Year: 2017
Type: conference-paper
Abstract: 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.
Authors: Lingke Zeng, Xiangmin Xu, Bolun Cai, Suo Qiu, Tong Zhang
Institution: South China University of Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2586716774