This paper presents the analysis of methods for client-side object detection on the Android platform. It describes a phased scheme of the object detection process, identifying its elementary tasks, namely keypoint detection, feature extraction and binary pattern matching. This is followed by a brief overview of the algorithms applied to those tasks in the Android mobile environment. A comparative analysis of those algorithms is performed, with respect to efficiency and object detection quality. The results of this study provide the ability to determine the best possible configuration of object detection algorithms for the Android platform.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.