Skip to Main content Skip to Navigation
Journal articles

Exploiting Feature Correlations by Brownian Statistics for People Detection and Recognition

Abstract : Characterizing an image region by its feature inter-correlations is a modern trend in computer vision. In this paper, we introduce a new image descriptor that can be seen as a natural extension of a covariance descriptor with the advantage of capturing nonlinear and non-monotone dependencies. Inspired from the recent advances in mathematical statistics of Brownian motion, we can express highly complex structural information in a compact and computationally efficient manner. We show that our Brownian covariance descriptor can capture richer image characteristics than the covariance descriptor. Additionally, a detailed analysis of the Brownian manifold reveals that in opposite to the classical covariance descriptor, the proposed descriptor lies in a relatively flat manifold, which can be treated as a Euclidean. This brings significant boost in the efficiency of the descriptor. The effectiveness and the generality of our approach is validated on two challenging vision tasks, pedestrian classification and person re-identification. The experiments are carried out on multiple datasets achieving promising results.
Complete list of metadata

Cited literature [50 references]  Display  Hide  Download
Contributor : Soumik Mallick Connect in order to contact the contributor
Submitted on : Thursday, July 26, 2018 - 5:22:26 PM
Last modification on : Saturday, June 25, 2022 - 11:31:42 PM
Long-term archiving on: : Saturday, October 27, 2018 - 3:28:36 PM


Files produced by the author(s)


  • HAL Id : hal-01850064, version 1



Slawomir Bak, Marco San Biagio, Ratnesh Kumar, Vittorio Murino, François Bremond. Exploiting Feature Correlations by Brownian Statistics for People Detection and Recognition. IEEE transactions on systems, man, and cybernetics, Institute of Electrical and Electronics Engineers (IEEE), 2016. ⟨hal-01850064⟩



Record views


Files downloads