Detection of Global and Local Motion Changes in Human Crowds

Almeida, Igor Rodrigues de; Cassol, Vinícius Jurinic; Badler, Norman I.; Musse, Soraia Raupp; Jung, Cláudio Rosito

doi:10.1109/tcsvt.2016.2596199

Cited by 24 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the wide use of video surveillance systems, the conventional manual analysis for labelling abnormal events in the amount of video data captured from crowd surveillance and public place monitoring is time-consuming and inefficient. Therefore, an intelligent surveillance system that can recognize and detect anomalies is urgently needed and has been a hotspot of computer vision researches and applications [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Anomaly Detection System for Crowded Scenes Using Variational Autoencoders

Mei

Chen

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Anomaly detection in crowded scenes is an important and challenging part of the intelligent video surveillance system. As the deep neural networks make success in feature representation, the features extracted by a deep neural network represent the appearance and motion patterns in different scenes more specifically, comparing with the hand-crafted features typically used in the traditional anomaly detection approaches. In this paper, we propose a new baseline framework of anomaly detection for complex surveillance scenes based on a variational auto-encoder with convolution kernels to learn feature representations. Firstly, the raw frames series are provided as input to our variational auto-encoder without any preprocessing to learn the appearance and motion features of the receptive fields. Then, multiple Gaussian models are used to predict the anomaly scores of the corresponding receptive fields. Our proposed two-stage anomaly detection system is evaluated on the video surveillance dataset for a large scene, UCSD pedestrian datasets, and yields competitive performance compared with state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%