Abrupt motion tracking via intensively adaptive Markov-chain Monte Carlo sampling.

College of Information Engineering, Capital Normal University, Beijing 100048, China.
IEEE Transactions on Image Processing (Impact Factor: 3.11). 09/2011; 21(2):789-801. DOI: 10.1109/TIP.2011.2168414
Source: PubMed

ABSTRACT The robust tracking of abrupt motion is a challenging task in computer vision due to its large motion uncertainty. While various particle filters and conventional Markov-chain Monte Carlo (MCMC) methods have been proposed for visual tracking, these methods often suffer from the well-known local-trap problem or from poor convergence rate. In this paper, we propose a novel sampling-based tracking scheme for the abrupt motion problem in the Bayesian filtering framework. To effectively handle the local-trap problem, we first introduce the stochastic approximation Monte Carlo (SAMC) sampling method into the Bayesian filter tracking framework, in which the filtering distribution is adaptively estimated as the sampling proceeds, and thus, a good approximation to the target distribution is achieved. In addition, we propose a new MCMC sampler with intensive adaptation to further improve the sampling efficiency, which combines a density-grid-based predictive model with the SAMC sampling, to give a proposal adaptation scheme. The proposed method is effective and computationally efficient in addressing the abrupt motion problem. We compare our approach with several alternative tracking algorithms, and extensive experimental results are presented to demonstrate the effectiveness and the efficiency of the proposed method in dealing with various types of abrupt motions.

1 Bookmark
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Stochastic sampling based trackers have shown good performance for abrupt motion tracking so that they have gained popularity in recent years. However, conventional methods tend to use a two-stage sampling paradigm, in which the search space needs to be uniformly explored with an inefficient preliminary sampling phase. In this paper, we propose a novel sampling-based method in the Bayesian filtering framework to address the problem. Within the framework, nearest neighbor field estimation is utilized to compute the importance proposal probabilities, which guide the Markov chain search towards promising regions and thus enhance the sampling efficiency; given the motion priors, a smoothing stochastic sampling Monte Carlo algorithm is proposed to approximate the posterior distribution through a smoothing weight-updating scheme. Moreover, to track the abrupt and the smooth motions simultaneously, we develop an abrupt-motion detection scheme which can discover the presence of abrupt motions during online tracking. Extensive experiments on challenging image sequences demonstrate the effectiveness and the robustness of our algorithm in handling the abrupt motions.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Conventional tracking solutions are not feasible in handling abrupt motion as they are based on smooth motion assumption or an accurate motion model. Abrupt motion is not subject to motion continuity and smoothness. To assuage this, we deem tracking as an optimisation problem and propose a novel abrupt motion tracker that based on swarm intelligence - the SwaTrack. Unlike existing swarm-based filtering methods, we first of all introduce an optimised swarm-based sampling strategy to tradeoff between the exploration and exploitation of the search space in search for the optimal proposal distribution. Secondly, we propose Dynamic Acceleration Parameters (DAP) allow on the fly tuning of the best mean and variance of the distribution for sampling. Such innovating idea of combining these strategies in an ingenious way in the PSO framework to handle the abrupt motion, which so far no existing works are found. Experimental results in both quantitative and qualitative had shown the effectiveness of the proposed method in tracking abrupt motions.
    Information Sciences 10/2014; 283. · 3.89 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose visual tracking over multiple temporal scales to handle occlusion and non-constant target motion. This is achieved by learning motion models from the target history at different temporal scales and applying those over multiple temporal scales in the future. These motion models are learned online in a computationally inexpen-sive manner. Reliable recovery of tracking after occlusions is achieved by extending the bootstrap particle filter to propagate particles at multiple temporal scales, possibly many frames ahead, guided by these motion models. In terms of the Bayesian tracking, the prior distribution at the current time-step is approximated by a mixture of the most probable modes of several previous posteriors propagated using their respective motion models. This improved and rich prior distribution, formed by the models learned and applied over multiple temporal scales, further makes the proposed method robust to complex target motion through covering relatively large search space with reduced sampling effort. Ex-tensive experiments have been carried out on both publicly available benchmarks and new video sequences. Results reveal that the proposed method successfully handles occlusions and a variety of rapid changes in target motion.
    Asian Conference on Computer Vision; 11/2014