Detecting abnormal crowd behaviors based on the div-curl characteristics of flow fields

基于流畅div-curl特征的异常群体行为检测  

Pattern Recognition, Volume 88, April 2019, Pages 342-355 

Xiao-Han Chen, Jian-Huang Lai 

摘 要：This study proposes a divergence-curl-driven framework for the perception of crowd motion states. In this framework, the characteristics of a flow field, divergence and curl, are used to analyze crowd states. As a collective motion, the movement of a pedestrian crowd shows coherent structural properties. By using the methods of fluid mechanics and the feature visualization of flow fields, a physical characteristic descriptor of crowd motion is established that can model the motion state in a crowd flow field. Given the significance of the temporal comparison of motion states for detecting changes in crowds, a method based on the temporal context of motion is presented to measure changes in the distribution of the physical characteristic descriptors of crowd motion. This method can be used to calculate differences in the distribution of the flow field’s physical characteristics between each state and measure these subtle continuous changes on the sample points, thereby obtaining a quantified metric of changes in a crowd’s motion state. Experiments on crowd event datasets demonstrate the effectiveness of our proposed framework for detecting crowd state changes and abnormal activity. 

Generalization of feature embeddings transferred from different video anomaly detection domains

不同视频异常检测域的特征嵌入泛化  

Journal of Visual Communication and Image Representation, Volume 60, April 2019, Pages 407-416 

Fernando P. dos Santos, Leonardo S. F. Ribeiro, Moacir A. Ponti 

摘 要：Detecting anomalous activity in video surveillance often suffers from limited availability of training data. Transfer learning may close this gap, allowing to use existing annotated data from some source domain. However, analyzing the source feature space in terms of its potential for transfer of learning to another context is still to be investigated. This paper reports a study on video anomaly detection, focusing on the analysis of feature embeddings of pre-trained CNNs with the use of novel cross-domain generalization measures that allow to study how source features generalize for different target video domains. This generalization analysis represents not only a theoretical approach, can be useful in practice as a path to understand which datasets allow better transfer of knowledge. Our results confirm this, achieving better anomaly detectors for video frames and allowing analysis of transfer learning’s positive and negative aspects. 

The human behaviour indicator: A measure of behavioural evolution

人类行为指标：行为演化测度  

Expert Systems with Applications, Volume 118, 15 March 2019, Pages 493-505 

Abubaker Elbayoudi, Ahmad Lotfi, Caroline Langensiepen 

摘 要：Activities of daily living (ADL) or activities of daily working (ADW) may be affected by changes in a person’s health or well-being. Measuring progressive changes in one activity or multiple activities is representative of behavioural variations. By inspecting the trends in multiple activities, it is possible to identify and predict human behavioural changes. We refer to the trends in people’s behaviour as behavioural evolution. In this paper, we propose a novel indicator to measure the progressive changes representing a participant’s behavioural evolution. The proposed indicator presents activities as a holistic measure, which first combine multi-activities and then measure the progressive changes in the combined activities for each single day. Real data sets were collected from a wireless sensor network and used to examine our proposed technique. As part of this process, we were able to quantify progressive changes for individual and aggregated activities. Our experimental results demonstrated that: (1) the proposed approach can identify and distinguish normal and abnormal behaviours; (2) large data sets gathered from sensors in an intelligent environment represented in various time series can be visualised in a simple and more understandable format; (3) identifying trends in ADLs or ADWs is a relevant means of sharing information with carers or supervisors.