Отрывок: The following tables, it is present the evaluation of the PCT [32] and PointNet [5] models. Given the small number of points, each model is trained until a clear sta- bilization tendency was observed. Table 1 shows the configuration analysis of the PCT model for on-road 3D object classification after training it over the dataset defined in the previous subsection. Its columns show the results with model depth variation as transformer block number. The rows ...
Название : | Transformer point net: cost-efficient classification of on-road objects captured by light ranging sensors on low-resolution conditions |
Авторы/Редакторы : | Pamplona, J. Madrigal, C. Herrera-Ramirez, J. |
Ключевые слова : | LiDAR deep learning point cloud object classification transformers low resolution autonomous vehicles low specification computing |
Дата публикации : | Апр-2022 |
Издательство : | Самарский национальный исследовательский университет |
Библиографическое описание : | Pamplona J, Madrigal C, Herrera-Ramirez J. Transformer point net: cost-efficient classification of on-road objects captured by light ranging sensors on low-resolution conditions. Computer Optics 2022; 46(2): 326-334. DOI: 10.18287/2412-6179-CO-1001. |
Серия/номер : | 46;2 |
Аннотация : | The three-dimensional perception applications have been growing since Light Detection and Ranging devices have become more affordable. On those applications, the navigation and collision avoidance systems stand out for their importance in autonomous vehicles, which are drawing an appreciable amount of attention these days. The on-road object classification task on three-dimensional information is a solid base for an autonomous vehicle perception system, where the analysis of the captured information has some factors that make this task challenging. On these applications, objects are represented only on one side, its shapes are highly variable and occlusions are commonly presented. But the highest challenge comes with the low resolution, which leads to a significant performance dropping on classification methods. While most of the classification architectures tend to get bigger to obtain deeper features, we explore the opposite side contributing to the implementation of low-cost mobile platforms that could use low-resolution detection and ranging devices. In this paper, we propose an approach for on-road objects classification on extremely low-resolution conditions. It uses directly three-dimensional point clouds as sequences on a transformer-convolutional architecture that could be useful on embedded devices. Our proposal shows an accuracy that reaches the 89.74 % tested on objects represented with only 16 points extracted from the Waymo, Lyft’s level 5 and Kitti datasets. It reaches a real time implementation (22 Hz) in a single core processor of 2.3 Ghz. |
URI (Унифицированный идентификатор ресурса) : | 10.18287/2412-6179-CO-1001 http://repo.ssau.ru/handle/Zhurnal-Komputernaya-optika/Transformer-point-net-costefficient-classification-of-onroad-objects-captured-by-light-ranging-sensors-on-lowresolution-conditions-102113 |
Другие идентификаторы : | Dspace\SGAU\20230220\102113 |
ГРНТИ: | 29.31.15, 29.33.43, 20.53.23 |
Располагается в коллекциях: | Журнал "Компьютерная оптика" |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
18-Pamplona-Madrigal-Herrera-Ramirez_KI-Lit-MA-JuN2.pdf | Основная статья | 690.15 kB | Adobe PDF | Просмотреть/Открыть |
Показать полное описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.