Отрывок: For a clear demonstration, it is proposed to construct a distance matrix between objects of the basic assembly and also to provide its visualization. The values in the distance matrix could be replaced by grayscale values, where black is the zero distance be- tween objects, and white is the maximum distance. The distance between the skeletal models from all videos in TST Fall Detection v2 database and skeletons from basic ass...
Название : | The basic assembly of skeletal models in the fall detection problem |
Авторы/Редакторы : | Seredin, O.S. Kopylov, A.V. Surkov, E.E. Huang, S.-C. |
Ключевые слова : | skeletal model of human figure pairwise similarity activity map featureless pattern recognition basic assembly convolutional neural networks |
Дата публикации : | Апр-2023 |
Издательство : | Самарский национальный исследовательский университет |
Библиографическое описание : | Seredin OS, Kopylov AV, Surkov EE, Huang SC. The basic assembly of skeletal models in the fall detection problem. Computer Optics 2023; 47(2): 323-334. DOI: 10.18287/2412-6179-CO-1158. |
Серия/номер : | 47;2 |
Аннотация : | The paper considers the appliance of the featureless approach to the human activity recognition problem, which exclude the direct anthropomorphic and visual characteristics of human figure from further analysis and thus increase the privacy of the monitoring system. A generalized pairwise comparison function of two human skeletal models, invariant to the sensor type, is used to project the object of interest to the secondary feature space, formed by the basic assembly of skeletons. A sequence of such projections in time forms an activity map, which allows an application of deep learning methods based on convolution neural networks for activity recognition. The proper ordering of skeletal models in a basic assembly plays an important role in secondary space design. The study of ordering of the basic assembly by the shortest unclosed path algorithm and correspondent activity maps for video streams from the TST Fall Detection v2 database are presented. |
URI (Унифицированный идентификатор ресурса) : | 10.18287/2412-6179-CO-1158 http://repo.ssau.ru/handle/Zhurnal-Komputernaya-optika/The-basic-assembly-of-skeletal-models-in-the-fall-detection-problem-102131 |
Другие идентификаторы : | Dspace\SGAU\20230222\102131 |
ГРНТИ: | 29.31.15, 29.33.43, 20.53.23 |
Располагается в коллекциях: | Журнал "Компьютерная оптика" |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
2412-6179_2023_47-2_323-334.pdf | Основная статья | 9.33 MB | Adobe PDF | Просмотреть/Открыть |
Показать полное описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.