Implementing object tracking for seeding quality on Android devices
ResumoThe recent increase in processing power of mobile devices opens up a wide range of opportunities for the development of innovative applications. Tracking combines object recognition with video processing technologies to detect objects in a scene and label them uniquely. In this work, we present an application for evaluating seeding quality, which is an important factor for achieving higher production numbers. The application developed in this work is implemented on Android platform and uses SORT algorithm as a basis for seed tracking. This paper proposes modifications to the tracking algorithm to increase precision and performance based on the conditions and constraints of the case study. In the experiments, the application running on a real device achieved a performance of 27 frames per second to detect and track five seeds in the scene.
Palavras-chave: Performance evaluation, Production, Systems engineering and theory, Mobile handsets, Object tracking, Object recognition, smartphone, seeding quality
MÜLLING, Lucas Eduardo Fischer; OYAMADA, Marcio Seiji. Implementing object tracking for seeding quality on Android devices. In: SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SISTEMAS COMPUTACIONAIS (SBESC), 11. , 2021, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 166-172. ISSN 2237-5430.