Particle PHD Filter Based Multiple Human Tracking Using Online Group-Structured Dictionary Learning
TL;DR: Experimental results demonstrate the proposed enhanced sequential Monte Carlo probability hypothesis density filter-based multiple human tracking system achieves the best performance amongst state-of-the-art random finite set-based methods, and the second best online tracker ranked on the leaderboard of latest MOT17 challenge.
read more
Abstract: An enhanced sequential Monte Carlo probability hypothesis density (PHD) filter-based multiple human tracking system is presented. The proposed system mainly exploits two concepts: a novel adaptive gating technique and an online group-structured dictionary learning strategy. Conventional PHD filtering methods preset the target birth intensity and the gating threshold for selecting real observations for the PHD update. This often yields inefficiency in false positives and missed detections in a cluttered environment. To address this issue, a measurement-driven mechanism based on a novel adaptive gating method is proposed to adaptively update the gating sizes. This yields an accurate approach to discriminate between survival and residual measurements by reducing the clutter inferences. In addition, online group-structured dictionary learning with a maximum voting method is used to robustly estimate the target birth intensity. It enables the new-born targets to be automatically detected from noisy sensor measurements. To improve the adaptability of our group-structured dictionary to appearance and illumination changes, we employ the simultaneous code word optimization algorithm for the dictionary update stage. Experimental results demonstrate our proposed method achieves the best performance amongst state-of-the-art random finite set-based methods, and the second best online tracker ranked on the leaderboard of latest MOT17 challenge.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Jonathon Luiten,Aljosa Osep,Patrick Dendorfer,Philip H. S. Torr,Andreas Geiger,Laura Leal-Taixé,Bastian Leibe +6 more
TL;DR: This work presents a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers.
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking.
Jonathon Luiten,Aljosa Osep,Patrick Dendorfer,Philip H. S. Torr,Andreas Geiger,Andreas Geiger,Laura Leal-Taixé,Bastian Leibe +7 more
TL;DR: Higher order tracking accuracy (HOTA) as mentioned in this paper is proposed to explicitly balance the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers, which is able to capture important aspects of MOT performance not previously taken into account by established metrics.
Multi-object Tracking with Neural Gating Using Bilinear LSTM
Chanho Kim,Fuxin Li,James M. Rehg +2 more
- 08 Sep 2018
TL;DR: A novel recurrent network model, the Bilinear LSTM, is proposed in order to improve the learning of long-term appearance models via a recurrent network based on intuitions drawn from recursive least squares.
Spatial-Temporal Relation Networks for Multi-Object Tracking
Jiarui Xu,Yue Cao,Zheng Zhang,Han Hu +3 more
- 01 Oct 2019
TL;DR: STRN as mentioned in this paper is a unified framework for similarity measurement based on spatial-temporal relation network which could simultaneously encode various cues and perform reasoning across both spatial and temporal domains, which can be trained in an end-to-end manner.
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
Patrick Dendorfer,Aljosa Osep,Anton Milan,Konrad Schindler,Daniel Cremers,Ian Reid,Stefan Roth,Laura Leal-Taixé +7 more
TL;DR: The MOTChallenge as mentioned in this paper is a benchmark for single-camera multiple object tracking (MOT) which has been widely used in the field of computer vision and has been used to evaluate the performance of object tracking algorithms.
References
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
- 20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Evaluating multiple object tracking performance: the CLEAR MOT metrics
TL;DR: This work introduces two intuitive and general metrics to allow for objective comparison of tracker characteristics, focusing on their precision in estimating object locations, their accuracy in recognizing object configurations and their ability to consistently label objects over time.
Multitarget Bayes filtering via first-order multitarget moments
TL;DR: Recursion Bayes filter equations for the probability hypothesis density are derived that account for multiple sensors, nonconstant probability of detection, Poisson false alarms, and appearance, spawning, and disappearance of targets and it is shown that the PHD is a best-fit approximation of the multitarget posterior in an information-theoretic sense.
2.5K
A Consistent Metric for Performance Evaluation of Multi-Object Filters
TL;DR: This paper outlines the inconsistencies of existing metrics in the context of multi- object miss-distances for performance evaluation, and proposes a new mathematically and intuitively consistent metric that addresses the drawbacks of current multi-object performance evaluation metrics.
The Gaussian Mixture Probability Hypothesis Density Filter
Ba-Ngu Vo,Wing-Kin Ma +1 more
TL;DR: Under linear, Gaussian assumptions on the target dynamics and birth process, the posterior intensity at any time step is a Gaussian mixture and closed-form recursions for propagating the means, covariances, and weights of the constituent Gaussian components of the posteriorintensity are derived.
2.1K