scholarly journals A Novel Spatio-Temporal Violence Classification Framework Based on Material Derivative and LSTM Neural Network

2020 ◽  
Vol 37 (5) ◽  
pp. 687-701
Author(s):  
Wafa Lejmi ◽  
Anouar Ben Khalifa ◽  
Mohamed Ali Mahjoub
Keyword(s):  
Confusion Matrix ◽  
Efficient Solutions ◽  
Rate Of Change ◽  
Surveillance Systems ◽  
Material Derivative ◽  
Classification Framework ◽  
Temporal Features ◽  
Proposed Model ◽  
Normal Human ◽  
Spatio Temporal

In the current era, the implementation of automated security video surveillance systems is particularly needy in terms of human violence recognition. Nevertheless, the latter encounters various interlinked difficulties which require efficient solutions as well as feasible methods that provide a relevant distinction between normal human actions and abnormal ones. In this paper, we present an overview of these issues and a literature review of the related works and current research on-going efforts on this field and suggests a novel prediction model for violence recognition, based on a preliminary spatio-temporal features extraction using the material derivative which describes the rate of change of a particle while in motion with respect to time. The classification algorithm is then carried out using a deep learning LSTM technique to classify generated features into eight specified violent and non-violent categories and a prediction value for each class of action is calculated. The whole model is trained on a public dataset and its classification capacity is evaluated on a confusion matrix which assembles all the predictions made by the system with their actual labels. The obtained results are promising and show that the proposed model can be potentially useful for detecting human violence.

Multi-Level Two-Stream Fusion-Based Spatio-Temporal Attention Model for Violence Detection and Localization

2021 ◽  
Author(s):  
Mujtaba Asad ◽  
He Jiang ◽  
Jie Yang ◽  
Enmei Tu ◽  
Aftab A. Malik
Keyword(s):  
Human Behavior ◽  
Superior Performance ◽  
Temporal Attention ◽  
Attention Model ◽  
Violence Detection ◽  
Temporal Features ◽  
Proposed Model ◽  
Multi Level ◽  
Spatio Temporal ◽  
Detection And Localization

Detection of violent human behavior is necessary for public safety and monitoring. However, it demands constant human observation and attention in human-based surveillance systems, which is a challenging task. Autonomous detection of violent human behavior is therefore essential for continuous uninterrupted video surveillance. In this paper, we propose a novel method for violence detection and localization in videos using the fusion of spatio-temporal features and attention model. The model consists of Fusion Convolutional Neural Network (Fusion-CNN), spatio-temporal attention modules and Bi-directional Convolutional LSTMs (BiConvLSTM). The Fusion-CNN learns both spatial and temporal features by combining multi-level inter-layer features from both RGB and Optical flow input frames. The spatial attention module is used to generate an importance mask to focus on the most important areas of the image frame. The temporal attention part, which is based on BiConvLSTM, identifies the most significant video frames which are related to violent activity. The proposed model can also localize and discriminate prominent regions in both spatial and temporal domains, given the weakly supervised training with only video-level classification labels. Experimental results evaluated on different publicly available benchmarking datasets show the superior performance of the proposed model in comparison with the existing methods. Our model achieves the improved accuracies (ACC) of 89.1%, 99.1% and 98.15% for RWF-2000, HockeyFight and Crowd-Violence datasets, respectively. For CCTV-FIGHTS dataset, we choose the mean average precision (mAp) performance metric and our model obtained 80.7% mAp.

Modeling 3D Convolution Architecture for Actions Recognition

2021 ◽  
Author(s):  
Bogdan Alexandru Radulescu ◽  
Victorita Radulescu
Keyword(s):  
Behavior Analysis ◽  
Action Recognition ◽  
Activation Function ◽  
Training Time ◽  
Temporal Features ◽  
Proposed Model ◽  
Convolution Model ◽  
Convolution Structure ◽  
Spatio Temporal ◽  
Behavior Characteristics

Abstract Action recognition infrastructure can be applied anywhere behavior analysis is required and represents presently a domain of maximum actuality in security and surveillance. The model based on 3D Convolutions is a middle ground between simple key-frame approaches based on 2D convolutions, and other more complex approaches based on Recurrent Neural Networks. Behavior analysis represents a domain greatly improved by action recognition. By placing human actions in different categories it is possible to extract statistics regarding a person’s behavior, characteristics, abilities and preferences which can be processed later by specialized personnel, depending on the selected domain. The proposed model follows simple 3D convolution architecture. Hidden layers are composed of a convolution operation, an activation function and, sometimes, a pooling layer. Leaky ReLU was used as activation function to alleviate the problem of vanishing gradients. Batch Normalization is a technique used for scaling and adjusting the output of an activation layer, and it has been used to reduce over-fitting and decrease the training time. The 3D Convolution structure has the advantage of learning spatio-temporal features, because the convolution is applied over a sequence of frames. In the present paper is presented a proposed 3D convolution model that has average results, with an accuracy of approximately 55% on the NTU RGB+D dataset.

scholarly journals Spatio-temporal Features of Urban Heat Island and its Relationship with Land Use/Cover in Mountainous City: A Case Study in Chongqing

2018 ◽  
Author(s):  
Chunxia Liu ◽  
Yuechen Li
Keyword(s):  
Urban Heat Island ◽  
Land Surface ◽  
Urban Landscape ◽  
Remote Sensing Data ◽  
Rate Of Change ◽  
Heat Island ◽  
Spatial And Temporal Patterns ◽  
Temporal Features ◽  
Urban Heat ◽  
Spatio Temporal

The urban heat island (UHI) becomes more and more serious with the acceleration of urbanization. Many researchers have shown interest in studying the UHI by using remote sensing data. But these studies rarely examine the mountainous cities. The studies on UHI in mountainous cities often used empirical parameters to estimate the land surface temperature (LST), and lacked satellite-ground synchronous experiment to test the accuracy. This paper revised the parameters in mono-window algorithm used to retrieve the LST according to the characteristics of mountainous cities. This study examined the spatial and temporal patterns of the UHI intensity in Chongqing, a typical mountainous city, and its relationship with land cover from 2007 to 2011 based on the Landsat TM data and the improved method. The accuracy of the LST derivation increased by about 1°C compared to the traditional method. The high LST areas increased and extended from the downtown to suburban area each year, but the rate of change decreased. The UHI is dramatically impacted by the rivers. There is a good relationship between the urban sprawl and the UHI. The LST was reduced by about 1°C within a 300m distance from large urban fringe green spaces. The urban landscape parks had a strong effect relieving the UHI at a 100m distance. The LST was reduced by about 0.5°C. The study greatly improves the accuracy of LST derivation, and provides a reliable parameters for the UHI researched in mountainous city.

Location prediction for facility placement by incorporating multi-characteristic information

2021 ◽  
Vol 25 (5) ◽  
pp. 1187-1210
Author(s):  
Pu Wang ◽  
Wei Chen ◽  
Jinjing Huang ◽  
Yuyang Wei ◽  
Junhua Fang ◽  
...  
Keyword(s):  
Location Prediction ◽  
Feature Evaluation ◽  
Temporal Features ◽  
Proposed Model ◽  
The Social ◽  
Efficiency And Effectiveness ◽  
Facility Placement ◽  
Spatio Temporal ◽  
Real World Datasets ◽  
Novel Model

In the course of recommending locations for establishing new facilities on urban planning or commercial programming, the location prediction offers the optimal candidates, which maximizes the number of served customers or minimize customer inconvenience, therefore brings the maximum profits. In most existing studies, only the spatial-temporal features are recognized to evaluate the location popularity, where social relationships of customers, which are significant factors for popularity assessing, have been ignored. Additionally, current researches also fail to take capacities and categories of the facilities into consideration. To overcome the drawbacks, we introduce a novel model of Multi-characteristic Information based Top-k Location Prediction (MITLP), it captures the spatio-temporal behaviors of customers based on historical trajectories, exploits the social relevancy from their friend relationships, as well as examines the category competitiveness of specific facilities thoroughly. Subsequently, by drawing on the feature evaluation and popularity quantization, MITLP will be implemented within a hybrid B-tree-liked recommending framework, Constrained Location and Social-Trajectory Clustered forest (CLSTC-forest), which can not only produce better performance in practice but also address the facility service constraints. Finally, extensive experiments conducted on real-world datasets demonstrate the higher efficiency and effectiveness of the proposed model.

Fusing Dynamic Images and Depth Motion Maps for Action Recognition in Surveillance Systems

2019 ◽  
Vol 09 ◽  
Author(s):  
Rajat Khurana ◽  
Alok Kumar Singh Kushwaha
Keyword(s):  
Action Recognition ◽  
Depth Map ◽  
Good Choice ◽  
Surveillance Systems ◽  
Activity Detection ◽  
Learning Capability ◽  
Proposed Model ◽  
Care Activity ◽  
Increasing Demand ◽  
Depth Motion Maps

Background & Objective: Identification of human actions from video has gathered much attention in past few years. Most of the computer vision tasks such as Health Care Activity Detection, Suspicious Activity detection, Human Computer Interactions etc. are based on the principle of activity detection. Automatic labelling of activity from videos frames is known as activity detection. Motivation of this work is to use most out of the data generated from sensors and use them for recognition of classes. Recognition of actions from videos sequences is a growing field with the upcoming trends of deep neural networks. Automatic learning capability of Convolutional Neural Network (CNN) make them good choice as compared to traditional handcrafted based approaches. With the increasing demand of RGB-D sensors combination of RGB and depth data is in great demand. This work comprises of the use of dynamic images generated from RGB combined with depth map for action recognition purpose. We have experimented our approach on pre trained VGG-F model using MSR Daily activity dataset and UTD MHAD Dataset. We achieve state of the art results. To support our research, we have calculated different parameters apart from accuracy such as precision, F score, recall. Conclusion: Accordingly, the investigation confirms improvement in term of accuracy, precision, F-Score and Recall. The proposed model is 4 Stream model is prone to occlusion, used in real time and also the data from the RGB-D sensor is fully utilized.

scholarly journals Estimating the local spatio‐temporal distribution of malaria from routine health information systems in areas of low health care access and reporting

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Elizabeth Hyde ◽  
Matthew H. Bonds ◽  
Felana A. Ihantamalala ◽  
Ann C. Miller ◽  
Laura F. Cordier ◽  
...  
Keyword(s):  
Health Care ◽  
Access To Health Care ◽  
Malaria Incidence ◽  
Universal Access ◽  
Surveillance Systems ◽  
Passive Surveillance ◽  
Transmission Season ◽  
Access To Health ◽  
Spatio Temporal ◽  
Geographic Access To Care

Abstract Background Reliable surveillance systems are essential for identifying disease outbreaks and allocating resources to ensure universal access to diagnostics and treatment for endemic diseases. Yet, most countries with high disease burdens rely entirely on facility-based passive surveillance systems, which miss the vast majority of cases in rural settings with low access to health care. This is especially true for malaria, for which the World Health Organization estimates that routine surveillance detects only 14% of global cases. The goal of this study was to develop a novel method to obtain accurate estimates of disease spatio-temporal incidence at very local scales from routine passive surveillance, less biased by populations' financial and geographic access to care. Methods We use a geographically explicit dataset with residences of the 73,022 malaria cases confirmed at health centers in the Ifanadiana District in Madagascar from 2014 to 2017. Malaria incidence was adjusted to account for underreporting due to stock-outs of rapid diagnostic tests and variable access to healthcare. A benchmark multiplier was combined with a health care utilization index obtained from statistical models of non-malaria patients. Variations to the multiplier and several strategies for pooling neighboring communities together were explored to allow for fine-tuning of the final estimates. Separate analyses were carried out for individuals of all ages and for children under five. Cross-validation criteria were developed based on overall incidence, trends in financial and geographical access to health care, and consistency with geographic distribution in a district-representative cohort. The most plausible sets of estimates were then identified based on these criteria. Results Passive surveillance was estimated to have missed about 4 in every 5 malaria cases among all individuals and 2 out of every 3 cases among children under five. Adjusted malaria estimates were less biased by differences in populations’ financial and geographic access to care. Average adjusted monthly malaria incidence was nearly four times higher during the high transmission season than during the low transmission season. By gathering patient-level data and removing systematic biases in the dataset, the spatial resolution of passive malaria surveillance was improved over ten-fold. Geographic distribution in the adjusted dataset revealed high transmission clusters in low elevation areas in the northeast and southeast of the district that were stable across seasons and transmission years. Conclusions Understanding local disease dynamics from routine passive surveillance data can be a key step towards achieving universal access to diagnostics and treatment. Methods presented here could be scaled-up thanks to the increasing availability of e-health disease surveillance platforms for malaria and other diseases across the developing world.

scholarly journals A Novel Time-Sensitive Composite Similarity Model for Multivariate Time-Series Correlation Analysis

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 731
Author(s):  
Mengxia Liang ◽  
Xiaolong Wang ◽  
Shaocong Wu
Keyword(s):  
Time Series ◽  
Correlation Analysis ◽  
Stock Price ◽  
Multivariate Time Series ◽  
Temporal Features ◽  
Proposed Model ◽  
Time Series Segmentation ◽  
Similarity Model ◽  
Dynamic Time ◽  
Investment Portfolios

Finding the correlation between stocks is an effective method for screening and adjusting investment portfolios for investors. One single temporal feature or static nontemporal features are generally used in most studies to measure the similarity between stocks. However, these features are not sufficient to explore phenomena such as price fluctuations similar in shape but unequal in length which may be caused by multiple temporal features. To research stock price volatilities entirely, mining the correlation between stocks should be considered from the point view of multiple features described as time series, including closing price, etc. In this paper, a time-sensitive composite similarity model designed for multivariate time-series correlation analysis based on dynamic time warping is proposed. First, a stock is chosen as the benchmark, and the multivariate time series are segmented by the peaks and troughs time-series segmentation (PTS) algorithm. Second, similar stocks are screened out by similarity. Finally, the rate of rising or falling together between stock pairs is used to verify the proposed model’s effectiveness. Compared with other models, the composite similarity model brings in multiple temporal features and is generalizable for numerical multivariate time series in different fields. The results show that the proposed model is very promising.

Fire Detection Based on Fractal Analysis and Spatio-Temporal Features

2021 ◽  
Author(s):  
Monir Torabian ◽  
Hossein Pourghassem ◽  
Homayoun Mahdavi-Nasab
Keyword(s):  
Fractal Analysis ◽  
Fire Detection ◽  
Temporal Features ◽  
Spatio Temporal

A Novel Cloud-Assisted Secure Deep Feature Classification Framework for Cancer Histopathology Images

2021 ◽  
Vol 21 (2) ◽  
pp. 1-22
Author(s):  
Abhinav Kumar ◽  
Sanjay Kumar Singh ◽  
K Lakshmanan ◽  
Sonal Saxena ◽  
Sameer Shrivastava
Keyword(s):  
Differential Privacy ◽  
Model Performance ◽  
Healthcare Services ◽  
Cloud Services ◽  
Efficient Computation ◽  
Sensitive Data ◽  
Classification Framework ◽  
Proposed Model ◽  
Diagnostic Framework ◽  
Histopathological Image Classification

The advancements in the Internet of Things (IoT) and cloud services have enabled the availability of smart e-healthcare services in a distant and distributed environment. However, this has also raised major privacy and efficiency concerns that need to be addressed. While sharing clinical data across the cloud that often consists of sensitive patient-related information, privacy is a major challenge. Adequate protection of patients’ privacy helps to increase public trust in medical research. Additionally, DL-based models are complex, and in a cloud-based approach, efficient data processing in such models is complicated. To address these challenges, we propose an efficient and secure cancer diagnostic framework for histopathological image classification by utilizing both differential privacy and secure multi-party computation. For efficient computation, instead of performing the whole operation on the cloud, we decouple the layers into two modules: one for feature extraction using the VGGNet module at the user side and the remaining layers for private prediction over the cloud. The efficacy of the framework is validated on two datasets composed of histopathological images of the canine mammary tumor and human breast cancer. The application of differential privacy preserving to the proposed model makes the model secure and capable of preserving the privacy of sensitive data from any adversary, without significantly compromising the model accuracy. Extensive experiments show that the proposed model efficiently achieves the trade-off between privacy and model performance.

Kinematic Adaptive Frequency Sampling Combined Spatio Temporal Features for Snow Monitoring in Aerospace Applications

2021 ◽  
pp. 115472
Author(s):  
Parameshwaran Ramalingam ◽  
Lakshminarayanan Gopalakrishnan ◽  
Manikandan Ramachandran ◽  
Rizwan Patan
Keyword(s):  
Aerospace Applications ◽  
Temporal Features ◽  
Frequency Sampling ◽  
Spatio Temporal
Sign in / Sign up

Export Citation Format

Share Document