
Тема выпуÑкной квалификационной работы: «Ðнализ изображей».Ð”Ð°Ð½Ð½Ð°Ñ Ð±ÑƒÐ´ÐµÑ‚ поÑвÑщена разработки приложениÑ, которое раÑпознание дорожную полоÑу в видеоматериале. Будет поÑтроена модель и обучена при помощи методик и технологий, в чаÑтноÑти открытой библиотекой OpenCV.Ð’ ходе работы будут решены Ñледующие задачи, а именно:Преобразование в вид Ñверху;Выделение на изображении белого цвета;ÐšÐ¾Ð½Ð²ÐµÑ€Ñ‚Ð°Ñ†Ð¸Ñ Ð¿Ð¾Ð»ÑƒÑ‡ÐµÐ½Ð½Ð¾Ð³Ð¾ Ð¸Ð·Ð¾Ð±Ñ€Ð°Ð¶ÐµÐ½Ð¸Ñ Ð² бинарное;Применение фильтра Ð´Ð»Ñ Ñ€Ð°Ð·Ð¼Ñ‹Ñ‚Ð¸Ñ Ð¸Ð·Ð¾Ð±Ñ€Ð°Ð¶ÐµÐ½Ð¸Ñ;МорфологичеÑкое преобразование;Разделение Ð¿Ð¾Ð»Ð¾Ñ Ñ€Ð°Ð·Ð¼ÐµÑ‚ÐºÐ¸;ПоÑтроение ÑƒÑ€Ð°Ð²Ð½ÐµÐ½Ð¸Ñ Ð¿Ñ€Ñмых.С помощью данного алгоритма будет возможно определÑть дорожную полоÑу в движении.Далее будет проведен ÑкÑперимент, как детектор будет работать в ночное Ð²Ñ€ÐµÐ¼Ñ Ñуток, решен Ð²Ð¾Ð¿Ñ€Ð¾Ñ Ñ Ð´Ð¸Ñтанцией, а именно: при Ñредней ÑкороÑти Ð°Ð²Ñ‚Ð¾Ð¼Ð¾Ð±Ð¸Ð»Ñ Ð¾Ð¿Ñ€ÐµÐ´ÐµÐ»ÑтьÑÑ Ñ€Ð°ÑÐ¿Ð¾Ð·Ð½Ð°Ð²Ð°ÐµÐ¼Ð°Ñ Ð¾Ð±Ð»Ð°Ñть, чтобы детектор уÑпевал обработать дорожную полоÑу до того, как автомобиль ее проедет. Справедливо будет обратить внимание на бездорожье, «Ñложную» дорогу – Ñможет ли детектор раÑпознать уÑловную пропаÑть.Â
The theme of the graduate qualification work is: «Image analysis».The work devoted to the development of an application that recognizes the road lane in the video. A model will be built and trained using methods and technologies, in particular, the OpenCV open library.In the course of the work next task will be solved:Convert to top view;Selection on the image of white color;Converting the resulting image to binary;Applying a filter to blur an image;Morphological transformation;Separation of lane markings;Construction of the equation of lines.  With this algorithm, it will be possible to determine the road lane in motion.Next, an experiment will be carried out on how the detector will work at night, the issue with the distance will be resolved, namely: at the average speed of the car, the recognizable area is determined so that the detector has time to process the road lane before the car passes it. It would be fair to pay attention to off-road, "difficult" road - whether the detector will be able to recognize the conditional abyss.
recording-road lane, ÑазмÑÑие гаÑÑÑа, компÑÑÑеÑное зÑение, gaussian blur, ÑаÑпознание доÑожной полоÑÑ, programming, computer vision, пÑогÑаммиÑование
recording-road lane, ÑазмÑÑие гаÑÑÑа, компÑÑÑеÑное зÑение, gaussian blur, ÑаÑпознание доÑожной полоÑÑ, programming, computer vision, пÑогÑаммиÑование
| 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 |
