scholarly journals Semantic Video Mining for Accident Detection

2020 ◽  
Vol 5 (6) ◽  
pp. 670-678
Author(s):  
Rohith G ◽  
Twinkle Roy ◽  
Vishnu Narayan V ◽  
Shery Shaju ◽  
Ann Rija Paul
Keyword(s):  
Object Detection ◽  
Traffic Monitoring ◽  
Machine Learning Techniques ◽  
Efficient System ◽  
The Public ◽  
Detection Algorithms ◽  
Video Mining ◽  
Detection And Tracking ◽  
Learning Techniques ◽  
Accident Detection

This paper depicts the efficient use of CCTV for traffic monitoring and accident detection. The system which is designed has the capability to classify the accident and can give alerts when necessary. Nowadays we have CCTVs on most of the roads, but its capabilities are being underused. There also doesn’t exist an efficient system to detect and classify accidents in real time. So many deaths occur because of undetected accidents. It is difficult to detect accidents in remote places and at night. The proposed system can identify and classify accidents as major and minor. It can automatically alert the authorities if it deals with a major accident. Using this system the response time on accident can be decreased by processing the visuals of CCTV. In this system different image processing and machine learning techniques are used. The dataset for training is extracted from the visuals of already occurred accidents. Accidents mainly occur because of careless driving, alcohol consumption and over speeding. Another main cause of death due to accidents are the delay in reporting accidents since there doesn’t exist any automated systems. Accidents are mainly reported by the public or by traffic authorities. We can save many lives by detecting and reporting the accident quickly. In this system live video is captured from the CCTV’s and it is processed to detect accidents. In this system the YOLOV3 algorithm is used for object detection. Nowadays traffic monitoring has a greater significance. CCTV’s can be used to detect accidents since it is present in most of the roads. It is only used for traffic monitoring. Normally accidents can be classified as two classes major and minor. The proposed system is able to classify the accident as major or minor by object detection and tracking methodologies. Every accident doesn’t need emergency support. Only major accidents must be handled quickly. The proposed system captures the video and undergo object detection algorithms to identify the different objects like vehicles and people. After the detection phase

scholarly journals The INUS Platform: A Modular Solution for Object Detection and Tracking from UAVs and Terrestrial Surveillance Assets

Computation ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 12
Author(s):  
Evangelos Maltezos ◽  
Athanasios Douklias ◽  
Aris Dadoukis ◽  
Fay Misichroni ◽  
Lazaros Karagiannidis ◽  
...  
Keyword(s):  
Decision Making ◽  
Object Detection ◽  
Situational Awareness ◽  
Machine Learning Techniques ◽  
Measurement Instruments ◽  
Time Data ◽  
Modular Architecture ◽  
Seamless Integration ◽  
Object Detection And Tracking ◽  
Detection And Tracking

Situational awareness is a critical aspect of the decision-making process in emergency response and civil protection and requires the availability of up-to-date information on the current situation. In this context, the related research should not only encompass developing innovative single solutions for (real-time) data collection, but also on the aspect of transforming data into information so that the latter can be considered as a basis for action and decision making. Unmanned systems (UxV) as data acquisition platforms and autonomous or semi-autonomous measurement instruments have become attractive for many applications in emergency operations. This paper proposes a multipurpose situational awareness platform by exploiting advanced on-board processing capabilities and efficient computer vision, image processing, and machine learning techniques. The main pillars of the proposed platform are: (1) a modular architecture that exploits unmanned aerial vehicle (UAV) and terrestrial assets; (2) deployment of on-board data capturing and processing; (3) provision of geolocalized object detection and tracking events; and (4) a user-friendly operational interface for standalone deployment and seamless integration with external systems. Experimental results are provided using RGB and thermal video datasets and applying novel object detection and tracking algorithms. The results show the utility and the potential of the proposed platform, and future directions for extension and optimization are presented.

scholarly journals Optimized Multi-layer Machine Learning Technique for Movement Detection and Tracking in Video Data Stream

2019 ◽  
Vol 8 (10) ◽  
pp. 1151-1159
Keyword(s):  
Object Detection ◽  
Moving Objects ◽  
Error Rates ◽  
Moving Object Detection ◽  
Video Data ◽  
Moving Object ◽  
Detection Accuracy ◽  
Efficient System ◽  
Detection And Tracking ◽  
The Given

With the advent in technology, security and authentication has become the main aspect in computer vision approach. Moving object detection is an efficient system with the goal of preserving the perceptible and principal source in a group. Surveillance is one of the most crucial requirements and carried out to monitor various kinds of activities. The detection and tracking of moving objects are the fundamental concept that comes under the surveillance systems. Moving object recognition is challenging approach in the field of digital image processing. Moving object detection relies on few of the applications which are Human Machine Interaction (HMI), Safety and video Surveillance, Augmented Realism, Transportation Monitoring on Roads, Medical Imaging etc. The main goal of this research is the detection and tracking moving object. In proposed approach, based on the pre-processing method in which there is extraction of the frames with reduction of dimension. It applies the morphological methods to clean the foreground image in the moving objects and texture based feature extract using component analysis method. After that, design a novel method which is optimized multilayer perceptron neural network. It used the optimized layers based on the Pbest and Gbest particle position in the objects. It finds the fitness values which is binary values (x_update, y_update) of swarm or object positions. Method and output achieved final frame creation of the moving objects in the video using BLOB ANALYSER In this research , an application is designed using MATLAB VERSION 2016a In activation function to re-filter the given input and final output calculated with the help of pre-defined sigmoid. In proposed methods to find the clear detection and tracking in the given dataset MOT, FOOTBALL, INDOOR and OUTDOOR datasets. To improve the detection accuracy rate, recall rate and reduce the error rates, False Positive and Negative rate and compare with the various classifiers such as KNN, MLPNN and J48 decision Tree.

scholarly journals Optimization of operational costs of Call centers employing classification techniques

2020 ◽  
Vol 9 (11) ◽  
pp. e86691110491
Author(s):  
Amanda Ferreira de Moura ◽  
Cíntia Maria de Araújo Pinho ◽  
Domingos Márcio Rodrigues Napolitano ◽  
Fellipe Silva Martins ◽  
João Carlos Franco de Barros Fornari Junior
Keyword(s):  
Call Center ◽  
Supervised Machine Learning ◽  
Bank Credit ◽  
Machine Learning Techniques ◽  
Gradient Boosting ◽  
Classification Techniques ◽  
Letter Of Credit ◽  
The Public ◽  
Operational Costs ◽  
Learning Techniques

The provision of credit to customers of banking chains through call center services has always been one of the resources that generate significant income for financial institutions, however, the service offers a cost, which is often above desirable to guarantee profitable contracting to Bank. Based on this, this work aims to evaluate the optimization of operational costs of call center, using classification techniques, through experimentation of supervised machine learning techniques to perform the classification task, in order to generate a predictive model, which offers a better performance in the operation of offering bank credit, to carry out an effective and productive action, conceiving greater savings for the company in identifying the public with greater adherence. For this, a database comprising 11,162 call records made from a bank offering its customers a letter of credit was employed. The results showed value correlations between variables, such as duration of the call, marital status, education level and even recurrence in adhering to subscribers' credit agreements. Through the application of the PCA to reduce dimensionality and classification models, such as AdaBoost, Gradient Boosting, SVM RBF, Naive Bayes, Random Forest, it was possible to perceive the consumer profile with good acquiescence for the investment proposal and a group of people with a high probability of not adhering to the letter of credit, so it was possible to outline an action directed to the public predisposed to the offer, minimizing expenses reaching greater profitability.

A Hybrid Machine Learning Approach for Freeway Traffic Speed Estimation

2020 ◽  
Vol 2674 (10) ◽  
pp. 68-78
Author(s):  
Zhao Zhang ◽  
Yun Yuan ◽  
Xianfeng (Terry) Yang
Keyword(s):  
Machine Learning ◽  
Flow Model ◽  
Hybrid Approach ◽  
Traffic Monitoring ◽  
Machine Learning Techniques ◽  
Learning Approach ◽  
Freeway Traffic ◽  
Learning Techniques ◽  
Machine Learning Approach ◽  
Traffic Speed Estimation

Accurate and timely estimation of freeway traffic speeds by short segments plays an important role in traffic monitoring systems. In the literature, the ability of machine learning techniques to capture the stochastic characteristics of traffic has been proved. Also, the deployment of intelligent transportation systems (ITSs) has provided enriched traffic data, which enables the adoption of a variety of machine learning methods to estimate freeway traffic speeds. However, the limitation of data quality and coverage remain a big challenge in current traffic monitoring systems. To overcome this problem, this study aims to develop a hybrid machine learning approach, by creating a new training variable based on the second-order traffic flow model, to improve the accuracy of traffic speed estimation. Grounded on a novel integrated framework, the estimation is performed using three machine learning techniques, that is, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN). All three models are trained with the integrated dataset including the traffic flow model estimates and the iPeMS and PeMS data from the Utah Department of Transportation (DOT). Further using the PeMS data as the ground truth for model evaluation, the comparisons between the hybrid approach and pure machine learning models show that the hybrid approach can effectively capture the time-varying pattern of the traffic and help improve the estimation accuracy.

Early Intervention Systems: Predicting Adverse Interactions Between Police and the Public

2017 ◽  
Vol 29 (2) ◽  
pp. 190-209 ◽  
Author(s):  
Jennifer Helsby ◽  
Samuel Carton ◽  
Kenneth Joseph ◽  
Ayesha Mahmud ◽  
Youngsoo Park ◽  
...  
Keyword(s):  
Machine Learning ◽  
Early Intervention ◽  
Police Department ◽  
Data Sources ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Police Legitimacy ◽  
The Public ◽  
Learning Techniques ◽  
Improve Accuracy

Adverse interactions between police and the public hurt police legitimacy, cause harm to both officers and the public, and result in costly litigation. Early intervention systems (EISs) that flag officers considered most likely to be involved in one of these adverse events are an important tool for police supervision and for targeting interventions such as counseling or training. However, the EISs that exist are not data-driven and based on supervisor intuition. We have developed a data-driven EIS that uses a diverse set of data sources from the Charlotte-Mecklenburg Police Department and machine learning techniques to more accurately predict the officers who will have an adverse event. Our approach is able to significantly improve accuracy compared with their existing EIS: Preliminary results indicate a 20% reduction in false positives and a 75% increase in true positives.

scholarly journals AUTOMATIC OBJECT EXTRACTION FROM HIGH RESOLUTION AERIAL IMAGERY WITH SIMPLE LINEAR ITERATIVE CLUSTERING AND CONVOLUTIONAL NEURAL NETWORKS

2019 ◽  
Vol XLII-2/W16 ◽  
pp. 61-66 ◽  
Author(s):  
A. C. Carrilho ◽  
M. Galo
Keyword(s):  
High Resolution ◽  
Object Detection ◽  
Semantic Segmentation ◽  
Aerial Images ◽  
Machine Learning Techniques ◽  
Object Extraction ◽  
Multi Scale ◽  
Learning Techniques ◽  
Simple Linear Iterative Clustering ◽  
Fast Region

<p><strong>Abstract.</strong> Recent advances in machine learning techniques for image classification have led to the development of robust approaches to both object detection and extraction. Traditional CNN architectures, such as LeNet, AlexNet and CaffeNet, usually use as input images of fixed sizes taken from objects and attempt to assign labels to those images. Another possible approach is the Fast Region-based CNN (or Fast R-CNN), which works by using two models: (i) a Region Proposal Network (RPN) which generates a set of potential Regions of Interest (RoI) in the image; and (ii) a traditional CNN which assigns labels to the proposed RoI. As an alternative, this study proposes an approach to automatic object extraction from aerial images similar to the Fast R-CNN architecture, the main difference being the use of the Simple Linear Iterative Clustering (SLIC) algorithm instead of an RPN to generate the RoI. The dataset used is composed of high-resolution aerial images and the following classes were considered: house, sport court, hangar, building, swimming pool, tree, and street/road. The proposed method can generate RoI with different sizes by running a multi-scale SLIC approach. The overall accuracy obtained for object detection was 89% and the major advantage is that the proposed method is capable of semantic segmentation by assigning a label to each selected RoI. Some of the problems encountered are related to object proximity, in which different instances appeared merged in the results.</p>

scholarly journals Advanced Agro Field & Crop Surveillance Systems

2019 ◽  
Vol 8 (4S2) ◽  
pp. 616-619
Keyword(s):  
Deep Learning ◽  
Primary Productivity ◽  
Machine Learning Techniques ◽  
Productivity Index ◽  
Surveillance Systems ◽  
Motion Sensing ◽  
Detection Algorithms ◽  
On Demand ◽  
Learning Techniques ◽  
The Cost

Agriculture becoming the major driver for Indian economy, applying some of the latest technological digital innovations to solve critical Agri-based challenges are becoming vital to improve the productivity and lower the cost of operations. Primary productivity index of agriculture is directly dependent on how much the crops escaped from attacks either by pests or by external intruders. Applying some of the advanced machine learning techniques in Computer Vision and multiple object detection algorithms in the field of Agriculture surveillance generates huge interest among farmer communities. In this paper, an aapproach which includes deployment of sensors to monitor the whole cultivation area, fixing appropriate cameras and detecting motions in the agro field, is proposed for Agro field surveillance. An orchestrated deployment of necessary sensing devices such as motion-sensing, capturing video based on demand and passes it on to the deep learning algorithms for further synthesis. The model is developed and trained leveraging technologies such as tensorflow, keras with google Colab, Jupyter notebook environment that runs entirely in the google cloud that requires very minimal setup. To evaluate the model, the authors create a test set which contains 200 captured events, more than 60,000 images that are relevant for this scope and available in public to train Deep Learning CNN based models.

scholarly journals Public Opinions and Concerns Regarding the Canadian Prime Minister’s Daily COVID-19 Briefing: Longitudinal Study of YouTube Comments Using Machine Learning Techniques

10.2196/23957 ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. e23957
Author(s):  
Chengda Zheng ◽  
Jia Xue ◽  
Yumin Sun ◽  
Tingshao Zhu
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Public Discourse ◽  
Latent Dirichlet Allocation ◽  
Prime Minister ◽  
Machine Learning Techniques ◽  
Future Health ◽  
The Public ◽  
Learning Techniques ◽  
The Government

Background During the COVID-19 pandemic in Canada, Prime Minister Justin Trudeau provided updates on the novel coronavirus and the government’s responses to the pandemic in his daily briefings from March 13 to May 22, 2020, delivered on the official Canadian Broadcasting Corporation (CBC) YouTube channel. Objective The aim of this study was to examine comments on Canadian Prime Minister Trudeau’s COVID-19 daily briefings by YouTube users and track these comments to extract the changing dynamics of the opinions and concerns of the public over time. Methods We used machine learning techniques to longitudinally analyze a total of 46,732 English YouTube comments that were retrieved from 57 videos of Prime Minister Trudeau’s COVID-19 daily briefings from March 13 to May 22, 2020. A natural language processing model, latent Dirichlet allocation, was used to choose salient topics among the sampled comments for each of the 57 videos. Thematic analysis was used to classify and summarize these salient topics into different prominent themes. Results We found 11 prominent themes, including strict border measures, public responses to Prime Minister Trudeau’s policies, essential work and frontline workers, individuals’ financial challenges, rental and mortgage subsidies, quarantine, government financial aid for enterprises and individuals, personal protective equipment, Canada and China’s relationship, vaccines, and reopening. Conclusions This study is the first to longitudinally investigate public discourse and concerns related to Prime Minister Trudeau’s daily COVID-19 briefings in Canada. This study contributes to establishing a real-time feedback loop between the public and public health officials on social media. Hearing and reacting to real concerns from the public can enhance trust between the government and the public to prepare for future health emergencies.

scholarly journals Detection of Fake Doctored Images used to Circulate Fake News

2020 ◽  
Vol 9 (7) ◽  
pp. 1031-1036
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Machine Learning Techniques ◽  
Fake News ◽  
Neural Network Models ◽  
The Public ◽  
Learning Techniques ◽  
The World ◽  
Classification Of Images

Over the few years the world has seen a surge in fake news and some people are even calling it an epidemic. Misleading false articles are sold as news items over social media, whatsapp etc where no proper barrier is set to check the authenticity of posts. And not only articles but news items also contain images which are doctored to mislead the public or cause sabotage. Hence a proper barrier to check for authenticity of images related to news items is absolutely necessary. And hence classification of images(related to news items) on the basis of authenticity is imminent. This paper discusses the possibilities of identifying fake images using machine learning techniques. This is an introduction into fake news detection using the latest evolving neural network models

scholarly journals Predictive Models for the Medical Diagnosis of Dengue: A Case Study in Paraguay

2019 ◽  
Vol 2019 ◽  
pp. 1-7 ◽  
Author(s):  
Jorge D. Mello-Román ◽  
Julio C. Mello-Román ◽  
Santiago Gómez-Guerrero ◽  
Miguel García-Torres
Keyword(s):  
Public Health ◽  
Medical Diagnosis ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
The Public ◽  
Learning Techniques ◽  
Previous Diagnosis ◽  
Vector Machines ◽  
High Incidence

Early diagnosis of dengue continues to be a concern for public health in countries with a high incidence of this disease. In this work, we compared two machine learning techniques: artificial neural networks (ANN) and support vector machines (SVM) as assistance tools for medical diagnosis. The performance of classification models was evaluated in a real dataset of patients with a previous diagnosis of dengue extracted from the public health system of Paraguay during the period 2012–2016. The ANN multilayer perceptron achieved better results with an average of 96% accuracy, 96% sensitivity, and 97% specificity, with low variation in thirty different partitions of the dataset. In comparison, SVM polynomial obtained results above 90% for accuracy, sensitivity, and specificity.

Sign in / Sign up

Export Citation Format

Share Document