• Corpus ID: 244488191

LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking

  title={LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking},
  author={Duy M. H. Nguyen and Roberto Henschel and Bodo Rosenhahn and Daniel Sonntag and Paul Swoboda},
Multi-Camera Multi-Object Tracking is currently draw-ing attention in the computer vision field due to its supe-rior performance in real-world applications such as video surveillance with crowded scenes or in wide spaces. In this work, we propose a mathematically elegant multi-camera multiple object tracking approach based on a spatial-temporal lifted multicut formulation. Our model utilizes state-of-the-art tracklets produced by single-camera trackers as proposals. As these tracklets may… 
1 Citations
Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
This survey conducts a comprehensive overview with in-depth analysis for embedding methods in MOT from seven different perspectives, including patch-level embedding, single-frameembedding, cross-frame joint embeddedding, correlation embedding and sequential embedding; and cross-track relational embedding.


Joint Discriminative and Generative Learning for Person Re-Identification
This paper proposes a joint learning framework that couples re-id learning and data generation end-to-end and renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets.
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts
This work proposes a generalization of the MP with long-range terms (LMP) and designs and implements two efficient algorithms (primal feasible heuristics) for the MP and LMP which allow us to study instances of both problems w.r.t. the pixel grid graphs of the images in the BSDS-500 benchmark.
Multi-Camera Multi-Target Tracking with Space-Time-View Hyper-graph
A new multi-camera multi-target tracking method based on a space-time-view hyper-graph that encodes higher-order constraints on 3D geometry, appearance, motion continuity, and trajectory smoothness among 2D tracklets within and across different camera views is proposed.
Simple online and realtime tracking with a deep association metric
This paper integrates appearance information to improve the performance of SORT and reduces the number of identity switches, achieving overall competitive performance at high frame rates.
Multi-view People Tracking via Hierarchical Trajectory Composition
This paper proposes a hierarchical composition model and re-formulate multi-view multi-object tracking as a problem of compositional structure optimization and sets of composition criteria, each of which corresponds to one particular cue.
A Bayesian Filter for Multi-View 3D Multi-Object Tracking With Occlusion Handling
The key innovation is a high fidelity yet tractable 3D occlusion model, amenable to optimal Bayesian multi-view multi-object filtering, which seamlessly integrates, into a single Bayesian recursion, the sub-tasks of track management, state estimation, clutter rejection, and occlusions/misdetection handling.
Tracking Objects as Points
Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that
Real-time 3D Deep Multi-Camera Tracking
A novel end-to-end tracking pipeline, Deep Multi-Camera Tracking (DMCT), which achieves reliable real-time multi-camera people tracking and fully unleashes the power of deep neural network to estimate the "ground point" of each person in each color image.
Multi-Target Multi-Camera Tracking by Tracklet-to-Target Assignment
This paper solves the cross-camera tracklet matching problem by TRACklet-to-Target Assignment (TRACTA), and proposes the Restricted Non-negative Matrix Factorization (RNMF) algorithm to compute the optimal assignment solution that meets a set of constraints, which should be in force in practice.
Semi-online Multi-people Tracking by Re-identification
This paper proposes a novel semi-online approach to tracking multiple people in a frame-by-frame manner by exploring the time, space and multi-camera relationship of detection hypotheses in the near future frames, and is the first semi- online approach achieved by re-identification.