| HAL-Inria | Publications, software ... of Inria's scientists |
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.
Cited literature [50 references]
https://hal.inria.fr/hal-01850064
Contributor : Soumik Mallick <>
Submitted on : Thursday, July 26, 2018 - 5:22:26 PM
Last modification on : Tuesday, May 25, 2021 - 11:44:01 AM
Long-term archiving on: : Saturday, October 27, 2018 - 3:28:36 PM
Contributor : Soumik Mallick <>
Submitted on : Thursday, July 26, 2018 - 5:22:26 PM
Last modification on : Tuesday, May 25, 2021 - 11:44:01 AM
Long-term archiving on: : Saturday, October 27, 2018 - 3:28:36 PM
File
slawekSMCBrownian2016.pdf
Files produced by the author(s)