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

Aurelie Bugeau 1 Patrick Pérez 1
1 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
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.
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal.inria.fr/inria-00181865
Contributor : Aurelie Bugeau <>
Submitted on : Monday, October 29, 2007 - 11:17:35 AM
Last modification on : Friday, November 16, 2018 - 1:30:39 AM
Long-term archiving on : Thursday, September 23, 2010 - 4:12:11 PM

Files

RR_suivi.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00181865, version 3

Citation

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⟩

Share

Metrics

Record views

327

Files downloads

362