Skip to Main content Skip to Navigation
Conference papers

Optimized Cascade of Classifiers for People Detection Using Covariance Features

Abstract : People detection on static images and video sequences is a critical task in many computer vision applications, like image retrieval and video surveillance. It is also one of most challenging task due to the large number of possible situations, including variations in people appearance and poses. The proposed approach optimizes an existing approach based on classification on Riemannian manifolds using covariance matrices in a boosting scheme, making training and detection faster while maintaining equivalent performances. This optimisation is achieved by clustering negative samples before training, providing a smaller number of cascade levels and less weak classifiers in most levels in comparison with the original approach. Our work was evaluated and validated on INRIA Person dataset.
Document type :
Conference papers
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-00794369
Contributor : Malik Souded <>
Submitted on : Monday, February 25, 2013 - 4:38:03 PM
Last modification on : Thursday, March 5, 2020 - 5:34:26 PM
Long-term archiving on: : Sunday, May 26, 2013 - 8:35:06 AM

File

VISAPP_2013_279_CR.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00794369, version 1

Collections

Citation

Malik Souded, François Bremond. Optimized Cascade of Classifiers for People Detection Using Covariance Features. International Conference on Computer Vision Theory and Applications (VISAPP), Feb 2013, Barcelona, Spain. ⟨hal-00794369⟩

Share

Metrics

Record views

395

Files downloads

400