10.14489/vkit.2018.11.pp.011-021

DOI: 10.14489/vkit.2018.11.pp.011-021

Блохинов Ю. Б., Андриенко Е. Э.
О ПРИМЕНЕНИИ РАСШИРЕННОГО МЕТОДА ХАФА ДЛЯ ВЫДЕЛЕНИЯ РАЗМЕТКИ АЭРОДРОМА
(c. 11-21)

Аннотация. Разработан метод выделения линейной разметки аэродрома по космическим снимкам высокого разрешения. Показано, что для детектирования контуров, представляющих собой сопряжение прямолинейных отрезков и кривых второго порядка, может быть эффективно использовано преобразование Хафа. Детально описан расширенный вариант метода, включающий в себя помимо преобразования Хафа, алгоритмы постобработки данных, позволяющие значительно усилить результаты классического подхода.

Ключевые слова: спутниковые снимки; аэродромные картографические базы данных; детектирование линейной разметки; выделение контуров; детектор Канни; преобразование Хафа; стабильный метод оценки параметров модели на основе случайных выборок.

Blokhinov Yu. B., Andrienko E. E.
EXTENDED HOUGH-BASED SCHEMES FOR AIRFIELD MARKING DETECTION
(pp. 11-21)

Abstract. The article deals with the problem of airfields maps creation and updating process automation based on high-resolution space imagery. The subject is very urgent due to growing aircrafts in air streams of and airports land space. At the same time, the largest air hubs of Russia and other leading countries of the world develops very dynamically. The original approach is proposed to airfield marking detection problem based on the Hough transform use. It is supposed that marking line consists of elementary curves: linear pieces and arches of circles, therefore, for detection of the corresponding parts of a contour in image it is possible to use the Hough transform for straight lines and circles. However, this method direct implementation on an terrain surface real images leads to a number of serious problems and not giving good results. Therefore, to increase a method efficiency for the considered important special cases a number of algorithms allowing filtering off small false a contours and increase speed at counting of votes in the Hough transform. The last one is especially important for circles where the accumulator is three-dimensional. The method under consideration is described in sufficient detail, special attention is paid to the data post-processing algorithms, allowing to solve effectively collisions at the choice of the correct hypothesis. One more serious problem is the problem to distinguish between pieces of a straight line and a circle arch of big radius in the presence of the real image noise. For solution of this task the special criterion is proposed by the authors. The developed algorithms have shown rather successful results on test database of space imagery.

Keywords: Space imagery; Aerodrome Mapping Data Base; Airfield marking detection; Contours extraction; Canny operator; Hough transform; RANSAC algorithm.

+ - Информация об авторах (About the Authors) Click to collapse

Рус

Ю. Б. Блохинов, Е. Э. Андриенко (ФГУП «Государственный научно-исследовательский институт авиационных систем» ГНЦ РФ, Москва, Россия) E-mail: Этот e-mail адрес защищен от спам-ботов, для его просмотра у Вас должен быть включен Javascript

Eng

Yu. B. Blokhinov, E. E. Andrienko (State Research Institute of Aviation Systems State Scientific Center of Russian Federation, Moscow, Russia) E-mail: Этот e-mail адрес защищен от спам-ботов, для его просмотра у Вас должен быть включен Javascript

+ - Библиографический список (References) Click to collapse

Рус

1. Ballard D. H. Generalizing the Hough Transform to Detect Arbitrary Shapes // Pattern Recoqnition. 1981. V. 13, No 2. P. 111 – 122. URL:http//userweb.cs.utexas.edu/data/HoughT.pdf
2. Duda R. O., Hart P. E. Use of the Hough Transformation to Detect Lines and Curves in Pictures // Communications of the ACM. 1972. V. 15, No 1. P. 11 – 15.
3. Canny J. A. Computational Approach to Edge Detection // IEEE Trans. on Pattern Analysis and Machine Intelligence. 1986. V. РАМI-8, No 6. P. 679 – 698.
4. Matas J., Galambos C., Kittler J. V. Robust Detection of Lines Using the Progressive Probabilistic Hough Transform // Comp. Vision and Image Understanding. 2000. V. PAMI-8, Is 1. P. 119 – 137. htts://doi.org/10.1006/cviu.1999.0831
5. Davies E. R. Machine Vision: Theory, Algorithms and Practicalities. Academic Press. 2012. 912 p.
6. Fischler M. A., Bolles R. C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography // Communications of the ACM. 1981. V. 24, No 6. P. 381 – 395.
7. Comparative Study of Hough Transform Methods for Circle Finding / Yuen H. K. et all // Image Vision Computing 1990. V. 8, No 1. P. 71 – 77.
8. Лешко Б. Ю. Методы оптимизации: конспект лекций. Новосибирск: Изд-во НГТУ, 2009. 126 с.

Eng

1. Ballard D. H. (1981). Generalizing the Hough Transform to Detect Arbitrary Shapes. Pattern Recoqnition, 13(2), pp. 111-122.
2. Duda R. O., Hart P. E. (1972). Use of the Hough Transformation to Detect Lines and Curves in Pictures. Communications of the ACM, 15, pp. 11-15.
3. Canny J. A. (1986). Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), pp. 679-698.
4. Matas J., Galambos C., Kittler J. V. (2000). Robust Detection of Lines Using the Progressive Probabilistic Hough Transform. Computer Vision and Image Understanding, 78(1), pp. 119-137.
5. Davies E. R. (2012). Machine Vision: Theory, Algorithms and Practicalities. Academic Press.
6. Fischler M. A., Bolles R. C. (1981). Random Sample Consensus: a Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Communications of the ACM, 24(6), pp. 381-395.
7. Yuen H. K. et al. (1990). Comparative Study of Hough Transform Methods for Circle Finding. Image and Vision Computing, 8(1), pp. 71-77.
8. Leshko B. Yu. (2009). Optimization methods: lecture notes. Novosibirsk: Izdatel'stvo NGTU. [in Russian language]

+ - Заказать электронную версию статьи (Purchase digital version of a single article) Click to collapse

Рус

Статью можно приобрести в электронном виде (PDF формат).

Стоимость статьи 350 руб. (в том числе НДС 18%). После оформления заказа, в течение нескольких дней, на указанный вами e-mail придут счет и квитанция для оплаты в банке.

После поступления денег на счет издательства, вам будет выслан электронный вариант статьи.

Для заказа скопируйте doi статьи:

10.14489/vkit.2018.11.pp.011-021

и заполните форму

Отправляя форму вы даете согласие на обработку персональных данных.

Eng

This article is available in electronic format (PDF).

The cost of a single article is 350 rubles. (including VAT 18%). After you place an order within a few days, you will receive following documents to your specified e-mail: account on payment and receipt to pay in the bank.

After depositing your payment on our bank account we send you file of the article by e-mail.

To order articles please copy the article doi:

10.14489/vkit.2018.11.pp.011-021

and fill out the form