期刊
APPLIED SCIENCES-BASEL
卷 9, 期 16, 页码 -出版社
MDPI
DOI: 10.3390/app9163337
关键词
video surveillance system; anomaly detection; unsupervised learning; convolutional auto-encoder; variational auto-encoder
类别
资金
- National Natural Science Foundation of China [61701101, U1713216, U1613214]
- National Key R&D Program of China [2017YFC0821402]
- National Key Robot Project [2017YFB1300900, 2017YFB1301103]
- Fundamental Research Fund for the Central Universities of China [N172603001, N172604004, N172604002, N181602014]
Anomaly detection in crowded scenes is an important and challenging part of the intelligent video surveillance system. As the deep neural networks make success in feature representation, the features extracted by a deep neural network represent the appearance and motion patterns in different scenes more specifically, comparing with the hand-crafted features typically used in the traditional anomaly detection approaches. In this paper, we propose a new baseline framework of anomaly detection for complex surveillance scenes based on a variational auto-encoder with convolution kernels to learn feature representations. Firstly, the raw frames series are provided as input to our variational auto-encoder without any preprocessing to learn the appearance and motion features of the receptive fields. Then, multiple Gaussian models are used to predict the anomaly scores of the corresponding receptive fields. Our proposed two-stage anomaly detection system is evaluated on the video surveillance dataset for a large scene, UCSD pedestrian datasets, and yields competitive performance compared with state-of-the-art methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据