Motion state estimation method and apparatus

A motion state estimation apparatus of a vehicle, comprising a processor, a memory, and a first sensor, wherein the memory is configured to store program instructions, and the processor is configured to invoke the program instructions to perform the following operations:

• obtaining a plurality of pieces of measurement data by using the first sensor, wherein each of the plurality of pieces of measurement data comprises at least velocity measurement information;
• determining, from the plurality of pieces of measurement data of the first sensor based on measurement data of a second sensor, the measurement data corresponding to one or more target reference objects, including separating the measurement data corresponding to one or more target reference objects from the plurality of pieces of measurement data;
• wherein each target reference object is recognized based on the measurement data of the second sensor;
• obtaining a motion state of the first sensor based on the measurement data corresponding to the one or more target reference objects, wherein the motion state comprises at least a velocity vector of the first sensor;
• wherein a pixel feature of the target reference object is prestored in the second sensor, and the operation further comprise:
• searching the measurement data of the second sensor for a matching pixel feature that matches the prestored pixel feature;
• based on the matching pixel feature being found, determining a location of the target reference object;
• wherein the measurement data corresponding to the one or more target reference objects is separated from the plurality of pieces of measurement data by feature recognition via Hough transform;
• transforming distance measurement data and azimuth measurement data of the first sensor to a Hough transform space to obtain a first parameter and a second parameter of the Hough transform space, wherein the first parameter is obtained by quantizing a result determined based on the distance measurement data, the azimuth measurement data, and the second parameter;
• accumulating counts or weights of the first parameter and the second parameter;
• obtaining parameters corresponding to one or more peaks in the Hough transform space;
• obtaining the measurement data corresponding to the one or more target reference objects based on the parameters corresponding to the one or more peaks;
• and
• controlling the vehicle to perform autonomous driving based on the measurement data corresponding to the one or more target reference objects.

A non-transitory computer readable medium, wherein the non-transitory computer readable medium stores program instructions, and when the program instructions are executed by a processor of a vehicle, the processor is enabled to perform a method of:

• obtaining a plurality of pieces of measurement data by using a first sensor, wherein each of the plurality of pieces of measurement data comprises at least velocity measurement information;
• determining, from the plurality of pieces of measurement data of the first sensor based on measurement data of a second sensor, the measurement data corresponding to one or more target reference objects, including separating the measurement data corresponding to one or more target reference objects from the plurality of pieces of measurement data;
• wherein each target reference object is recognized based on the measurement data of the second sensor;
• obtaining a motion state of the first sensor based on the measurement data corresponding to the one or more target reference objects, wherein the motion state comprises at least a velocity vector of the first sensor;
• wherein a pixel feature of a target reference object is prestored in the second sensor, and the method further comprises:
• searching the measurement data of the second sensor for a matching pixel feature that matches the prestored pixel feature;
• based on the matching pixel feature being found, determining a location of the target reference object;
• wherein the measurement data corresponding to the one or more target reference objects is separated from the plurality of pieces of measurement data by feature recognition via Hough transform;
• transforming distance measurement data and azimuth measurement data of the first sensor to a Hough transform space to obtain a first parameter and a second parameter of the Hough transform space, wherein the first parameter is obtained by quantizing a result determined based on the distance measurement data, the azimuth measurement data, and the second parameter;
• accumulating counts or weights of the first parameter and the second parameter;
• obtaining parameters corresponding to one or more peaks in the Hough transform space;
• obtaining the measurement data corresponding to the one or more target reference objects based on the parameters corresponding to the one or more peaks;
• and
• controlling the vehicle to perform autonomous driving based on the measurement data corresponding to the one or more target reference objects.