python programming language and the Tensorflow framework were used as development tools. Software algorithms for the implementation of the fundamental and main blocks of the network are given. The quality of the developed model was assessed based on the analysis of graphs for training and validation losses, as well as three metrics: Accuracy, RMS, and IOU. The results of the network operation are presented in the form of output reconstructed three-dimensional objects.

Keywords

Ñ‚Ñ€ÐµÑ Ð¼ÐµÑ€Ð½Ñ‹Ðµ изображения, Нейронные сети, 3D images, 3D реконструкция, 3D reconstruction, Python

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Related to Research communities
Upload OA version
Are you the author? Do you have the OA version of this publication?