Video Anomaly Detection for Smart Surveillance

@article{Zhu2020VideoAD,
  title={Video Anomaly Detection for Smart Surveillance},
  author={Sijie Zhu and Chen Chen and Waqas Sultani},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.00222}
}
In modern intelligent video surveillance systems, automatic anomaly detection through computer vision analytics plays a pivotal role which not only significantly increases monitoring efficiency but also reduces the burden on live monitoring. Anomalies in videos are broadly defined as events or activities that are unusual and signify irregular behavior. The goal of anomaly detection is to temporally or spatially localize the anomaly events in video sequences. Temporal localization (i.e… 

Visual anomaly detection in video by variational autoencoder

TLDR
This paper has demonstrated comparison between performance of convolutional LSTM versus a variation convolutionAL L STM autoencoder https://github.com/rafapm/CS_230/ and found that variation autoenCoder has better regularization effect.

MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection

TLDR
A multiple instance self-training framework (MIST) to efficiently refine task-specific discriminative representations with only video-level annotations, which performs comparably to or even better than existing supervised and weakly supervised methods.

Grid HTM: Hierarchical Temporal Memory for Anomaly Detection in Videos

TLDR
This paper explores the capabilities of the Hierarchical Temporal Memory (HTM) algorithm to perform anomaly detection in videos, as it has favorable properties such as noise tolerance and online learning which combats concept drift.

Real-Time Multiple Object Visual Tracking for Embedded GPU Systems

TLDR
A system has been designed that extends a joint architecture of tracking and detection by adding a module comprised of appearance-based and movement-based trackers that allow to maintain the identity of the objects of interest for longer periods of time while alleviating the burden of the detector.

Exploring Convolutional Recurrent architectures for anomaly detection in videos: a comparative study

TLDR
With comprehensive quantitative and visual evidence, it is established that the ConvGRU based configurations are the most effective and perform better than the popular ConvLSTM configurations on video anomaly detection tasks, in contrast to what is seen from the literature.

Recent Advances in Video Analytics for Rail Network Surveillance for Security, Trespass and Suicide Prevention—A Survey

Railway networks systems are by design open and accessible to people, but this presents challenges in the prevention of events such as terrorism, trespass, and suicide fatalities. With the rapid

Fine-grained anomaly detection via multi-task self-supervision

TLDR
This work combines both high-scale shape features and low-scale fine features in a multi-task framework to improve fine-grained anomaly detection and outperforms state-of-the-art with up to 31% relative error reduction measured with AUROC on various anomaly detection problems.

A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines

TLDR
A deep learning method to detect invading foreign objects for power transmission line inspection is proposed, based on the regression strategy with oriented bounding boxes to accurately predict spatial location and orientation angle of foreign objects, as well as their categories in cluttered backgrounds.

References

SHOWING 1-10 OF 28 REFERENCES

Future Frame Prediction for Anomaly Detection - A New Baseline

TLDR
This paper proposes to tackle the anomaly detection problem within a video prediction framework by introducing a motion (temporal) constraint in video prediction by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and is the first work that introduces a temporal constraint into the video prediction task.

Street Scene: A new dataset and evaluation protocol for video anomaly detection

TLDR
This paper introduces a large and varied new dataset called Street Scene, as well as two new evaluation criteria that provide a better estimate of how an algorithm will perform in practice.

An anomaly-introduced learning method for abnormal event detection

TLDR
This work proposes an anomaly-introduced learning (AL) method to detect abnormal events, which makes use of abnormal information and prune testing instances with a coarse filter and reduce time cost of computing SRC.

Unsupervised Traffic Accident Detection in First-Person Videos

TLDR
An unsupervised approach for traffic accident detection in first-person (dashboard-mounted camera) videos to detect anomalies by predicting the future locations of traffic participants and then monitoring the prediction accuracy and consistency metrics with three different strategies.

Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video

TLDR
An unsupervised feature learning framework based on object-centric convolutional auto-encoders to encode both motion and appearance information is introduced and a supervised classification approach based on clustering the training samples into normality clusters is proposed.

Anomaly Candidate Identification and Starting Time Estimation of Vehicles from Traffic Videos

TLDR
A novel two-stage framework for anomaly event detection in road traffic based on anomaly candidate identification and starting time estimation of vehicles is proposed.

When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos

TLDR
A new dataset called Detection of Traffic Anomaly (DoTA) is introduced containing 4,677 videos with temporal, spatial, and categorical annotations and a new spatial-temporal area under curve (STAUC) evaluation metric is proposed and used with DoTA.

Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors

TLDR
A novel algorithm for detection of certain types of unusual events based on multiple local monitors which collect low-level statistics that is robust and works well in crowded scenes where tracking-based algorithms are likely to fail.

Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates

  • Jaechul KimK. Grauman
  • Computer Science
    2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
TLDR
Experimental results on surveillance videos show that the space-time MRF model robustly detects abnormal activities both in a local and global sense: not only does it accurately localize the atomic abnormal activities in a crowded video, but at the same time it captures the global-level abnormalities caused by irregular interactions between local activities.

Traffic Anomaly Detection via Perspective Map based on Spatial-temporal Information Matrix

TLDR
This paper proposes an anomaly detection system that includes three modules: background modeling module, perspective detection module, and spatialtemporal matrix discriminating module, which is effective in the Track3 test-set of NVIDIA AI CITY 2019 CHALLENGE.