Track and Cut: simultaneous tracking and segmentation of multiple objects with graph cuts - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2007

Track and Cut: simultaneous tracking and segmentation of multiple objects with graph cuts

(1) , (1)
1
Aurelie Bugeau
Patrick Pérez
  • Function : Author
  • PersonId : 1022281

Abstract

This paper presents a new method to both track and segment multiple objects in videos using min-cut/max-flow optimizations. We introduce objective functions that combine low-level pixel-wise measures (color, motion), high-level observations obtained via an independent detection module, motion prediction and contrast-sensitive contextual regularization. One novelty is that external observations are used without adding any association step. The observations are image regions (pixel sets) that can be output by any kind of detector. The minimization of these cost functions simultaneously allows "detection-before-track" tracking (track-to-observation assignment and automatic initialization of new tracks) and segmentation of tracked objects. When several tracked objects get mixed up by the detection module (e.g., single foreground detection mask for objects close to each other), a second stage of minimization allows the proper tracking and segmentation of these individual entities despite the observation confusion. Experiments on different type of sequences demonstrate the ability of the method to detect, track and precisely segment persons as they enter and traverse the field of view, even in cases of partial occlusions, temporary grouping and frame dropping.
Fichier principal
Vignette du fichier
RR_suivi.pdf (871.25 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00181865 , version 1 (24-10-2007)
inria-00181865 , version 2 (26-10-2007)
inria-00181865 , version 3 (29-10-2007)

Identifiers

  • HAL Id : inria-00181865 , version 3

Cite

Aurelie Bugeau, Patrick Pérez. Track and Cut: simultaneous tracking and segmentation of multiple objects with graph cuts. [Research Report] RR-6337, INRIA. 2007, pp.23. ⟨inria-00181865v3⟩
279 View
785 Download

Share

Gmail Facebook Twitter LinkedIn More