DSPNet: Deep scale purifier network for dense crowd counting

•A novel counting model for dense crowd scene is proposed.•We present a scale purifier module to decrease contextual information loss.•Results clearly show that our method outperforms various state-of-the-art methods.•Cross-scene evaluation verifies the high generalization ability of our model. Crowd counting has produced considerable concern in recent years. However, crowd counting in highly congested scenes is a challenging problem owing to scale variation. To remedy this issue, we propose a novel deep scale purifier network (DSPNet) that can encode multiscale features and reduce the loss of contextual information for dense crowd counting. Our proposed method has two strong points. First, the DSPNet model consists of a frontend and a backend. The frontend is a conventional deep convolutional neural network, while the unified deep neural network backend adopts a “maximal ratio combining” strategy to learn complementary scale information at different levels. The scale purifier module, which improves scale representations, can effectively fuse multiscale features. Second, DSPNet performs the whole RGB image-based inference to facilitate model learning and decrease contextual information loss. Our customized network is end-to-end and has a fully convolutional architecture. We demonstrate the generalization ability of our approach by cross-scene evaluation. Extensive experiments on three publicly available crowd counting benchmarks (i.e., UCF-QNRF, ShanghaiTech, and UCF_CC_50 datasets) show that our DSPNet delivers superior performance against state-of-the-art methods.