Towards Reliable Real-Time Person Detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Towards Reliable Real-Time Person Detection

Abstract

We propose a robust real-time person detection system, which aims to serve as solid foundation for developing solutions at an elevated level of reliability. Our belief is that clever handling of input data correlated with efficacious training algorithms are key for obtaining top performance. We introduce a comprehensive training method based on random sampling that compiles optimal classifiers with minimal bias and overfit rate. Building upon recent advances in multi-scale feature computations, our approach attains state-of-the-art accuracy while running at high frame rate.
Fichier principal
Vignette du fichier
VISAPP_CR.pdf (5.27 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00909124 , version 1 (25-11-2013)

Identifiers

  • HAL Id : hal-00909124 , version 1

Cite

Silviu-Tudor Serban, Srinidhi Mukanahallipatna Simha, Vasanth Bathrinarayanan, Etienne Corvee, Francois Bremond. Towards Reliable Real-Time Person Detection. VISAPP - The International Conference on Computer Vision Theory and Applications, Jan 2014, Lisbon, Portugal. ⟨hal-00909124⟩

Collections

INRIA INRIA2
195 View
503 Download

Share

Gmail Facebook Twitter LinkedIn More