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: 3.63). 09/2011; 21(2):789-801. DOI: 10.1109/TIP.2011.2168414
Source: PubMed


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 Follower
31 Reads
  • Source
    • "To solve the two problems mentioned above, we present a novel stochastic sampling paradigm for abrupt motion tracking. First, we utilize an approximate nearest neighbor field(ANNF) algorithm to compute the importance proposal probabilities, which drive the Markov chain dynamics and achieve tremendous speedup in comparison with previous MCMC methods[17] [18]. Second, we incorporate the approximate nearest neighbor field into a smoothing stochastic approximation Monte Carlo(SSAMC) framework. "
    [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.
    Neurocomputing 10/2014; 165. DOI:10.1016/j.neucom.2015.03.024 · 2.08 Impact Factor
  • Source
    • "The exchange of information between these trackers has been shown to cope with abrupt motion while retaining the number of samples used. In another advancement, an intensively adaptive MCMC (IA-MCMC) sampler [16] has been proposed. Their method further reduces the number of samples required when tracking abrupt motion by performing a two-step sampling scheme; the preliminary sampling step to discover the rough landscape of the proposal distribution (common when there is large motion uncertainty in abrupt motion) and the adaptive sampling step to refine the sampling space towards the promising regions found by the preliminary sampling step. "
    [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. DOI:10.1016/j.ins.2014.01.003 · 4.04 Impact Factor
  • Source
    • "Kwon and Lee [10], combined the Wang-Landau Monte Carlo method with the MCMC method to escape local maxima in a complex target distribution, while searching in a regular grid that divides the image space in a number of equally sized cells. Towards a similar goal, a Stochastic approximation Monte Carlo (SAMC) based tracking algorithm was proposed by [11] to search for the optimal target state in a regular grid. An important ingredient of visual tracking is the motion model. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Visual tracking frameworks have traditionally relied upon a single motion model such as Random Walk, and a fixed, embedded search method like Particle Filter. As a single motion model can't reliably handle various target motion types, the interest toward multiple motion models has grown over the years. The existence of multiple competing hypotheses or predictions by the multiple motion models opens up the possibility of a wider range of search methods. To search for the target in a fixed grid of equal sized cells, an integration of the Wang-Landau method and the Markov Chain Monte Carlo (MCMC) method has recently been introduced. In this paper, we generalize this search method to cells of variable size and location, where the cells are formed around the predictions generated by multiple motion models. The effectiveness of the proposed method is tested by adopting a multiple motion model tracker. Experiments show that the modified tracker has improved accuracy and better consistency over different runs compared to its original, and superior performance over state-of-the-art trackers in challenging video sequences.
    22nd International Conference on Pattern Recognition (ICPR), 2014; 08/2014
Show more

Similar Publications