Astronomy & Space Sciences
Title : | Target identification using machine learning algorithms from MOTR radar data |
Area of research : | Astronomy & Space Sciences |
Focus area : | Machine Learning/AI in Radar Data |
Contact info : | challaravi@shar.gov.in |
Details
Executive Summary : | Target Identification from radar data will be the end product of any radar tracking. Using history of tracked data from known sources as knowledge, identifying characteristics of the target from new detections is the requirement. This requirement can be solved using Machine Learning Algorithms. Multi Object Tracking Radar (MOTR) is an L-Band Active Phased Array Radar designed to track multiple targets. It is a long range skin mode tracking radar capable of tracking 0.25m2 RCS target up to a range of 1000km. MOTR can track more than 10 simultaneous targets using single agile beam. Research Proposal:Radar data consists of Range, Azimuth, Elevation and Signal to Noise Ratio (SNR). From Range and SNR correlation target size can be classified. From SNR variation alone in a single track duration, target nature can be established. Implementation:Using Machine Learning algorithms a model should be trained on radar tracked data (Range, Azimuth, Elevation and SNR). The trained model should identify a target nature(controlled or uncontrolled) and size. Using standard libraries in Python Machine Learning Algorithms have become realizable models. |
Co-PI: | Ch.Ravindra, Satish Dhawan Space Centre- SHAR (SDSC-SHAR), Sriharikota |
Organizations involved
