Abnormal Event Detection in Videos using Spatiotemporal Autoencoder

Chong, Yong Shean; Tay, Yong Haur

doi:10.48550/arxiv.1701.01546

Cited by 5 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, motivated by the observation that Convolutional Neural Networks (CNN) has strong capability to learn spatial features, while Recurrent Neural Network (RNN)and its long short term memory (LSTM) variant have been widely used for sequential data modeling. Thus, by taking both advantages of CNN and RNN, [5][21] leverage a Convolutional LSTMs Auto-Encoder (ConvLSTM-AE) to model normal appearance and motion patterns at the same time, which further boosts the performance of the Conv-AE based solution. In [22], Luo et al propose a temporally coherent sparse coding based method which can map to a stacked RNN framework.…”

Section: Deep Learning Based Anomaly Detectionmentioning

confidence: 99%

Future Frame Prediction for Anomaly Detection - A New Baseline

Luo

Lian

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

1,117

1,029

View full text Add to dashboard Cite

Anomaly detection in videos refers to the identification of events that do not conform to expected behavior. However, almost all existing methods tackle the problem by minimizing the reconstruction errors of training data, which cannot guarantee a larger reconstruction error for an abnormal event. In this paper, we propose to tackle the anomaly detection problem within a video prediction framework. To the best of our knowledge, this is the first work that leverages the difference between a predicted future frame and its ground truth to detect an abnormal event. To predict a future frame with higher quality for normal events, other than the commonly used appearance (spatial) constraints on intensity and gradient, we also introduce a motion (temporal) constraint in video prediction by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and this is the first work that introduces a temporal constraint into the video prediction task. Such spatial and motion constraints facilitate the future frame prediction for normal events, and consequently facilitate to identify those abnormal events that do not conform the expectation. Extensive experiments on both a toy dataset and some publicly available datasets validate the effectiveness of our method in terms of robustness to the uncertainty in normal events and the sensitivity to abnormal events. All codes are released in https://github. com/StevenLiuWen/ano_pred_cvpr2018.We also compare the video prediction network based and Auto-Encoder network based anomaly detection. Here for Auto-Encoder network based anomaly detection, we use the Conv-AE [13] which is the latest work and achieves state-of-the-art performance for anomaly detection. Because of the capacity of deep neural network, Auto-Encoder

show abstract

Section: Deep Learning Based Anomaly Detectionmentioning

confidence: 99%

Future Frame Prediction for Anomaly Detection - A New Baseline

Luo

Lian

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

1,117

1,029

View full text Add to dashboard Cite

show abstract

“…RNN networks were employed for anomaly detection task in different operational setups [52][53][54][55][56][57]. The authors of [52] proposed an architecture of LSTM-based anomaly detector which incorporates both hierarchical approach and multi-step analysis.…”

Section: Recurrent Neural Networkmentioning

confidence: 99%

“…The authors trained the model of the autoencoder on regular data and set a threshold above which the reconstruction error is considered an anomaly. The papers deal with acoustic signals, but such an approach may be efficiently employed in other domain such as videos [57]. Systems based on those principles may be trained in an end-to-end fashion.…”

Section: Recurrent Neural Networkmentioning

confidence: 99%

The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization

Wielgosz

Mertik

Skoczeń

et al. 2018

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

A B S T R A C TThis paper focuses on an examination of an applicability of Recurrent Neural Network models for detecting anomalous behavior of the CERN superconducting magnets. In order to conduct the experiments, the authors designed and implemented an adaptive signal quantization algorithm and a custom Gated Recurrent Unit-based detector and developed a method for the detector parameters selection.Three different datasets were used for testing the detector. Two artificially generated datasets were used to assess the raw performance of the system whereas the dataset intended for real-life experiments and model training was composed of the signals acquired from a new type of magnet, to be used during High-Luminosity Large Hadron Collider project. Several different setups of the developed anomaly detection system were evaluated and compared with state-of-the-art One Class Support Vector Machine (OC-SVM) reference model operating on the same data. The OC-SVM model was equipped with a rich set of feature extractors accounting for a range of the input signal properties.It was determined in the course of the experiments that the detector, along with its supporting design methodology, reaches F1 equal or very close to 1 for almost all test sets. Due to the profile of the data, the setup with the lowest maximum false anomaly length of the detector turned out to perform the best among all five tested configuration schemes of the detection system. The quantization parameters have the biggest impact on the overall performance of the detector with the best values of input/output grid equal to 16 and 8, respectively. The proposed solution of the detection significantly outperformed OC-SVM-based detector in most of the cases, with much more stable performance across all the datasets.

show abstract

“…Reconstruction approaches aim to break down inputs into their common constituent pieces and put them back together to reconstruct the input, minimizing "reconstruction error". [12,5,21,31] are examples of methods that use this approach. In our experience, reconstruction based approaches seem to be naively biased against reconstructing faster motion, for the simple reason that absence of motion is much more common and easier to reconstruct.…”

Section: Reconstruction Approachesmentioning

confidence: 99%

“…The CNN feature maps provide higher level features than raw pixels. The other major theme of deep network approaches is to learn an auto-encoder [12,5] or generative adversarial network [31,21] to learn to reconstruct or predict only normal video frames. Reconstruction error is then used as an anomaly score.…”

Section: Reconstruction Approachesmentioning

confidence: 99%

Learning a distance function with a Siamese network to localize anomalies in videos

Ramachandra¹,

Jones²,

Vatsavai³

2020

Preprint

View full text Add to dashboard Cite

This work introduces a new approach to localize anomalies in surveillance video. The main novelty is the idea of using a Siamese convolutional neural network (CNN) to learn a distance function between a pair of video patches (spatiotemporal regions of video). The learned distance function, which is not specific to the target video, is used to measure the distance between each video patch in the testing video and the video patches found in normal training video. If a testing video patch is not similar to any normal video patch then it must be anomalous. We compare our approach to previously published algorithms using 4 evaluation measures and 3 challenging target benchmark datasets. Experiments show that our approach either surpasses or performs comparably to current state-of-the-art methods.

show abstract

Abnormal Event Detection in Videos using Spatiotemporal Autoencoder

Cited by 5 publications

References 0 publications

Future Frame Prediction for Anomaly Detection - A New Baseline

Future Frame Prediction for Anomaly Detection - A New Baseline

The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization

Learning a distance function with a Siamese network to localize anomalies in videos

Contact Info

Product

Resources

About