Perspective-Guided Convolution Networks for Crowd Counting
This addresses crowd counting in surveillance and public safety, offering a novel method for handling continuous scale variations, though it is incremental in the context of existing CNN-based approaches.
The authors tackled the problem of dramatic intra-scene scale variations in crowd counting due to perspective effects by proposing a perspective-guided convolution network (PGCNet), which improved performance against state-of-the-art methods on four benchmark datasets.
In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i.e. PGCNet), which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect. While most state-of-the-arts adopt multi-scale or multi-column architectures to address such issue, they generally fail in modeling continuous scale variations since only discrete representative scales are considered. PGCNet, on the other hand, utilizes perspective information to guide the spatially variant smoothing of feature maps before feeding them to the successive convolutions. An effective perspective estimation branch is also introduced to PGCNet, which can be trained in either supervised setting or weakly-supervised setting when the branch has been pre-trained. Our PGCNet is single-column with moderate increase in computation, and extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts. Additionally, we also introduce Crowd Surveillance, a large scale dataset for crowd counting that contains 13,000+ high-resolution images with challenging scenarios.