SatSAM2 improves satellite video object tracking by integrating Kalman motion priors and a motion state machine into SAM2, outperforming prior methods with a 5.84% AUC gain on OOTB while introducing the MVOT synthetic benchmark.
Samurai: Adapting segment anything model for zero-shot visual tracking with motion-aware memory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors
SatSAM2 improves satellite video object tracking by integrating Kalman motion priors and a motion state machine into SAM2, outperforming prior methods with a 5.84% AUC gain on OOTB while introducing the MVOT synthetic benchmark.