Real-world Anomaly Detection in Surveillance Videos

CVPR 2018  ·  Waqas Sultani, Chen Chen, Mubarak Shah ·

Surveillance videos are able to capture a variety of realistic anomalies. In this paper, we propose to learn anomalies by exploiting both normal and anomalous videos. To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i.e. the training labels (anomalous or normal) are at video-level instead of clip-level. In our approach, we consider normal and anomalous videos as bags and video segments as instances in multiple instance learning (MIL), and automatically learn a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments. Furthermore, we introduce sparsity and temporal smoothness constraints in the ranking loss function to better localize anomaly during training. We also introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as fighting, road accident, burglary, robbery, etc. as well as normal activities. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Our experimental results show that our MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches. We provide the results of several recent deep learning baselines on anomalous activity recognition. The low recognition performance of these baselines reveals that our dataset is very challenging and opens more opportunities for future work. The dataset is available at: https://webpages.uncc.edu/cchen62/dataset.html

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Introduced in the Paper:

UCF-Crime

Used in the Paper:

UBnormal UBI-Fights
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Abnormal Event Detection In Video UBI-Fights Sultani et al. AUC 0.892 # 2
Decidability 0.804 # 2
EER 0.186 # 2
Semi-supervised Anomaly Detection UBI-Fights Sultani et al. AUC 0.787 # 3
Decidability 0.738 # 3
EER 0.294 # 3
Anomaly Detection UBnormal MIL AUC 50.3% # 14
RBDC 0.002 # 4
TBDC 0.001 # 4
Anomaly Detection In Surveillance Videos UCF-Crime Sultani et al. ROC AUC 75.41 # 15
Decidability 0.613 # 2
EER 0.353 # 2

Methods


No methods listed for this paper. Add relevant methods here