Cohort plc’s Chess Dynamics has launched its Deep Embedded Feature Tracking (DEFT) system, an advanced real-time video tracking capability that provides accurate, robust tracking in complex situations.
Using a deep learning approach developed by Vision4ce (a Chess Dynamics brand), DEFT creates comprehensive models of the target, allowing for continuous accurate tracking after occasional occlusion, for example. It provides for improved tracking of difficult targets – an issue not unknown in C-UAS circles – in which traditional algorithms often struggle. The models are continuously fine-tuned so as to enhances user understanding of the target, resulting in precise long-term, robust tracking performance. The technology enhances the company’s AI-driven target detection and tracking capability and integrates with neural network-based object detection and classification of targets, including multi-rotor drones, vessels and land vehicles.
“The increased proliferation of stealthy drones and more flexibly deployed forces has posed an unprecedented threat to security and privacy,” said David Tuddenham, Group Managing Director. “These agile and hard-to-detect devices capitalise on cluttered environments to evade traditional surveillance methods, highlighting the urgent need for innovative technologies to counteract them [DEFT has been developed in response to this growing issue.
For more information: www.chess-dynamics.com
(Image: An “inability to see the wood for the trees” will not longer be a viable excuse for users of DEFT, which readily locates and tracks the UAS in the northeast quadrant against the difficult cluttered background. Credit: Chess Dynamics)
