Real-time refinement method for foreground objects detectors using super fast resolution-free tracking system

Axel Beaugendre, Satoshi Goto

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Moving objects or more generally foreground objects are the simplest objects in the field of computer vision after the pixel. Indeed, a moving object can be defined by 4 integers only, either two pairs of coordinates or a pair of coordinates and the size. In fixed camera scenes, moving objects (or blobs) can be extracted quite easily but the methods to produce them are not able to tell if a blob corresponds to remaining background noise, a single target or if there is an occlusion between many target which are too close together thus creating a single blob resulting from the fusion of all targets. In this paper we propose an novel method to refine moving object detection results in order to get as many blobs as targets on the scene by using a tracking system for additional information. Knowing if a blob is at proximity of a tracker allows us to remove noise blobs, keep the rest and handle occlusions when there are more than one tracker on a blob. The results show that the refinement is an efficient tool to sort good blobs from noise blobs and accurate enough to perform a tracking based on moving objects. The tracking process is a resolution free system able to reach speed such as 20 000 fps even for UHDTV sequences. The refinement process itself is in real time, running at more than 2000 fps in difficult situations. Different tests are presented to show the efficiency of the noise removal and the reality of the independence of the refinement tracking system from the resolution of the videos.

Original languageEnglish
Pages (from-to)520-529
Number of pages10
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE97-A
Issue number2
DOIs
Publication statusPublished - 2014

Fingerprint

Free Resolution
Tracking System
Moving Objects
Computer vision
Refinement
Fusion reactions
Pixels
Cameras
Detector
Detectors
Real-time
Target
Occlusion
Moving Object Detection
Noise Removal
Computer Vision
Sort
Proximity
Fusion
Pixel

Keywords

  • Detection
  • Refinement
  • Tracking
  • UHDTV

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics
  • Signal Processing

Cite this

@article{e44bb4aca1454888b1275636579db522,
title = "Real-time refinement method for foreground objects detectors using super fast resolution-free tracking system",
abstract = "Moving objects or more generally foreground objects are the simplest objects in the field of computer vision after the pixel. Indeed, a moving object can be defined by 4 integers only, either two pairs of coordinates or a pair of coordinates and the size. In fixed camera scenes, moving objects (or blobs) can be extracted quite easily but the methods to produce them are not able to tell if a blob corresponds to remaining background noise, a single target or if there is an occlusion between many target which are too close together thus creating a single blob resulting from the fusion of all targets. In this paper we propose an novel method to refine moving object detection results in order to get as many blobs as targets on the scene by using a tracking system for additional information. Knowing if a blob is at proximity of a tracker allows us to remove noise blobs, keep the rest and handle occlusions when there are more than one tracker on a blob. The results show that the refinement is an efficient tool to sort good blobs from noise blobs and accurate enough to perform a tracking based on moving objects. The tracking process is a resolution free system able to reach speed such as 20 000 fps even for UHDTV sequences. The refinement process itself is in real time, running at more than 2000 fps in difficult situations. Different tests are presented to show the efficiency of the noise removal and the reality of the independence of the refinement tracking system from the resolution of the videos.",
keywords = "Detection, Refinement, Tracking, UHDTV",
author = "Axel Beaugendre and Satoshi Goto",
year = "2014",
doi = "10.1587/transfun.E97.A.520",
language = "English",
volume = "E97-A",
pages = "520--529",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "2",

}

TY - JOUR

T1 - Real-time refinement method for foreground objects detectors using super fast resolution-free tracking system

AU - Beaugendre, Axel

AU - Goto, Satoshi

PY - 2014

Y1 - 2014

N2 - Moving objects or more generally foreground objects are the simplest objects in the field of computer vision after the pixel. Indeed, a moving object can be defined by 4 integers only, either two pairs of coordinates or a pair of coordinates and the size. In fixed camera scenes, moving objects (or blobs) can be extracted quite easily but the methods to produce them are not able to tell if a blob corresponds to remaining background noise, a single target or if there is an occlusion between many target which are too close together thus creating a single blob resulting from the fusion of all targets. In this paper we propose an novel method to refine moving object detection results in order to get as many blobs as targets on the scene by using a tracking system for additional information. Knowing if a blob is at proximity of a tracker allows us to remove noise blobs, keep the rest and handle occlusions when there are more than one tracker on a blob. The results show that the refinement is an efficient tool to sort good blobs from noise blobs and accurate enough to perform a tracking based on moving objects. The tracking process is a resolution free system able to reach speed such as 20 000 fps even for UHDTV sequences. The refinement process itself is in real time, running at more than 2000 fps in difficult situations. Different tests are presented to show the efficiency of the noise removal and the reality of the independence of the refinement tracking system from the resolution of the videos.

AB - Moving objects or more generally foreground objects are the simplest objects in the field of computer vision after the pixel. Indeed, a moving object can be defined by 4 integers only, either two pairs of coordinates or a pair of coordinates and the size. In fixed camera scenes, moving objects (or blobs) can be extracted quite easily but the methods to produce them are not able to tell if a blob corresponds to remaining background noise, a single target or if there is an occlusion between many target which are too close together thus creating a single blob resulting from the fusion of all targets. In this paper we propose an novel method to refine moving object detection results in order to get as many blobs as targets on the scene by using a tracking system for additional information. Knowing if a blob is at proximity of a tracker allows us to remove noise blobs, keep the rest and handle occlusions when there are more than one tracker on a blob. The results show that the refinement is an efficient tool to sort good blobs from noise blobs and accurate enough to perform a tracking based on moving objects. The tracking process is a resolution free system able to reach speed such as 20 000 fps even for UHDTV sequences. The refinement process itself is in real time, running at more than 2000 fps in difficult situations. Different tests are presented to show the efficiency of the noise removal and the reality of the independence of the refinement tracking system from the resolution of the videos.

KW - Detection

KW - Refinement

KW - Tracking

KW - UHDTV

UR - http://www.scopus.com/inward/record.url?scp=84893258664&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893258664&partnerID=8YFLogxK

U2 - 10.1587/transfun.E97.A.520

DO - 10.1587/transfun.E97.A.520

M3 - Article

AN - SCOPUS:84893258664

VL - E97-A

SP - 520

EP - 529

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 2

ER -