A Novel Segmentation Method for Crowded Scenes

Video surveillance is one of the most studied application in Computer Vision. We propose a novel method to identify and track people in a complex environment with stereo cameras. It uses two stereo cameras to deal with occlusions, two different background models that handle shadows and illumination changes and a new segmentation algorithm that is effective in crowded environments. The algorithm is able to work in real time and results demonstrating the effectiveness of the approach are shown.

• Publication year

  2009

• Venue

  International Conference on Computer Vision Theory and Applications

• Publication date

  2009-02-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.5220/0001792604840489
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multi Person Tracking Within Crowded Scenes

  2007cited by this paper
• Multiple Human Objects Tracking in Crowded Scenes

  2006cited by this paper
• A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint

  2006cited by this paper
• Integrating plan-view tracking and color-based person models for multiple people tracking

  2005cited by this paper
• Real-time people localization and tracking through fixed stereo vision

  2005cited by this paper
• A survey on visual surveillance of object motion and behaviors

  2004cited by this paper
• Backpack: detection of people carrying objects using silhouettes

  2001cited by this paper
• Plan-view trajectory estimation with dense stereo background models

  2001cited by this paper
• Learning Patterns of Activity Using Real-Time Tracking

  2000cited by this paper
• Non-parametric Model for Background Subtraction

  2000cited by this paper
• A real-time system for monitoring of cyclists and pedestrians

  1999cited by this paper
• Hydra: multiple people detection and tracking using silhouettes

  1999cited by this paper
• Small Vision Systems: Hardware and Implementation

  1998cited by this paper
• Motion of disturbances: detection and tracking of multi-body non-rigid motion

  1997cited by this paper
• Image Segmentation in Video Sequences: A Probabilistic Approach

  1997cited by this paper

• PLaTHEA: a marker‐less people localization and tracking system for home automation

  2015cites this paper
• Ground Truth Acquisition of Humanoid Soccer Robot Behaviour

  2013cites this paper
• Context-Aware Video Analysis for Infomobility

  2012cites this paper
• Visual Tracking and Data Fusion for Automatic Video Surveillance

  2010cites this paper
• An Adaptive Tracker for Assisted Living

  2009cites this paper