Approaches of building a real-world object detector data source

Вантажиться...
Ескіз
Дата
2023
Автори
Pavlova, O.
Bashta, A.
Kuzmin, A.
Назва журналу
Номер ISSN
Назва тому
Видавець
Хмельницький національний університет
Анотація
In our constantly developing world virtual, augmented, and mixed reality technologies are becoming integral parts of our daily lives. In the current stage of Information Technology field development, technologies of virtual, augmented and mixed reality can be seen in almost all areas of human life. Nowadays AR is used in Marketing and Advertising, Education, Medicine, Automotive, Game Development, Navigation and other areas of our everyday life. Therefore, object detection is a crucial task in computer vision and AI applications, enabling machines to identify and locate objects within images or video frames. The accuracy and performance of an object detector heavily rely on the quality and diversity of the training data. This paper is aimed at finding the approaches of building a real-world object detector data source to be able to create a model for detecting a sport games surfaces using the Action & Vision App. During this research several structured approaches of building an object detector data source have been built, drawing inspiration from Apple's Create ML documentation on the topic. Additionally, real-world applications available on both the App Store and Google Play that leverage object detection technology were showcased and analyzed. In the course of study a dataset of objects has been collected and then utilized to build a robust detection model, tailored to function seamlessly with Vision and Core ML frameworks on iOS devices. The trained object detection model, informed by the diverse dataset and robust training process, is employed to identify and outline tables and rectangles in each frame of the video stream. The model and the proposed approaches will be further applied to develop the method of object detection in the real world and create a mobile application for sport games simulation, that would help players to practice their skills out of the training field.
Опис
Ключові слова
object detection, computer vision, AI applications, training data, Create ML, structured data source, real-world applications, App Store, Google Play
Бібліографічний опис
Pavlova O. Approaches of building a real-world object detector data source / O. Pavlova, A. Bashta, A. Kuzmin // Computer Systems and Information Technologies. – 2023. – No 3. – P. 23-31.
Зібрання