Bayesian Model Adaptation for Crowd Counts

The problem of transfer learning is considered in the domain of crowd counting. A solution based on Bayesian model adaptation of Gaussian processes is proposed. This is shown to produce intuitive model updates, which are tractable, and lead to an adapted model (predictive distribution) that accounts for all information in both training and adaptation data. The new adaptation procedure achieves significant gains over previous approaches, based on multi-task learning, while requiring much less computation to deploy. This makes it particularly suited for the problem of expanding the capacity of crowd counting camera networks. A large video dataset for the evaluation of adaptation approaches to crowd counting is also introduced. This contains a number of adaptation tasks, involving information transfer across video collected by 1) a single camera under different scene conditions (different times of the day) and 2) video collected from different cameras. Evaluation of the proposed model adaptation procedure in this dataset shows good performance in realistic operating conditions.

1. Introduction

The problem of crowd counting [4] has recently received significant attention in computer vision. Given video of a crowded environment, the goal is to estimate the density of the crowd, by counting the number of people that it contains. Various methods have shown that the problem is solvable with fairly high accuracy [4], [5], [14], [21], [23]. In fact, state of the art results place the prediction error at around ±1 person per video frame, for crowds with dozens of pedestrians. While this is sufficient for most applications of practical interest, the scalability problem remains open. Most works assume a large annotated training set per camera view. This is not practical for large camera networks, where crowd counting systems are most useful.