
Объект иÑÑÐ»ÐµÐ´Ð¾Ð²Ð°Ð½Ð¸Ñ â€“ ÑиÑтемы компьютерного зрениÑ. Цель работы – разработка ÑиÑтемы компьютерного Ð·Ñ€ÐµÐ½Ð¸Ñ Ð´Ð»Ñ Ñ€Ð°ÑÐ¿Ð¾Ð·Ð½Ð°Ð²Ð°Ð½Ð¸Ñ Ð·Ð°Ð¿Ñ€ÐµÑ‰Ð°ÑŽÑ‰Ð¸Ñ… дорожных знаков, ÑоответÑтвующих требованиÑм венÑкой конвенции о дорожном движении. Ð’ работе раÑÑмотрены ÑущеÑтвующие алгоритмы компьютерного Ð·Ñ€ÐµÐ½Ð¸Ñ Ð¸ машинного обучениÑ. Разработано программное обеÑпечение ÑиÑтемы раÑÐ¿Ð¾Ð·Ð½Ð°Ð²Ð°Ð½Ð¸Ñ Ð·Ð°Ð¿Ñ€ÐµÑ‰Ð°ÑŽÑ‰Ð¸Ñ… дорожных знаков, ÑоÑтоÑщее из детектора и клаÑÑификатора. РаÑÑмотрены ÑредÑтва вычиÑлительной техники, подходÑщие Ð´Ð»Ñ Ð¸ÑÐ¿Ð¾Ð»ÑŒÐ·Ð¾Ð²Ð°Ð½Ð¸Ñ Ð¸Ñ… в качеÑтве оÑновы Ð´Ð»Ñ Ð±Ð¾Ñ€Ñ‚Ð¾Ð²Ð¾Ð¹ ÑиÑтемы компьютерного Ð·Ñ€ÐµÐ½Ð¸Ñ Ð¸ в качеÑтве уÑкорителей вычиÑлений. Разработанное программное обеÑпечение развернуто и протеÑтировано на предлагаемом аппаратном обеÑпечении. Определены оÑновные параметры разработанной ÑиÑтемы. Проведен анализ полученных результатов. Предложены методы ÑƒÐ²ÐµÐ»Ð¸Ñ‡ÐµÐ½Ð¸Ñ Ð¿Ñ€Ð¾Ð¸Ð·Ð²Ð¾Ð´Ð¸Ñ‚ÐµÐ»ÑŒÐ½Ð¾Ñти разработанной ÑиÑтемы раÑÐ¿Ð¾Ð·Ð½Ð°Ð²Ð°Ð½Ð¸Ñ Ð·Ð°Ð¿Ñ€ÐµÑ‰Ð°ÑŽÑ‰Ð¸Ñ… дорожных знаков.
The object of the graduate qualification work is computer vision systems. The subject of the graduate qualification work is the development a computer vision system for recognizing prohibitory traffic signs that comply with the requirements of the Vienna Convention on Road Signs and Signals. In this work existing computer vision and machine learning algorithms were considered. Prohibitory road signs detector and classifier software were developed. Hardware devices suitable for use as a basis for an onboard computer vision system and as computational accelerators were surveyed. The developed software was deployed and tested on the proposed hardware. The main parameters of the developed system were determined. The analysis of the obtained results was carried out. Methods for increasing the performance of the developed prohibitory traffic signs recognition system were proposed.
machine learning, меÑод гÑадиенÑного ÑпÑÑка, компÑÑÑеÑное зÑение, маÑинное обÑÑение, computer vision, gradient descent algorithm
machine learning, меÑод гÑадиенÑного ÑпÑÑка, компÑÑÑеÑное зÑение, маÑинное обÑÑение, computer vision, gradient descent algorithm
| selected citations These citations are derived from selected sources. 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 |
