| 10.14489/vkit.2018.02.pp.003-009 |
|
DOI: 10.14489/vkit.2018.02.pp.003-009 Лисицын В. М., Обросов К. В. Аннотация. Предложены методы и алгоритмы обнаружения фрагментов образов цилиндрических поверхностей на сцене по дальностному лазерно-локационному изображению. Эффективность алгоритмов продемонстрирована на реальных изображениях сцен городского типа. Ключевые слова: Laser location; Image segmentation; Processing of statistical data; Estimation of parameters; Testing of statistical hypotheses; Criterion of agreement. Lisitsyn V. M., Obrosov K. V. Abstract. Segmentation is the necessary stage of image processing while automatic pattern recognition and scene analysis. The Laser-Location (LL) image segmentation effectiveness can be much higher than the television (TV) or infrared (IR) image segmentation. This is because LL systems form 3D images, while passive systems form images contains only indirect object shape signs (brightness, contrast, texture, etc.). However, methods for segmentation of LL-images are much less developed than for TV- and IR-images. At present, the researches directed to increase the quantity of identifiable objects surfaces on LL images, in particular, second order surfaces (cylinders, spheres, cones, etc.) are actual. In this paper, a method is proposed and algorithms are developed to select fragments of cylindrical surfaces (pipes, cooling towers, cisterns, oil storage tanks, water towers, etc.) on LL-images with their parameters estimation. For the case of equality in the accuracy of measuring the distances and the sensing points coordinates, optimal estimates of the axis position and radius of the cylindrical surface fragment were obtained. When searching, the validity about measurements belonging to a cylindrical surface hypothesis is verified. A one-sided statistical agreement criterion is used, since in this application the problem of choosing one from several measurements approximation models is not solved. Such a criterion defines a confidence interval for the chosen proximity measure, which corresponds to cylindrical surface measurements approximating possibility. Therefore, when making a search, decisions on LL-image segmentation are taken, i.e. corresponding to cylindrical surfaces fragments areas allocation. The efficiency of methods and algorithms is verified by modeling with using industrial-urban scenes real LL-images. Keywords: Laser location; Image segmentation; Processing of statistical data; Estimation of parameters; Testing of statistical hypotheses; Criterion of agreement.
РусВ. М. Лисицын, К. В. Обросов (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 EngV. M. Lisitsyn, K. V. Obrosov (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
Рус
Eng1. Rozhdestvin V. N. (2006). Fundamentals of pulsed laser location. Moscow: Izdatel'stvo MGTU. [in Russian language]
РусСтатью можно приобрести в электронном виде (PDF формат). DOI: 10.14489/vkit.2018.02.pp.003-009 Скопируйте DOI статьи и перейдите по ссылке https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-vestnik-kompyuternyh-i-informatsionnyh-tehnologiy В комментарии к заказу обязательно укажите DOI статьи. .
EngThis article is available in electronic format (PDF). DOI: 10.14489/vkit.2018.02.pp.003-009 Copy the article DOI and follow the link https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-vestnik-kompyuternyh-i-informatsionnyh-tehnologiy Please specify the article DOI in the order comments.
.
|
Archive
Разработка концепции и создание сайта - ООО «Издательский дом «СПЕКТР»