Detecting anomalous events in videos by learning deep representations of appearance and motion

By Dan Xu, Yan Yan, Elisa Ricci, Nicu Sebe. Computer Vision and Image Understanding, 2017

464 citations recorded by the source corpus.

Abstract Anomalous event detection is of utmost importance in intelligent video surveillance. Currently, most approaches for the automatic analysis of complex video scenes typically rely on hand-crafted appearance and motion features. However, adopting user defined representations is clearly suboptimal, as it is desirable to learn descriptors specific to the scene of interest. To cope with this need, in this paper we propose Appearance and Motion DeepNet (AMDN), a novel approach based on deep neural networks to automatically learn feature representations. To exploit the complementary information of both appearance and motion patterns, we introduce a novel double fusion framework, combining the benefits of traditional early fusion and late fusion strategies. Specifically, stacked denoising autoencoders are proposed to separately learn both appearance and motion features as well as a joint representation (early fusion). Then, based on the learned features, multiple one-class SVM models are used to predict the anomaly scores of each input. Finally, a novel late fusion strategy is proposed to combine the computed scores and detect abnormal events. The proposed ADMN is extensively evaluated on publicly available video surveillance datasets including UCSD pedestian, Subway, and Train, showing competitive performance with respect to state of the art approaches.

Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e5366a704ffa3b41aacd385f3c087ec3fd566934

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Abnormal event detection in videos using generative adversarial nets (2017, methodology): “[17] proposed to use stacked denoising autoencoders.”
A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction (2021, methodology): “Rather than traditional handcrafted feature based methods [1, 20, 2, 34], a lot of modern deep neural network based methods [11, 45, 50, 31, 25, 30, 8, 36, 38, 47, 43, 24] have been proposed for VAD.”
Learning Memory-Guided Normality for Anomaly Detection (2020, unknown): “9 AMDN [46] 90.”
An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos (2018, methodology): “SDAEs are used to learn representations from a video using both appearance, i.e. raw values, and motion information, i.e. optical ﬂow between consecutive frames [49].”
Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video (2018, methodology): “[36, 37] used Stacked Denoising Auto-Encoders on multi-scale patches.”
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning (2020, methodology): “While the early works [1, 2, 6, 25, 29, 32, 33, 46, 58] on video anomaly detection relied heavily on handcrafted appearance and motion features, the recent literature is abundant in deep learning methods [9, 10, 14, 16, 17, 27, 31, 38, 40, 41, 44, 47, 54, 59, 60].”