In this paper, the radar target recognition is given by using LDA (linear discriminant algorithm) on angular-diversity RCS (radar cross section). The goal is to enhance the separating ability and then achieve reliable prediction in the recognition of radar targets. Initially, the angular-diversity RCS data from a target are collected to constitute RCS vectors (usually high-dimensional). These RCS vectors are first projected onto a low-dimensional PCA (principal components analysis) space. The elementary radar recognition is performed on the PCA space. However, the separating ability for such an elementary recognition is usually poor. This poor separation of radar target recognition will make the prediction results unreliable. To enhance the separating ability of radar target recognition, the projection features on the PCA space are further projected onto the LDA space and the recognition is performed on the LDA space. Our simulation shows that the separating ability for RCS based recognition of targets is much increased by using the LDA in the radar recognition process. In addition, the use of LDA in the recognition process increases the ability to tolerate noise effects. This study will be helpful in many applications of radar target recognition.
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Physics and Astronomy(all)
- Electrical and Electronic Engineering