Robust Multi-Object Tracking by Marginal Inference

• URL: http://arxiv.org/abs/2208.03727v1
• Date: Sun, 7 Aug 2022 14:04:45 GMT
• Title: Robust Multi-Object Tracking by Marginal Inference
• Authors: Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu
• Abstract summary: Multi-object tracking in videos requires to solve a fundamental problem of one-to-one assignment between objects in adjacent frames. We present an efficient approach to compute a marginal probability for each pair of objects in real time. It achieves competitive results on MOT17 and MOT20 benchmarks.
• Score: 92.48078680697311
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-object tracking in videos requires to solve a fundamental problem of one-to-one assignment between objects in adjacent frames. Most methods address the problem by first discarding impossible pairs whose feature distances are larger than a threshold, followed by linking objects using Hungarian algorithm to minimize the overall distance. However, we find that the distribution of the distances computed from Re-ID features may vary significantly for different videos. So there isn't a single optimal threshold which allows us to safely discard impossible pairs. To address the problem, we present an efficient approach to compute a marginal probability for each pair of objects in real time. The marginal probability can be regarded as a normalized distance which is significantly more stable than the original feature distance. As a result, we can use a single threshold for all videos. The approach is general and can be applied to the existing trackers to obtain about one point improvement in terms of IDF1 metric. It achieves competitive results on MOT17 and MOT20 benchmarks. In addition, the computed probability is more interpretable which facilitates subsequent post-processing operations.

Related papers

• Scalable 3D Registration via Truncated Entry-wise Absolute Residuals [65.04922801371363]
  A $3$D registration approach can process more than ten million ($107$) point pairs with over $99%$ random outliers. We call our method TEAR, as it involves minimizing an outlier-robust loss that computes Truncated Entry-wise Absolute Residuals.
  arXiv  Detail & Related papers  (2024-04-01T04:43:39Z)
• BASE: Probably a Better Approach to Multi-Object Tracking [0.0]
  Probabilistic tracking algorithms, which are leading in other fields, are surprisingly absent from the leaderboards. We present BASE, a simple, performant and easily extendible visual tracker, achieving state-of-the-art (SOTA) on MOT17 and MOT20, without using Re-Id.
  arXiv  Detail & Related papers  (2023-09-21T12:58:21Z)
• An Oblivious Stochastic Composite Optimization Algorithm for Eigenvalue Optimization Problems [76.2042837251496]
  We introduce two oblivious mirror descent algorithms based on a complementary composite setting. Remarkably, both algorithms work without prior knowledge of the Lipschitz constant or smoothness of the objective function. We show how to extend our framework to scale and demonstrate the efficiency and robustness of our methods on large scale semidefinite programs.
  arXiv  Detail & Related papers  (2023-06-30T08:34:29Z)
• SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth [84.64121608109087]
  We propose a pseudo-depth estimation method for obtaining the relative depth of targets from 2D images. Secondly, we design a depth cascading matching (DCM) algorithm, which can use the obtained depth information to convert a dense target set into multiple sparse target subsets. By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack.
  arXiv  Detail & Related papers  (2023-06-08T14:36:10Z)
• A Probabilistic Transformation of Distance-Based Outliers [2.1055643409860743]
  We describe a generic transformation of distance-based outlier scores into interpretable, probabilistic estimates. The transformation is ranking-stable and increases the contrast between normal and outlier data points. Our work generalizes to a wide range of distance-based outlier detection methods.
  arXiv  Detail & Related papers  (2023-05-16T14:05:30Z)
• Pseudonorm Approachability and Applications to Regret Minimization [73.54127663296906]
  We convert high-dimensional $ell_infty$-approachability problems to low-dimensional pseudonorm approachability problems. We develop an algorithmic theory of pseudonorm approachability, analogous to previous work on approachability for $ell$ and other norms.
  arXiv  Detail & Related papers  (2023-02-03T03:19:14Z)
• Real Time Detection Free Tracking of Multiple Objects Via Equilibrium Optimizer [0.951828574518325]
  Multiple objects tracking (MOT) is a difficult task, as it usually requires special hardware and higher computation. We present a new framework of MOT by using equilibrium algorithm (EO) and reducing the resolution of the bounding boxes of the objects. Experimental results confirm that EO multi-object tracker achieves satisfying tracking results.
  arXiv  Detail & Related papers  (2022-05-22T06:04:34Z)
• Nearest Neighbor Search Under Uncertainty [19.225091554227948]
  Nearest Neighbor Search (NNS) is a central task in knowledge representation, learning, and reasoning. This paper studies NNS under Uncertainty (NNSU)
  arXiv  Detail & Related papers  (2021-03-08T20:20:01Z)
• A Video Analysis Method on Wanfang Dataset via Deep Neural Network [8.485930905198982]
  We describe the new function for real-time multi-object detection in sports competition and pedestrians flow detection in public based on deep learning. Based on the proposed algorithm, we adopt wanfang sports competition dataset as the main test dataset. Our work also can used for pedestrians flow detection and pedestrian alarm tasks.
  arXiv  Detail & Related papers  (2020-02-28T04:09:53Z)
• Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces [62.35667646858558]
  We introduce the Anchor Energy (AE) and Anchor Wasserstein (AW) distances, which are respectively the energy and Wasserstein distances instantiated on such representations. Our main contribution is to propose a sweep line algorithm to compute AE emphexactly in log-quadratic time, where a naive implementation would be cubic. We show that AE and AW perform well in various experimental settings at a fraction of the computational cost of popular GW approximations.
  arXiv  Detail & Related papers  (2020-02-05T03:09:23Z)

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.