Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies

Pourreza, Masoud; Salehi, Mohammadreza; Sabokrou, Mohammad

doi:10.48550/arxiv.2103.10502

Cited by 5 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The noises of intensity-based features can be reduced by extracting the features describing human skeletons and motion instead of pixels. By levering a novel structure, our approach achieves advantages over RNNs and improves understanding of the global scenes in contrast to the coarse-grained STGCNN [5], [70]. As expected, anomalous events about humans can be correctly detected in different scenes in the ShanghaiTech dataset, as shown in Fig.…”

Section: B Evaluation 1) Comparisons With Existing Methods On Accuracysupporting

confidence: 52%

“…Table I lists the comparison between the proposed HST-GCNN model and the latest state-of-the-art methods using ROC AUC. The ten methods are Frame-Pred [1], MPED-RNN [2], w/Mem [67], ST-GCAE [68], Multi-timescale [9], PoseCVAE [60], LSA [69], Ano-Graph [70], AnomalyNet [71], and Normal Graph [5], some of them integrate a model focusing on appearance and motion with others dealing with the trajectories of human skeletons. From experiments, we can conclude that HSTGCNN outperforms the ten methods mentioned above on four public datasets, including Human-Related (HR) and original datasets.…”

Section: B Evaluation 1) Comparisons With Existing Methods On Accuracymentioning

confidence: 99%

See 1 more Smart Citation

A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos

Zeng,

Jiang,

Ding

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep learning models have been widely used for anomaly detection in surveillance videos. Typical models are equipped with the capability to reconstruct normal videos and evaluate the reconstruction errors on anomalous videos to indicate the extent of abnormalities. However, existing approaches suffer from two disadvantages. Firstly, they can only encode the movements of each identity independently, without considering the interactions among identities which may also indicate anomalies. Secondly, they leverage inflexible models whose structures are fixed under different scenes, this configuration disables the understanding of scenes. In this paper, we propose a Hierarchical Spatio-Temporal Graph Convolutional Neural Network (HST-GCNN) to address these problems, the HSTGCNN is composed of multiple branches that correspond to different levels of graph representations. High-level graph representations encode the trajectories of people and the interactions among multiple identities while low-level graph representations encode the local body postures of each person. Furthermore, we propose to weightedly combine multiple branches that are better at different scenes. An improvement over single-level graph representations is achieved in this way. An understanding of scenes is achieved and serves anomaly detection. High-level graph representations are assigned higher weights to encode moving speed and directions of people in low-resolution videos while low-level graph representations are assigned higher weights to encode human skeletons in high-resolution videos. Experimental results show that the proposed HSTGCNN significantly outperforms current state-ofthe-art models on four benchmark datasets (UCSD Pedestrian, ShanghaiTech, CUHK Avenue and IITB-Corridor) by using much less learnable parameters.

show abstract

Section: B Evaluation 1) Comparisons With Existing Methods On Accuracysupporting

confidence: 52%

Section: B Evaluation 1) Comparisons With Existing Methods On Accuracymentioning

confidence: 99%

A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos

Zeng,

Jiang,

Ding

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other hand, the latter methods explicitly combine the images or regions with their relationships as the contexts to understand and discover diverse image-level or region-level anomalies, such as video surveillance [ 1 , 2 ] and human monitoring [ 7 , 8 , 9 ]. Among such works, several approaches [ 9 , 15 , 16 , 27 , 28 ] consider the regions and their relations in the visual perspective for region anomaly detection, while our previous methods [ 7 , 8 ] additionally adopt deep-captioning models, such as DenseCap [ 17 ], to obtain region captions as the semantic information for the task. Sun et al [ 27 ] proposed a Spatio-Temporal Graph (STG) to represent spatio-temporal relations among objects to bridge the gap between an anomaly and its context.…”

Section: Related Workmentioning

confidence: 99%

“…Sun et al [ 27 ] proposed a Spatio-Temporal Graph (STG) to represent spatio-temporal relations among objects to bridge the gap between an anomaly and its context. Similarly, Ano-Graph [ 28 ] detects video anomalies by modeling spatio-temporal interactions among objects via self-supervised learning. Moreover, Spatial-Temporal Graph-based Convolutional Neural Networks (STGCNs) [ 13 ] construct a spatial similarity graph and a temporal consistency graph with a self-attention mechanism to model the correlations of video clips for video anomaly detection.…”

Section: Related Workmentioning

confidence: 99%

Region Anomaly Detection via Spatial and Semantic Attributed Graph in Human Monitoring

Zhang

Fadjrimiratno

Suzuki

2023

Sensors

View full text Add to dashboard Cite

This paper proposes a graph-based deep framework for detecting anomalous image regions in human monitoring. The most relevant previous methods, which adopt deep models to obtain salient regions with captions, focus on discovering anomalous single regions and anomalous region pairs. However, they cannot detect an anomaly involving more than two regions and have deficiencies in capturing interactions among humans and objects scattered in multiple regions. For instance, the region of a man making a phone call is normal when it is located close to a kitchen sink and a soap bottle, as they are in a resting area, but abnormal when close to a bookshelf and a notebook PC, as they are in a working area. To overcome this limitation, we propose a spatial and semantic attributed graph and develop a Spatial and Semantic Graph Auto-Encoder (SSGAE). Specifically, the proposed graph models the “context” of a region in an image by considering other regions with spatial relations, e.g., a man sitting on a chair is adjacent to a white desk, as well as other region captions with high semantic similarities, e.g., “a man in a kitchen” is semantically similar to “a white chair in the kitchen”. In this way, a region and its context are represented by a node and its neighbors, respectively, in the spatial and semantic attributed graph. Subsequently, SSGAE is devised to reconstruct the proposed graph to detect abnormal nodes. Extensive experimental results indicate that the AUC scores of SSGAE improve from 0.79 to 0.83, 0.83 to 0.87, and 0.91 to 0.93 compared with the best baselines on three real-world datasets.

show abstract

“…After obtaining this distance, we determine whether the video is normal or not by verifying that the distance is greater than some threshold. This approach can be viewed as a simplified version of [19,20]. As official implementations of these methods were not available during this study, we are unable to provide a comparison.…”

Section: Image Features-based Admentioning

confidence: 99%

Approaches Toward Physical and General Video Anomaly Detection

Kart¹,

Cohen²

2021

Preprint

View full text Add to dashboard Cite

In recent years, many works have addressed the problem of finding never-seen-before anomalies in videos. Yet, most work has been focused on detecting anomalous frames in surveillance videos taken from security cameras. Meanwhile, the task of anomaly detection (AD) in videos exhibiting anomalous mechanical behavior, has been mostly overlooked. Anomaly detection in such videos is both of academic and practical interest, as they may enable automatic detection of malfunctions in many manufacturing, maintenance, and real-life settings. To assess the potential of the different approaches to detect such anomalies, we evaluate two simple baseline approaches: (i) Temporal-pooled image AD techniques. (ii) Density estimation of videos represented with features pretrained for video-classification.Development of such methods calls for new benchmarks to allow evaluation of different possible approaches. We introduce the Physical Anomalous Trajectory or Motion (PHANTOM) dataset 1 , which contains six different video classes. Each class consists of normal and anomalous videos. The classes differ in the presented phenomena, the normal class variability, and the kind of anomalies in the videos. We also suggest an even harder benchmark where anomalous activities should be spotted on highly variable scenes.

show abstract

Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies

Cited by 5 publications

References 0 publications

A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos

A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos

Region Anomaly Detection via Spatial and Semantic Attributed Graph in Human Monitoring

Approaches Toward Physical and General Video Anomaly Detection

Contact Info

Product

Resources

About