COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation

Viet-Quoc Pham, Tatsuo Kozakaya, Osamu Yamaguchi, Ryuzo Okada; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 3253-3261

Abstract


This paper presents a patch-based approach for crowd density estimation in public scenes. We formulate the problem of estimating density in a structured learning framework applied to random decision forests. Our approach learns the mapping between patch features and relative locations of all objects inside each patch, which contribute to generate the patch density map through Gaussian kernel density estimation. We build the forest in a coarse-to-fine manner with two split node layers, and further propose a crowdedness prior and an effective forest reduction method to improve the estimation accuracy and speed. Moreover, we introduce a semi-automatic training method to learn the estimator for a specific scene. We achieved state-of-the-art results on the public Mall dataset and UCSD dataset, and also proposed two potential applications in traffic counts and scene understanding with promising results.

Related Material


[pdf]
[bibtex]
@InProceedings{Pham_2015_ICCV,
author = {Pham, Viet-Quoc and Kozakaya, Tatsuo and Yamaguchi, Osamu and Okada, Ryuzo},
title = {COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}