Low-Rank and Sparse Based Deep-Fusion Convolutional Neural Network for Crowd Counting. (25th September 2017)

• Record Type: Journal Article
• Authors: Tang, Siqi; Pan, Zhisong; Zhou, Xingyu
• Other Names: Shontz Suzanne M. Academic Editor.
• Is Part Of: Mathematical problems in engineering. Volume 2017(2017)
• Publication Date: 2017-09-25
• Subjects: Engineering mathematics -- Periodicals; 510.2462
• DOI: 10.1155/2017/5046727
• Languages: English
• ISSNs: 1024-123X

Abstract

Abstract : This paper proposes an accurate crowd counting method based on convolutional neural network and low-rank and sparse structure. To this end, we firstly propose an effective deep-fusion convolutional neural network to promote the density map regression accuracy. Furthermore, we figure out that most of the existing CNN based crowd counting methods obtain overall counting by direct integral of estimated density map, which limits the accuracy of counting. Instead of direct integral, we adopt a regression method based on low-rank and sparse penalty to promote accuracy of the projection from density map to global counting. Experiments demonstrate the importance of such regression process on promoting the crowd counting performance. The proposed low-rank and sparse based deep-fusion convolutional neural network (LFCNN) outperforms existing crowd counting methods and achieves the state-of-the-art performance.