This article describes the algorithms of spatial orientation of SLAM, PTAM and
their positive and negative sides. Based on the SLAM method, a method that uses an RGBD camera and additional sensors was developed: an accelerometer, a gyroscope, and a magnetometer. The investigated orientation methods have their advantages when moving along a straight trajectory or when rotating a moving platform. As a result of experiments and a weighted linear combination of the positions obtained from data of the RGBD camera and the nine-axis sensor, it became possible to improve the accuracy of the original algorithm even using a constant as a weight function. In the future, it is planned to develop an algorithm for the dynamic construction of a weight function, as a result of which an increase in the accuracy of the algorithm is expected.
Provkov_2018_J._Phys.%253A_Conf._Ser._1015_032184.pdf
Количество просмотров:
Вернуться в раздел Параллельные направления