Residual spatiotemporal autoencoder for unsupervised video anomaly detection

Kumar, Deepak; Chandrakala, S.; Mohan, C. Krishna

doi:10.1007/s11760-020-01740-1

Cited by 78 publications

(22 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From these clusters, one-class SVM classifier is used to differentiate between normal and abnormal events based on the normality scores. Deepak et al [29] proposed a residual spatio-temporal autoencoder, which is trainable endto-end to carry out the anomaly detection task in surveillance videos. Irregularities are detected using the reconstruction loss, where normal frames are reconstructed with a low reconstruction cost, and the converse is identified as abnormal frames.…”

Section: Related Workmentioning

confidence: 99%

IA-SSLM: Irregularity-Aware Semi-Supervised Deep Learning Model for Analyzing Unusual Events in Crowds

Aljaloud

Ullah

2021

IEEE Access

View full text Add to dashboard Cite

Analyzing unusual events is significantly important for video surveillance to ensure people safety. These events are characterized by irregular patterns that do not conform to the expected behavior in the surveillance scenes. We present a novel irregularity-aware semi-supervised deep learning model (IA-SSLM) for detection of unusual events. While most existing works depend on the availability of large amount of labeled data for training, our proposed method utilizes a semi-supervised deep model to automatically learn feature representations from limited number of labeled data samples. Our method extracts meaningful information from both labeled and unlabeled data during the training stage to improve the performance. For this purpose, we explore the concept of consistency regularization and entropy minimization to output confident predictions on unlabeled data. For experimental analysis, we consider various standard and diverse datasets. The results show that our IA-SSLM method outperforms several reference methods using different performance metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

IA-SSLM: Irregularity-Aware Semi-Supervised Deep Learning Model for Analyzing Unusual Events in Crowds

Aljaloud

Ullah

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…2 Abnormal events that deviate qualitatively from what is considered to be normal. Such as only walking is normal in a scene, the running, falling or loitering is regarded as anomaly [29,152]. alities, g and nature information is extracted from input video data.…”

Section: Examples Of Anomaly Event In Various Contextsmentioning

confidence: 99%

“…Among many studies, abnormal behavior can be classified into the following categories:1 One or more behaviors that are explicitly specified.Such as designating falls as abnormal behavior [68].2 Abnormal events that deviate qualitatively from what is considered to be normal. Such as only walking is normal in a scene, the running, falling or loitering is regarded as anomaly [29,152].3 The events happen with a low frequency (probability). Namely they are nature rare, unexpected, or out-of-the-ordinary [46,70].…”

mentioning

confidence: 99%

Abnormal Human Behavior Detection in Videos: A Review

Sun

Yuan

et al. 2021

ITC

View full text Add to dashboard Cite

Modeling human behavior patterns for detecting the abnormal event has become an important domain in recentyears. A lot of efforts have been made for building smart video surveillance systems with the purpose ofscene analysis and making correct semantic inference from the video moving target. Current approaches havetransferred from rule-based to statistical-based methods with the need of efficient recognition of high-levelactivities. This paper presented not only an update expanding previous related researches, but also a study coveredthe behavior representation and the event modeling. Especially, we provided a new perspective for eventmodeling which divided the methods into the following subcategories: modeling normal event, predictionmodel, query model and deep hybrid model. Finally, we exhibited the available datasets and popular evaluationschemes used for abnormal behavior detection in intelligent video surveillance. More researches will promotethe development of abnormal human behavior detection, e.g. deep generative network, weakly-supervised. It isobviously encouraged and dictated by applications of supervising and monitoring in private and public space.The main purpose of this paper is to widely recognize recent available methods and represent the literature ina way of that brings key challenges into notice.

show abstract

“…The reconstruction error is used as a threshold to detect anomalies because it is expected that the reconstruction error will be lower for the normal data and higher for the abnormal data. We discussed in this section autoencoder models focused on providing spatio-temporal representations [22].…”

Section: Autoencodersmentioning

confidence: 99%

“…We compare the results achieved by our proposed GAN against five different models. More specifically, four supervised methods: a custom 3D CNN, 3D ResNet-34 [19], Mobile Video Networks (MoViNet-A2) [20], and Convolution 3D (C3D) [21]; and one semi-supervised method: an autoencoder model composed of residual blocks, ConvLSTM, and ConvCNN layers, recently proposed in [22].…”

Section: Introductionmentioning

confidence: 99%

Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case

et al. 2021

View full text Add to dashboard Cite

Data-driven methods—particularly machine learning techniques—are expected to play a key role in the headway of Industry 4.0. One increasingly popular application in this context is when anomaly detection is employed to test manufactured goods in assembly lines. In this work, we compare supervised, semi/weakly-supervised, and unsupervised strategies to detect anomalous sequences in video samples which may be indicative of defective televisions assembled in a factory. We compare 3D autoencoders, convolutional neural networks, and generative adversarial networks (GANs) with data collected in a laboratory. Our methodology to simulate anomalies commonly found in TV devices is discussed in this paper. We also propose an approach to generate anomalous sequences similar to those produced by a defective device as part of our GAN approach. Our results show that autoencoders perform poorly when trained with only non-anomalous data—which is important because class imbalance in industrial applications is typically skewed towards the non-anomalous class. However, we show that fine-tuning the GAN is a feasible approach to overcome this problem, achieving results comparable to those of supervised methods.

show abstract

Residual spatiotemporal autoencoder for unsupervised video anomaly detection

Cited by 78 publications

References 32 publications

IA-SSLM: Irregularity-Aware Semi-Supervised Deep Learning Model for Analyzing Unusual Events in Crowds

IA-SSLM: Irregularity-Aware Semi-Supervised Deep Learning Model for Analyzing Unusual Events in Crowds

Abnormal Human Behavior Detection in Videos: A Review

Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case

Contact Info

Product

Resources

About