AlexandreAlahi

Contents

Home
Research Projects
Publications
Teaching
Data set
Source Code
CV
Media Coverage


Research fields

Computer Vision
Signal Processing
Machine learning
Robotics
Computational Neuroscience


Research Interests

Sparse approximation
Compressed-sensing
Inverse problems
Real-time vision
Bio-inspired vision
Large-scale vision
Big Visual data

 

Detect And Track Objects Across Any Network of Uncalibrated Non-Overlapping Cameras

- What is the problem?

Most multi-camera systems assume a well structured environment to detect and track objects across cameras. Cameras need to be fixed and calibrated, or only objects within a training data can be detected (e.g. pedestrians only).

- What is our solution?

A master-slave system is presented to detect and track any objects in a network of uncalibrated fixed and mobile cameras. Cameras can have non-overlapping field-of-views. Objects are detected with the mobile cameras (the slaves) given only observations from the fixed
cameras (the masters). No training stage and data are used. Detected objects are correctly tracked across cameras leading to a better understanding of the scene.

A cascade of grids of region descriptors is proposed to describe any object of interest. To lend insight on the addressed problem, most state-of-the-art region descriptors are evaluated given various schemes. The covariance matrix of various features, the histogram of colors, the histogram of oriented gradients, the scale invariant feature transform (SIFT), the speeded up robust features (SURF) descriptors, and the color interest points [1] are evaluated. A sparse scan of the cameras’image plane is also presented to reduce the search space of the localization process, approaching nearly real-time performance.

- Why is our solution proposed?

The proposed approach outperforms existing works such as scale invariant feature transform (SIFT), or the speeded-up robust features (SURF). The approach is robust to some changes in illumination, viewpoint, color distribution, image quality, and object deformation. Objects with partial occlusion are also detected and tracked.


Related publications:

Alexandre Alahi, Pierre Vandergheynst, Michel Bierlaire, and Murat Kunt, Cascade of Descriptors to Detect and Track Objects Across Any Network of Cameras, submitted to Computer Vision and Image Understanding Journal.
[ detailed record ] [ bibtex ]

A. Alahi, M. Bierlaire and M. Kunt, Object Detection and Matching with Mobile Cameras Collaborating with Fixed Cameras, The 10th European Conference on Computer Vision, 2008. [ detailed record ] [ bibtex ]

A. Alahi, P. Vandergheynst, M. Bierlaire and M. Kunt, Object Detection and Matching in a Mixed Network of Fixed and Mobile Cameras, The ACM International Conference on Multimedia, 2008. [ detailed record ] [ bibtex ]

A. Alahi, D. Marimon, M. Bierlaire and M. Kunt, A Master-Slave Approach for Object Detection and Matching with Fixed and Mobile Cameras, 15th IEEE International Conference on Image Processing, 2008. [ detailed record ] [ bibtex ]

   
   
 
top

© alahi {at} stanford.edu
updated: January 2015

Follow me on

Alahi on ScholarAlahi on LinkedinAlahi on Twitter

 

Schools Studied


Stanford


Ecole Polytechnique Fédérale de Lausanne


Labs Worked

Vision lab at Stanford

LTS2

Transpor


Companies Worked

VisioSafe