A rapid space non-cooperative target recognition method based on dimension reduction feature extraction was proposed to identify the target satellite containing interference information quickly and efficiently in the three-dimensional space. First, K-means clustering was performed on the source point cloud to obtain n clusters of point cloud. Next, valid points that met the requirements were retained according to the target characteristics. Then kd-tree algorithm was used to get the point density of each point, and further, the main features of various clusters were obtained after projecting the n clusters of point cloud based on the point density. Finally, all kinds of point cloud after dimension reduction were matched with a given reference point cloud, which aimed to get rough and precise two-dimensional rotation matrices respectively and corresponding rotation errors. By searching for the minimum rotation error, the cluster of the target could be searched. The source point cloud clustered into 4 and 6 clusters respectively was matched with the given 6 sets of reference point cloud. The result of the experiment shows that the proposed algorithm is not affected by the number of clusters for the point cloud data with interference information, and it can find the target accurately with a 100% recognition rate within 2 seconds.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.