Method and system for generating object 3D point cloud in medical imaging system
A method for generating an object 3D point cloud in a medical imaging system comprising a machine table and a scanning device comprises: extracting a valid 3D point cloud in a valid region where the machine table is located from a global 3D point cloud based on a current height of the machine table and boundary information of the machine table, wherein the global 3D point cloud comprises 3D point clouds of an object and a surrounding environment thereof, and the object 3D point cloud is comprised in the valid 3D point cloud; and removing an environment 3D point cloud of the surrounding environment from the valid 3D point cloud to obtain the object 3D point cloud, wherein the surrounding environment comprises at least part of the machine table. In some embodiments, a moving path of the machine table in the medical imaging system is planned using the object 3D point cloud. In some embodiments, collision prediction of the object is performed in the medical imaging system using the object 3D point cloud.
1. A method for generating an object 3D point cloud in a medical imaging system, wherein the medical imaging system comprises:
a depth camera;
a table for carrying an object; and
a scanning device coupled to the table and the depth camera, the scanning device having a scanning space allowing the table to enter therein,
the method comprising:
generating a global 3D point cloud, wherein the global 3D point cloud includes an 3D point cloud of the object and a surrounding environment thereof;
extracting a valid 3D point cloud in a valid region where the table is located from the global 3D point cloud based on a current height of the table and boundary information of the table obtained from real-time position information from the medical imaging system, wherein a bottom surface of the valid region is a carrying surface of the table, and the object 3D point cloud is comprised in the valid 3D point cloud;
reducing noise from the valid 3D point cloud by deleting points in a noise class; and
removing an environment 3D point cloud of the surrounding environment from the valid 3D point cloud to obtain the object 3D point cloud, wherein the surrounding environment comprises at least part of the table.
2. The method according to claim 1 , wherein the medical imaging system is a computed tomography (CT) system.
3. The method according to claim 1 , wherein the boundary information of the table comprises position information of four corners of the table, and the valid region is rectangular.
4. The method according to claim 1 , wherein a width of the valid region is greater than a maximum width of the scanning space in a width direction of the table.
5. The method according to claim 1 , wherein a length of the valid region in a length direction of the table is greater than a length of the table.
6. The method according to claim 1 , further comprising performing coordinate conversion on at least one of the global 3D point cloud and the boundary information of the table to convert them to the same coordinate system.
7. The method according to claim 6 , wherein the same coordinate system is a coordinate system of the global 3D point cloud itself or a coordinate system of the medical imaging system.
8. The method according to claim 1 , further comprising:
receiving depth image data of the object and the surrounding environment thereof from the depth camera; and
converting the depth image data into the global 3D point cloud through coordinate transformation.
9. The method according to claim 1 , further comprising voxelizing the object 3D point cloud.
10. The method according to claim 1 , wherein the environment 3D point cloud is pre-stored in the medical imaging system or obtained by photographing the surrounding environment using a depth camera before the object is carried on the table.