Deep Learning for Video Anomaly Detection: A Review
Authors:
- Peng WuPWPeng Wu
- Chengyu PanCPChengyu Pan
- Yuting YanYYYuting Yan
- Guansong PangGPGuansong Pang
- Peng WangPWPeng Wang
- Yanning ZhangYZYanning Zhang
Preprint
Abstract
Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. As a long-standing task in the field of computer vision, VAD has witnessed much good progress. In the era of deep learning, with the explosion of architectures of continuously growing capability and capacity, a great variety of deep learning based methods are constantly emerging for the VAD task, greatly improving the generalization ability of detection algorithms and broadening the application scenarios. Therefore, such a multitude of methods and a large body of literature make a comprehensive survey a pressing necessity. In this paper, we present an extensive and comprehensive research review, covering the spectrum of five different categories, namely, semi-supervised, weakly supervised, fully supervised, unsupervised and open-set supervised VAD, and we also delve into the latest VAD works based on pre-trained large models, remedying the limitations of past reviews in terms of only focusing on semi-supervised VAD and small model based methods. For the VAD task with different levels of supervision, we construct a well-organized taxonomy, profoundly discuss the characteristics of different types of methods, and show their performance comparisons. In addition, this review involves the public datasets, open-source codes, and evaluation metrics covering all the aforementioned VAD tasks. Finally, we provide several important research directions for the VAD community.Keywords
All Related Versions
This publication has 64 references indexed in Scilit:
- Learning weakly supervised audio-visual violence detection in hyperbolic spaceImage and Vision Computing, 2024
- Stochastic video normality network for abnormal event detection in surveillance videosKnowledge-Based Systems, 2023
- SSMTL++: Revisiting self-supervised multi-task learning for video anomaly detectionComputer Vision and Image Understanding, 2023
- Anomaly detection in surveillance videos: a thematic taxonomy of deep models, review and performance analysisArtificial Intelligence Review, 2022
- Human-related anomalous event detection via spatial-temporal graph convolutional autoencoder with embedded long short-term memory networkNeurocomputing, 2022
- Weakly-supervised anomaly detection in video surveillance via graph convolutional label noise cleaningNeurocomputing, 2022
- Normal graph: Spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detectionNeurocomputing, 2021
- A comprehensive review on deep learning-based methods for video anomaly detectionImage and Vision Computing, 2021
- Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenesComputer Vision and Image Understanding, 2018
- Detecting anomalous events in videos by learning deep representations of appearance and motionComputer Vision and Image Understanding, 2017