Various embodiments of the present technology generally relate to identification of tumor location. More specifically, some embodiments of the present technology relate automated tracking of fiducial marker clusters in x-ray images for the real-time identification of tumor location and guidance of radiation therapy beams. Some embodiments use processed CBCT projection images, an automated routine of reconstruction, forward-projection, tracking, and stabilization generated static templates of the marker cluster at arbitrary viewing angles. Breathing data can be incorporated into some embodiments, resulting in dynamic templates dependent on both viewing angle and breathing motion. In some embodiments, marker clusters can be tracked using normalized cross correlations between templates (either static or dynamic) and CBCT projection images.