Fast sparse coding networks for anomaly detection in videos

•Novel methods focus on high-level features rather than frame reconstruction error.•Discriminative Spatial-Temporal Fusion Features for anomaly detection in videos.•Fast Sparse Coding Networks achieve higher accuracy at maximum 10000 lower latency.•Experiments show the superiority of our method in a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Pattern recognition Ročník 107; s. 107515
Hlavní autoři: Wu, Peng, Liu, Jing, Li, Mingming, Sun, Yujia, Shen, Fang
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.11.2020
Témata:
Anomaly detection
Encoding-decoding networks
Sparse coding networks
Spatial-temporal information
Video representation
Sparse coding networks
Encoding-decoding networks
Anomaly detection
Spatial-temporal information
Video representation
ISSN:0031-3203, 1873-5142
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Novel methods focus on high-level features rather than frame reconstruction error.•Discriminative Spatial-Temporal Fusion Features for anomaly detection in videos.•Fast Sparse Coding Networks achieve higher accuracy at maximum 10000 lower latency.•Experiments show the superiority of our method in accuracy and efficiency. The semi-supervised video anomaly detection assumes that only normal video clips are available for training. Therefore, the intuitive idea is either to learn a dictionary by sparse coding or to train encoding-decoding neural networks by minimizing the reconstruction errors. For the former, the optimization of sparse coefficients is extremely time-consuming. For the latter, this manner cannot guarantee that an abnormal data corresponds to a larger reconstruction error due to the strong generalization of neural networks. To remedy their weaknesses and leverage their strengths, we propose a Fast Sparse Coding Network (FSCN) based on High-level Features. First, we propose a two-stream neural network to extract Spatial-Temporal Fusion Features (STFF) in hidden layers. With the STFF at hand, we use a Fast Sparse Coding Network to build a normal dictionary. By leveraging the predictor to produce approximate sparse coefficients, our FSCN generates sparse coefficients within a forward pass, which is simple and computationally efficient. Compared with traditional sparse coding based methods, FSCN is hundreds of or even thousands of times faster at the test stage. Extensive experiments on benchmark datasets demonstrate that our method reaches the state-of-the-art level.11Code will be released at https://github.com/Roc-Ng/FSCN_AnomalyDetection.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2020.107515