Multiple Instance-Based Video Anomaly Detection using Deep Temporal Encoding-Decoding

by   Ammar Mansoor Kamoona, et al.

In this paper, we propose a weakly supervised deep temporal encoding-decoding solution for anomaly detection in surveillance videos using multiple instance learning. The proposed approach uses both abnormal and normal video clips during the training phase which is developed in the multiple instance framework where we treat video as a bag and video clips as instances in the bag. Our main contribution lies in the proposed novel approach to consider temporal relations between video instances. We deal with video instances (clips) as a sequential visual data rather than independent instances. We employ a deep temporal and encoder network that is designed to capture spatial-temporal evolution of video instances over time. We also propose a new loss function that is smoother than similar loss functions recently presented in the computer vision literature, and therefore; enjoys faster convergence and improved tolerance to local minima during the training phase. The proposed temporal encoding-decoding approach with modified loss is benchmarked against the state-of-the-art in simulation studies. The results show that the proposed method performs similar to or better than the state-of-the-art solutions for anomaly detection in video surveillance applications.


Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning

Anomaly detection in surveillance videos is a challenging task due to th...

3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos

Abnormal activity detection is one of the most challenging tasks in the ...

Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction

Video anomaly detection is commonly used in many applications such as se...

Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection

Video anomaly detection is recently formulated as a multiple instance le...

Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection

Multiple-instance learning (MIL) provides an effective way to tackle the...

A MIL Approach for Anomaly Detection in Surveillance Videos from Multiple Camera Views

Occlusion and clutter are two scene states that make it difficult to det...

Sharp Multiple Instance Learning for DeepFake Video Detection

With the rapid development of facial manipulation techniques, face forge...

Please sign up or login with your details

Forgot password? Click here to reset