Отрывок: From (8) and (9) the resulting expression for jh is given by 1 j j j j h M T M u . (10) When the background image is available, an adaptive algorithm can be used to improve the DC of composite filters [14]. The background can be described either stochastically, treated as a realization of a stochastic process, or deterministically in the form of a typical background picture. The background used in the adaptive algorithm can als...
Полная запись метаданных
Поле DC | Значение | Язык |
---|---|---|
dc.contributor.author | Kober, V. | - |
dc.contributor.author | Kuznetsov, V. | - |
dc.date.accessioned | 2017-05-15 12:40:08 | - |
dc.date.available | 2017-05-15 12:40:08 | - |
dc.date.issued | 2017 | - |
dc.identifier | Dspace\SGAU\20170512\63739 | ru |
dc.identifier.citation | Kober V. Target tracking with composite linear filters on noisy scenes / V. Kober, V. Kuznetsov // Сборник трудов III международной конференции и молодежной школы «Информационные технологии и нанотехнологии» (ИТНТ-2017) - Самара: Новая техника, 2017. - С. 563-567. | ru |
dc.identifier.uri | http://repo.ssau.ru/handle/Informacionnye-tehnologii-i-nanotehnologii/Target-tracking-with-composite-linear-filters-on-noisy-scenes-63739 | - |
dc.description.abstract | A tracking system using a bank of adaptive linear filters is proposed. Tracking is carried out by means of multiple target detections. The linear filters are designed from multiple views of a target using synthetic discriminant functions. For each view an optimum filter is derived from noisy reference image and disjoint background model. An iterative algorithm is used to improve the performance of the synthesized filters. The number of filters in the bank can be controlled to guarantee a prescribed tracking accuracy. Computer simulation results show that the proposed algorithm is able to precisely track a target. | ru |
dc.description.sponsorship | This work was supported the Russian Science Foundation grant №15-19-10010. | ru |
dc.language.iso | en_US | ru |
dc.publisher | Новая техника | ru |
dc.subject | object tracking | ru |
dc.subject | correlation filters | ru |
dc.subject | composite filters | ru |
dc.title | Target tracking with composite linear filters on noisy scenes | ru |
dc.type | Article | ru |
dc.textpart | From (8) and (9) the resulting expression for jh is given by 1 j j j j h M T M u . (10) When the background image is available, an adaptive algorithm can be used to improve the DC of composite filters [14]. The background can be described either stochastically, treated as a realization of a stochastic process, or deterministically in the form of a typical background picture. The background used in the adaptive algorithm can als... | - |
Располагается в коллекциях: | Информационные технологии и нанотехнологии |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
paper 109_563-567.pdf | Основная статья | 829.51 kB | Adobe PDF | Просмотреть/Открыть |
Показать базовое описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.