|
ИСТИНА |
Войти в систему Регистрация |
Интеллектуальная Система Тематического Исследования НАукометрических данных |
||
Композиции признаков для видеотрекинга при помощи фильтра частицстатья
- Автор: Нижибицкий Е.А.
- Журнал: Машинное обучение и анализ данных
- Том: 1
- Номер: 11
- Год издания: 2015
- Первая страница: 1517
- Последняя страница: 1528
- Аннотация: This work considers the likelihood models based on similarity measures extracted from image features which are widely used in the field of video tracking using particle filters. New computationally optimal methods for multiple feature extraction from several regions of the same image are proposed. The optimization is performed by using integral images, first prominently used in computer vision within Viola–Jones object detection framework for Haar rectangles and for other studied features. It is experimentally demonstrated that feature compositions can be used even in the tasks where each of them is useless by itself. The performance achieved using the proposed compositions is greater than one in the similar study and comparable to the performance of more complicated models based on ensemble boosting.
- Добавил в систему: Нижибицкий Евгений Алексеевич