Multi-scale Convolutional Neural Networks for Crowd Counting
This addresses the problem of efficient and accurate crowd counting for surveillance and public safety applications, offering a more practical solution compared to existing multi-column methods.
The paper tackles crowd counting in static images by proposing a multi-scale convolutional neural network (MSCNN) that uses a single-column architecture to handle scale variations, achieving state-of-the-art accuracy and robustness with fewer parameters.
Crowd counting on static images is a challenging problem due to scale variations. Recently deep neural networks have been shown to be effective in this task. However, existing neural-networks-based methods often use the multi-column or multi-network model to extract the scale-relevant features, which is more complicated for optimization and computation wasting. To this end, we propose a novel multi-scale convolutional neural network (MSCNN) for single image crowd counting. Based on the multi-scale blobs, the network is able to generate scale-relevant features for higher crowd counting performances in a single-column architecture, which is both accuracy and cost effective for practical applications. Complemental results show that our method outperforms the state-of-the-art methods on both accuracy and robustness with far less number of parameters.