Multiple Hypothesis Tracking Revisited

  title={Multiple Hypothesis Tracking Revisited},
  author={Chanho Kim and Fuxin Li and Arridhana Ciptadi and James M. Rehg},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
This paper revisits the classical multiple hypotheses tracking (MHT) algorithm in a tracking-by-detection framework. The success of MHT largely depends on the ability to maintain a small list of potential hypotheses, which can be facilitated with the accurate object detectors that are currently available. We demonstrate that a classical MHT implementation from the 90's can come surprisingly close to the performance of state-of-the-art methods on standard benchmark datasets. In order to further… 

Figures and Tables from this paper

Enhancing Detection Model for Multiple Hypothesis Tracking

A novel enhancing detection model that included detection-scene analysis and detection-detection analysis was incorporated, which improved the ability to deal with close object hypotheses in crowded scenarios and achieved competitive results with current state-of-the-art trackers.

Multi-object Tracking via End-to-end Tracklet Searching and Ranking

A novel method for optimizing tracklet consistency is proposed, which directly takes the prediction errors into account by introducing an online, end-to-end tracklet search training process and achieves remarkable performance gain from conventional tracklet association baseline.

Long-Term Tracking With Deep Tracklet Association

This paper introduces an iterative clustering method that generates more tracklets while maintaining high confidence and proposes a deep association method for tracklet association, which shows robust performance on avoiding internal identity switch.

Online Multi-Object Tracking with United Siamese Network and Candidate-Refreshing Model

This work proposes a multi-task tracking framework including the United Siamese Network (USN) and Candidate-Refreshing (CR) model, which aims to combine detection candidates with tracking candidates, and compensate for unreliable detection results by scoring and regressing the bounding boxes.

Robust Multi-Object Tracking by Marginal Inference

An efficient approach to compute a marginal probability for each pair of objects in real time which is significantly more stable than the original feature distance is presented and can be applied to the existing trackers to obtain about one point improvement in terms of IDF1 metric.

Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking

This paper solves the problem of simultaneously considering all tracks during memory updating, with only a small spatial overhead, via a novel multi-track pooling module and proposes a training strategy adapted to multi- track pooling which generates hard tracking episodes online.

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

A probabilistic autoregressive motion model is introduced to score tracklet proposals by directly measuring their likelihood, achieved by training the model to learn the underlying distribution of natural tracklets.

Fast Online Tracking With Detection Refinement

This work presents a fast online MOT algorithm by introducing the minimum output sum of squared error filter and introducing an alternative targets hypotheses to reduce the dependence on detections and adaptively refine the object detection boxes.

Non-Markovian Globally Consistent Multi-object Tracking

This paper proposes a non-Markovian approach to imposing global consistency by using behavioral patterns to guide the tracking algorithm, and shows significant improvements both in supervised settings where ground truth is available and behavioral patterns can be learned from it, and in completely unsupervised settings.

Multi-object Tracking with Pre-classified Detection

A novel algorithm is proposed which will first divide the detections into false ones, high uncertainty and low uncertainty ones, and can achieved competitive results with state-of-the-art trackers on some challenging datasets such as MOTChallenge2016.



Joint tracking and segmentation of multiple targets

This work proposes a multi-target tracker that exploits low level image information and associates every (super)-pixel to a specific target or classifies it as background and obtains a video segmentation in addition to the classical bounding-box representation in unconstrained, real-world videos.

Multiple Target Tracking by Learning-Based Hierarchical Association of Detection Responses

The proposed hierarchical association approach to multiple target tracking from a single camera by progressively linking detection responses into longer track fragments outperforms previous state-of-the-art algorithms in terms of tracking accuracy, in particular, considerably reducing fragmentations and identity switches.

The Way They Move: Tracking Multiple Targets with Similar Appearance

We introduce a computationally efficient algorithm for multi-object tracking by detection that addresses four main challenges: appearance similarity among targets, missing data due to targets being

Learning Optimal Parameters For Multi-target Tracking

Surprisingly, with proper parameter learning, the simple data-association model without explicit appearance/motion reasoning is able to outperform many state-of-the-art methods that use far more complex motion features and affinity metric learning.

Enhancing Linear Programming with Motion Modeling for Multi-target Tracking

The minimum-cost network flow approach to multi-target tracking is extended, by incorporating a motion model, allowing the tracker to better cope with long term occlusions and missed detections.

An online learned CRF model for multi-target tracking

  • Bo YangR. Nevatia
  • Computer Science
    2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
The online CRF approach is more powerful at distinguishing spatially close targets with similar appearances, as well as in dealing with camera motions, and an efficient algorithm is introduced for finding an association with low energy cost.

Continuous Energy Minimization for Multitarget Tracking

This work proposes an alternative formulation of multitarget tracking as minimization of a continuous energy that focuses on designing an energy that corresponds to a more complete representation of the problem, rather than one that is amenable to global optimization.

Multiobject tracking as maximum weight independent set

This paper presents a new, polynomial-time MWIS algorithm, and proves that it converges to an optimum, and demonstrates advantages of simultaneously accounting for soft and hard contextual constraints in multitarget tracking.

Multiple Object Tracking Using K-Shortest Paths Optimization

This paper shows that reformulating that step as a constrained flow optimization results in a convex problem and takes advantage of its particular structure to solve it using the k-shortest paths algorithm, which is very fast.

Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera

This paper proposes a novel approach for multiperson tracking-by-detection in a particle filtering framework that detects and tracks a large number of dynamically moving people in complex scenes with occlusions, requires no camera or ground plane calibration, and only makes use of information from the past.