A Deep One-Class Neural Network for Anomalous Event Detection in Complex Scenes

被引:145
作者
Wu, Peng [1 ]
Liu, Jing [1 ]
Shen, Fang [1 ]
机构
[1] Xidian Univ, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
Anomaly detection; Feature extraction; Neural networks; Training; Event detection; Testing; Optical imaging; deep one-class (DeepOC) classifier; learning representation; neural networks; video surveillance; SUPPORT-VECTOR; REPRESENTATION;
D O I
10.1109/TNNLS.2019.2933554
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
How to build a generic deep one-class (DeepOC) model to solve one-class classification problems for anomaly detection, such as anomalous event detection in complex scenes? The characteristics of existing one-class labels lead to a dilemma: it is hard to directly use a multiple classifier based on deep neural networks to solve one-class classification problems. Therefore, in this article, we propose a novel DeepOC neural network, termed as DeepOC, which can simultaneously learn compact feature representations and train a DeepOC classifier. Only with the given normal samples, we use the stacked convolutional encoder to generate their low-dimensional high-level features and train a one-class classifier to make these features as compact as possible. Meanwhile, for the sake of the correct mapping relation and the feature representations' diversity, we utilize a decoder in order to reconstruct raw samples from these low-dimensional feature representations. This structure is gradually established using an adversarial mechanism during the training stage. This mechanism is the key to our model. It organically combines two seemingly contradictory components and allows them to take advantage of each other, thus making the model robust and effective. Unlike methods that use handcrafted features or those that are separated into two stages (extracting features and training classifiers), DeepOC is a one-stage model using reliable features that are automatically extracted by neural networks. Experiments on various benchmark data sets show that DeepOC is feasible and achieves the state-of-the-art anomaly detection results compared with a dozen existing methods.
引用
收藏
页码:2609 / 2622
页数:14
相关论文
共 58 条
[1]   Robust real-time unusual event detection using multiple fixed-location monitors [J].
Adam, Amit ;
Rivlin, Ehud ;
Shimshoni, Ilan ;
Reinitz, David .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2008, 30 (03) :555-560
[2]  
[Anonymous], 2014, ADV NEURAL INFORM PR
[3]  
[Anonymous], 2014, Comput. Sci.
[4]  
[Anonymous], IEEE T PATTERN ANAL, DOI DOI 10.1109/ICCICCT.2016.7987947
[5]  
[Anonymous], 1961, Adaptive Control Processes: a Guided Tour, DOI DOI 10.1515/9781400874668
[6]  
[Anonymous], 2013, COMPUTER VISION PATT
[7]  
[Anonymous], 2015, INT C MACHINE LEARNI
[8]  
[Anonymous], 2018, ARXIV180105365
[9]  
[Anonymous], 2015, PROC CVPR IEEE
[10]  
[Anonymous], P WINT C APPL COMP V