• Corpus ID: 1605557

A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects

  title={A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects},
  author={Margret Keuper and Siyu Tang and Zhongjie Yu and Bjoern Andres and Thomas Brox and Bernt Schiele},
Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion trajectory segmentation and multi-target tracking scenarios. Both tasks benefit from decomposing a graphical model into an optimal number of connected components based on attractive and repulsive pairwise terms. The two tasks are formulated on different levels of granularity and, accordingly, leverage mostly local information for motion segmentation and mostly high-level information for… 

Figures and Tables from this paper

A Framework to Combine Multi-Object Video Segmentation and Tracking

  • S. NadeemA. RahmanA. Butt
  • Computer Science
    2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
  • 2017
In this framework, the multi-object tracking and segmentation modules initially produce results on the authors' dataset independently, but are jointly processed and updated to improve the accuracy of both the tracking and the segmentation results.

Fusion of Head and Full-Body Detectors for Multi-object Tracking

This work demonstrates how to fuse two detectors into a tracking system using the Frank-Wolfe algorithm, and proposes to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program.

Online Multi-Object Tracking Using Joint Domain Information in Traffic Scenarios

A novel tracking method that solves the problem of visual tracking of multiple objects by put together information from both enlarged structural and temporal domain by putting together the heterogeneous domain information, which exhibits an improved state-of-the-art performance on standard benchmarks.

Exploit the Connectivity: Multi-Object Tracking with TrackletNet

This paper proposes an innovative and effective tracking method called TrackletNet Tracker (TNT) that combines temporal and appearance information together as a unified framework and achieves promising results on MOT16 and MOT17 benchmark datasets compared with other state-of-the-art methods.

Efficient Multi-Object Tracking by Strong Associations on Temporal Window

A method to combine bounding boxes extracted from multiple CNNs-based detections as a light and accurate alternative to confidence-based detection methods such as non-maximum suppression and clustering approaches predicting a single bounding box is introduced.

A Two-Stage Minimum Cost Multicut Approach to Self-supervised Multiple Person Tracking

This work presents a selfsupervised multiple object tracking approach based on visual features and minimum cost lifted multicuts that can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features can be extracted.

Simultaneous Trajectory Association and Clustering for Motion Segmentation

This letter proposes an alternating optimization strategy to improve the association and clustering in each iteration of the MSTAC framework and introduces a tensor-based multidimensional assignment method with high-order motion context information and a minimum cost multicut-based trajectory clustering method.

Training Algorithms for Multiple Object Tracking

This thesis proposes a model that tracks both types of objects simultaneously, while respecting the physical laws of ball motion when in free fall, and interaction constraints that appear when players are in the possession of the ball.

Two is a crowd: tracking relations in videos

This paper proposes a plug-in Relation Encoding Module (REM), which allows for tracking severely or even fully occluded objects by utilizing relational cues and aims to employ heavy and persistent overlap with the partner rather than rejecting that information.

Online Multi-Object Tracking With Instance-Aware Tracker and Dynamic Model Refreshment

This paper proposes an instance-aware tracker to integrate SOT techniques for MOT by encoding awareness both within and between target models, and considers response maps from all target models and assigns spatial locations exclusively to optimize the overall accuracy.

Motion Trajectory Segmentation via Minimum Cost Multicuts

This paper provides a method to create a long-term point trajectory graph with attractive and repulsive binary terms and outperform state-of-the-art methods based on spectral clustering on the FBMS-59 dataset and on the motion subtask of the VSB100 dataset.

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.

Perspective Motion Segmentation via Collaborative Clustering

This paper first formulates the 3-D motion segmentation from two perspective views as a subspace clustering problem, utilizing the epipolar constraint of an image pair, and proposes an over-segment and merge approach, where the merging step is based on the property of the ell_1-norm of the mutual sparse representation of two over-Segmented groups.

Level-set person segmentation and tracking with multi-region appearance models and top-down shape information

This paper proposes a localized appearance model that uses additional level-sets in order to enforce a hierarchical subdivision of the object shape into multiple connected regions with distinct appearance models and a novel mechanism to include detailed object shape information in the form of a per-pixel figure/ground probability map obtained from an object detection process.

Robust Trajectory Clustering for Motion Segmentation

This paper uses the Discrete Cosine Transform bases as a temporal smoothness constraint on trajectory projection to ensure the validity of resulting components to repair pathological trajectories, and proposes a two-stage clustering strategy that first performs foreground-background separation then segments remaining foreground trajectories.

Detection free tracking: Exploiting motion and topology for segmenting and tracking under entanglement

A detection-free system for segmenting multiple interacting and deforming people in a video by forming video segmentation as graph partitioning in the trajectory domain and incorporating object connectedness constraints into trajectory weight matrix based on topology of foreground.

Robust Motion Segmentation with Unknown Correspondences

This paper introduces an approach to performing motion segmentation without any prior knowledge of point correspondences in terms of Partial Permutation Matrices (PPMs) and aims to match feature descriptors while simultaneously encouraging point trajectories to satisfy subspace constraints.

Multi-scale Clustering of Frame-to-Frame Correspondences for Motion Segmentation

We present an approach for motion segmentation using independently detected keypoints instead of commonly used tracklets or trajectories. This allows us to establish correspondences over non-

Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor

  • Wongun Choi
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
A novel Aggregated Local Flow Descriptor (ALFD) that encodes the relative motion pattern between a pair of temporally distant detections using long term interest point trajectories (IPTs) and ablative analysis verifies the superiority of the ALFD metric over the other conventional affinity metrics.

Discrete-continuous optimization for multi-target tracking

This paper forms multi-target tracking as a discrete-continuous optimization problem that handles each aspect in its natural domain and allows leveraging powerful methods for multi-model fitting and demonstrates the accuracy and robustness of this approach with state-of-the-art performance on several standard datasets.