Tracking objects in low frame rate (LFR) video or with abrupt motion poses two main difficulties which most conventional
tracking methods can hardly handle: 1) poor motion continuity and increased search space and 2) fast appearance variation of target
and more background clutter due to increased search space. In this paper, we address the problem from a view which integrates
conventional tracking and detection and present a temporal probabilistic combination of discriminative observers of different life spans.
Each observer is learned from different ranges of samples, with different subsets of features, to achieve varying levels of
discriminative power at varying costs. An efficient fusion and temporal inference is then done by a cascade particle filter which consists
of multiple stages of importance sampling. Experiments show significantly improved accuracy of the proposed approach in
comparison with existing tracking methods, under the condition of LFR data and abrupt motion of both target and camera.