Feature Mining for Localised Crowd Counting

TLDR

Existing regression-based crowd counting methods either use a single global model or many separate regressors for local density estimation. The study introduces a single multi-output regression model that estimates crowd counts in spatially localized regions, aiming to replace numerous separate regressors and improve scalability. The model learns a functional mapping from low-level features to multi-dimensional structured outputs, automatically discovering feature importance for counting at different spatial locations. Evaluations on a standard benchmark and a new challenging dataset show the approach’s effectiveness.

Abstract

This paper presents a multi-output regression model for crowd counting in public scenes. Existing counting by regression methods either learn a single model for global counting, or train a large number of separate regressors for localised density estimation. In contrast, our single regression model based approach is able to estimate people count in spatially localised regions and is more scalable without the need for training a large number of regressors proportional to the number of local regions. In particular, the proposed model automatically learns the functional mapping between interdependent low-level features and multi-dimensional structured outputs. The model is able to discover the inherent importance of different features for people counting at different spatial locations. Extensive evaluations on an existing crowd analysis benchmark dataset and a new more challenging dataset demonstrate the effectiveness of our approach.