Robust Feature Tracking in Underwater Video Sequences

| This paper proposes a robust feature tracker based on an eecient outlier rejection scheme, suitable for feature tracking in subsea video sequences. We extend the Shi-Tomasi-Kanade scheme by introducing a technique for rejecting spurious features. We employ a simple and ee-cient outlier rejection rule, called X84, and prove that its theoretical assumptions are satissed in the feature tracking scenario. Experiments with synthetic and real subsea sequence connrm that our algorithm locates and discards unreliable features accurately and consistently, and tracks good features reliably over many frames. We also illustrate quantitatively the beneets introduced by the algorithm with the example of fundamental matrix estimation .