Deep Convolutional Likelihood Particle Filter for Visual Tracking

• URL: http://arxiv.org/abs/2006.06746v1
• Date: Thu, 11 Jun 2020 19:02:27 GMT
• Title: Deep Convolutional Likelihood Particle Filter for Visual Tracking
• Authors: Reza Jalil Mozhdehi and Henry Medeiros
• Abstract summary: We propose a novel particle filter for convolutional-correlation visual trackers. Our method uses correlation response maps to estimate likelihood distributions. Our framework outperforms state-of-the-art methods.
• Score: 0.7424262881242935
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a novel particle filter for convolutional-correlation visual trackers. Our method uses correlation response maps to estimate likelihood distributions and employs these likelihoods as proposal densities to sample particles. Likelihood distributions are more reliable than proposal densities based on target transition distributions because correlation response maps provide additional information regarding the target's location. Additionally, our particle filter searches for multiple modes in the likelihood distribution, which improves performance in target occlusion scenarios while decreasing computational costs by more efficiently sampling particles. In other challenging scenarios such as those involving motion blur, where only one mode is present but a larger search area may be necessary, our particle filter allows for the variance of the likelihood distribution to increase. We tested our algorithm on the Visual Tracker Benchmark v1.1 (OTB100) and our experimental results demonstrate that our framework outperforms state-of-the-art methods.

Related papers

• Improved off-policy training of diffusion samplers [93.66433483772055]
  We study the problem of training diffusion models to sample from a distribution with an unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods. Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work.
  arXiv  Detail & Related papers  (2024-02-07T18:51:49Z)
• Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models [72.07462371883501]
  We propose emphProjection Regret (PR), an efficient novelty detection method that mitigates the bias of non-semantic information. PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.
  arXiv  Detail & Related papers  (2023-12-05T09:44:47Z)
• Unsupervised Learning of Sampling Distributions for Particle Filters [80.6716888175925]
  We put forward four methods for learning sampling distributions from observed measurements. Experiments demonstrate that learned sampling distributions exhibit better performance than designed, minimum-degeneracy sampling distributions.
  arXiv  Detail & Related papers  (2023-02-02T15:50:21Z)
• Computational Doob's h-transforms for Online Filtering of Discretely Observed Diffusions [65.74069050283998]
  We propose a computational framework to approximate Doob's $h$-transforms. The proposed approach can be orders of magnitude more efficient than state-of-the-art particle filters.
  arXiv  Detail & Related papers  (2022-06-07T15:03:05Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)
• Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking [1.1531505895603305]
  This work proposes a novel framework for visual tracking based on the integration of an iterative particle filter, a deep convolutional neural network, and a correlation filter. We employ a novel strategy to assess the likelihood of the particles after the iterations by applying K-means clustering. Experimental results on two different benchmark datasets show that our tracker performs favorably against state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-07-07T02:44:43Z)
• Differentiable Particle Filters through Conditional Normalizing Flow [6.230706386020833]
  Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. In this paper, we utilize conditional normalizing flows to construct proposal distributions for differentiable particle filters. We demonstrate the performance of the proposed conditional normalizing flow-based differentiable particle filters in a visual tracking task.
  arXiv  Detail & Related papers  (2021-07-01T14:31:27Z)
• Innovative And Additive Outlier Robust Kalman Filtering With A Robust Particle Filter [68.8204255655161]
  We propose CE-BASS, a particle mixture Kalman filter which is robust to both innovative and additive outliers, and able to fully capture multi-modality in the distribution of the hidden state. Furthermore, the particle sampling approach re-samples past states, which enables CE-BASS to handle innovative outliers which are not immediately visible in the observations, such as trend changes.
  arXiv  Detail & Related papers  (2020-07-07T07:11:09Z)
• Multiplicative Gaussian Particle Filter [18.615555573235987]
  We propose a new sampling-based approach for approximate inference in filtering problems. Instead of approximating conditional distributions with a finite set of states, as done in particle filters, our approach approximates the distribution with a weighted sum of functions from a set of continuous functions.
  arXiv  Detail & Related papers  (2020-02-29T09:19:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.