A BACKGROUND MODELLING ALGORITHM BASED ON ENERGY EVALUATION

Detecting moving objects is very important in many application contexts such as people detection, visual surveillance, automatic generation of video effects, and so on. The first and fundamental step of all motion detection algorithms is the background modeling. The goal of the methodology here proposed is to create a background model substantially independent from each hypothesis about the training phase, as the presence of moving persons, moving background objects, and changing (sudden or gradual) light conditions. We propose an unsupervised approach that combines the results of temporal analysis of pixel intensity with a sliding window procedure to preserve the model from the presence of foreground moving objects during the building phase. Moreover, a multilayered approach has been implemented to handle small movements in background objects. The algorithm has been tested in many different contexts, in both indoor and outdoor environments. Finally, it has been tested even on the CAVIAR 2005 dataset.

• Publication year

  2016

• Venue

  International Conference on Computer Vision Theory and Applications

• Publication date

  2016-11-20

• Fields of study

  Computer Science

• Identifiers
  DOI 10.5220/0001373404220427
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Background Subtraction

  2009cited by this paper
• Background modeling and subtraction by codebook construction

  2004cited by this paper
• Detected motion classification with a double-background and a Neighborhood-based difference

  2003cited by this paper
• Background modeling and subtraction of dynamic scenes

  2003cited by this paper
• Segmenting foreground objects from a dynamic textured background via a robust Kalman filter

  2003cited by this paper
• ComMode: an algorithm for video background modeling and object segmentation

  2002cited by this paper
• Advances in Cooperative Multi-Sensor Video Surveillance

  1999cited by this paper
• Wallflower: principles and practice of background maintenance

  1999cited by this paper
• California Partners for Advanced Transit and Highways ( PATH ) UC Berkeley Title : Robust Multiple Car Tracking With Occlusion Reasoning

  1998cited by this paper
• Ghost: a human body part labeling system using silhouettes

  1998cited by this paper
• Pfinder: real-time tracking of the human body

  1996cited by this paper

• No citing papers are available for this paper.