Semi-Supervised Multi-View Crowd Counting by Ranking Multi-View Fusion Models

TL;DR

This paper introduces two semi-supervised frameworks for multi-view crowd counting that leverage ranking of model predictions and uncertainties to improve accuracy with limited labeled data.

Contribution

It proposes novel semi-supervised multi-view crowd counting methods based on ranking models by prediction results and uncertainties, addressing data scarcity issues.

Findings

The proposed methods outperform existing semi-supervised counting approaches.

Ranking based on model predictions and uncertainties effectively guides training.

Experiments validate the advantages of the proposed frameworks.

Abstract

Multi-view crowd counting has been proposed to deal with the severe occlusion issue of crowd counting in large and wide scenes. However, due to the difficulty of collecting and annotating multi-view images, the datasets for multi-view counting have a limited number of multi-view frames and scenes. To solve the problem of limited data, one approach is to collect synthetic data to bypass the annotating step, while another is to propose semi- or weakly-supervised or unsupervised methods that demand less multi-view data. In this paper, we propose two semi-supervised multi-view crowd counting frameworks by ranking the multi-view fusion models of different numbers of input views, in terms of the model predictions or the model uncertainties. Specifically, for the first method (vanilla model), we rank the multi-view fusion models' prediction results of different numbers of camera-view inputs, namely, the model's predictions with fewer camera views shall not be larger than the predictions with more camera views. For the second method, we rank the estimated model uncertainties of the multi-view fusion models with a variable number of view inputs, guided by the multi-view fusion models' prediction errors, namely, the model uncertainties with more camera views shall not be larger than those with fewer camera views. These constraints are introduced into the model training in a semi-supervised fashion for multi-view counting with limited labeled data. The experiments demonstrate the advantages of the proposed multi-view model ranking methods compared with other semi-supervised counting methods.