Fusion of Omnidirectional and PTZ Cameras for Face Detection and Tracking

@article{Iraqui2010FusionOO,
  title={Fusion of Omnidirectional and PTZ Cameras for Face Detection and Tracking},
  author={H. Amine Iraqui and Yohan Dupuis and R{\'e}mi Boutteau and Jean-Yves Ertaud and Xavier Savatier},
  journal={2010 International Conference on Emerging Security Technologies},
  year={2010},
  pages={18-23}
}
  • H. A. Iraqui, Y. Dupuis, X. Savatier
  • Published 6 September 2010
  • Computer Science, Physics
  • 2010 International Conference on Emerging Security Technologies
Many applications for mobile robot authentication require to be able to explore a large field of view with high resolution. The proposed vision system is composed of a catadioptric sensor for full range monitoring and a pan tilt zoom (PTZ) camera leading to an innovative sensor, able to detect and track any moving objects at a higher zoom level. In our application, the catadioptric sensor is calibrated and used to detect and track regions of interest (ROIs) within its 360 degree field of view… 

Face Detection and Recognition based on Fusion of Omnidirectional and PTZ Vision Sensors and Heteregenous Database

TLDR
The compressed sensing (CS) algorithm is used to solve the Small Sample Size (SSS) problem in NOBA face database and some experiments can prove the feasibility and validity of this solution.

Face Detection and Recognition under Heterogeneous Database Based on Fusion of Catadioptric and PTZ Vision Sensors

TLDR
The vision system proposed here is composed of a catadioptric sensor for full range monitoring and a Pan Tilt Zoom camera together forming an innovative sensor, able to detect and track any moving objects at a higher zoom level.

Face Detection & Recognition based on Fusion of Omnidirectional & PTZ Vision Sensors and Heteregenous Database

TLDR
The compressed sensing (CS) algorithm is used to solve the Small Sample Size (SSS) problem in NOBA face database and some experiments can prove the feasibility and validity of this solution.

Control of a PTZ camera in a hybrid vision system

TLDR
A target recognition method designed to cope with the illumination problems, the distortion of the omnidirectional image and the inherent dissimilarity of resolution and color responses between both cameras is proposed.

A direct approach for object detection with catadioptric omnidirectional cameras

TLDR
This paper adopts the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features, and describes how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras.

Car detection with omnidirectional cameras using Haar-like features and cascaded boosting

TLDR
The conventional method of using Haar-like features and cascaded boosting for conventional camera images and panoramic images from omnidirectional ones is applied and it is concluded that spherical profile panoramas are more convenient than cylindricalPanoramas.

A Direct approach for human detection with catadioptric omnidirectional cameras

TLDR
This paper first goes through the conventional sliding window approaches for human detection, then describes how the feature extraction step of the conventional approaches should be modified for a theoretically correct and effective use in omnidirectional cameras.

A direct approach for object detection with omnidirectional cameras

TLDR
Owing to the proposed methods, object detection process can be performed on the omnidirectional images without converting them to panoramic or perspective image.

Face Tracking Techniques in Color Images : A Study and Review

TLDR
Of the face tracking methods used till now, Memory-based Particle Filter method and Stereo methods and Kanade-Lucas-Tomasi and Scale-invariant Feature Transform of Model Based used for face tracking algorithm produces almost 100% results.

OmniDRL: Robust Pedestrian Detection using Deep Reinforcement Learning on Omnidirectional Cameras*

TLDR
A novel and efficient technique for robust pedestrian detection in omnidirectional images that takes advantage of the distortion in the image and avoids the need of pre-processing steps to remove the distortion, which is computationally expensive.

References

SHOWING 1-10 OF 13 REFERENCES

A Flexible Technique for Accurate Omnidirectional Camera Calibration and Structure from Motion

TLDR
Compared with classical techniques, which rely on a specific parametric model of the omnidirectional camera, the proposed procedure is independent of the sensor, easy to use, and flexible.

Towards complete generic camera calibration

  • S. RamalingamP. SturmS. Lodha
  • Mathematics, Physics
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
A complete calibration approach that should in principle be able to handle any camera that can be described by the generic imaging model and if non-central models are more appropriate for certain cameras than central models is considered.

Single View Point Omnidirectional Camera Calibration from Planar Grids

  • Christopher MeiP. Rives
  • Computer Science
    Proceedings 2007 IEEE International Conference on Robotics and Automation
  • 2007
TLDR
This paper presents a flexible approach for calibrating omnidirectional single viewpoint sensors from planar grids based on an exact theoretical projection function to which well identified parameters are added to model real-world errors.

A Theory of Single-Viewpoint Catadioptric Image Formation

TLDR
This paper derives the complete class of single-lens single-mirror catadioptric sensors that have a single viewpoint, and describes all of the solutions in detail, including the degenerate ones, with reference to many of the catadi optric systems that have been proposed in the literature.

A Unifying Theory for Central Panoramic Systems and Practical Applications

TLDR
This paper provides a unifying theory for all central catadioptric systems and shows that all of them are isomorphic to projective mappings from the sphere to a plane with a projection center on the perpendicular to the plane.

Robust Real-Time Face Detection

TLDR
A new image representation called the “Integral Image” is introduced which allows the features used by the detector to be computed very quickly and a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions.

A unifying geometric representation for central projection systems

Conception d'un capteur de stéréovision omnidirectionnelle : architecture, étalonnage et applications à la reconstruction de scènes 3D

Les travaux de these presentes dans ce memoire ont pour objectif la conception et l'evaluation d'un systeme de vision 3D constitue de deux capteurs catadioptriques positionnes verticalement. Afin

Reconstruction tridimensionnelle de l'environnement d'un robot mobile, à partir d'informations de vision omnidirectionnelle, pour la préparation d'interventions. (3D reconstruction of the environment of a mobile robot, using omnidirectionnal vision data, for preparing military operations)

TLDR
Notre principale contribution porte sur le developpement d'un algorithme d'ajustement de faisceaux pour les capteurs stereoscopiques omnidirectionnels qui permet d'obtenir une estimation des deplacements en ne necessitant que des donnees visuelles.

A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES

The standard method for solving least squares problems which lead to non-linear normal equations depends upon a reduction of the residuals to linear form by first order Taylor approximations taken