Method and apparatus for training trajectory classification model, and electronic device
AssigneeBeijing Baidu Netcom Science Technology Co., Ltd.
InventorsEnyang Bai, Kedi Chen, Miao Zhou, Quan Meng, Wei Wang
Life of this patent
Estimating the term…
Abstract
Embodiments of the present disclosure relate to a method for training a trajectory classification model. The method includes: acquiring trajectory data; computing a trajectory feature of the trajectory data based on a temporal feature and a spatial feature of the trajectory data, the trajectory feature comprising at least one of a curvature or a rotation angle; and training the trajectory feature to obtain the trajectory classification model. Embodiments of the present disclosure further provide an apparatus for training a trajectory classification model, an electronic device, and a computer readable medium.
Claims20
A method for training a trajectory classification model, comprising:
- acquiring trajectory data;
- preprocessing the trajectory data, wherein the preprocessing comprises deleting trajectory data satisfying at least one condition, to obtain preprocessed trajectory data, and the at least one condition comprises:
- a first condition that temporal features of first pieces of trajectory data are identical, but spatial features of the first pieces of trajectory data are different from each other;
- or a second condition that a number of second pieces of trajectory data is smaller than a preset value, and each of the second pieces of trajectory data comprises a spatial feature beyond a geographical range;
- computing a trajectory feature of the trajectory data based on a temporal feature and a spatial feature of the preprocessed trajectory data, the trajectory feature comprising at least one of a curvature or a rotation angle;
- and
- training the trajectory feature to obtain the trajectory classification model.
An apparatus for training a trajectory classification model, comprising:
- at least one processor;
- and
- a non-transitory computer-readable memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
- acquiring trajectory data;
- preprocessing the trajectory data, wherein the preprocessing comprises deleting trajectory data satisfying at least one condition, to obtain preprocessed trajectory data, and the at least one condition comprises:
- a first condition that temporal features of first pieces of trajectory data are identical, but spatial features of the first pieces of trajectory data are different from each other;
- or a second condition that a number of second pieces of trajectory data is smaller than a preset value, and each of the second pieces of trajectory data comprises a spatial feature beyond a geographical range;
- computing a trajectory feature of the trajectory data based on a temporal feature and a spatial feature of the preprocessed trajectory data, the trajectory feature comprising at least one of a curvature or a rotation angle;
- and
- training the trajectory feature to obtain the trajectory classification model.
A non-transitory computer readable medium, storing a computer program thereon, wherein the computer program, when executed by a processor, causes the processor to perform operations, the operations comprising:
- acquiring trajectory data;
- preprocessing the trajectory data, wherein the preprocessing comprises deleting trajectory data satisfying at least one condition, to obtain preprocessed trajectory data, and the at least one condition comprises:
- a first condition that temporal features of first pieces of trajectory data are identical, but spatial features of the first pieces of trajectory data are different from each other;
- or a second condition that a number of second pieces of trajectory data is smaller than a preset value, and each of the second pieces of trajectory data comprises a spatial feature beyond a geographical range;
- computing a trajectory feature of the trajectory data based on a temporal feature and a spatial feature of the preprocessed trajectory data, the trajectory feature comprising at least one of a curvature or a rotation angle;
- and
- training the trajectory feature to obtain the trajectory classification model.
Dependencies are inferred from the claim text.