scholarly journals Novel Video Surveillance-Based Fire and Smoke Classification Using Attentional Feature Map in Capsule Networks

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 98
Author(s):  
Muksimova Shakhnoza ◽  
Umirzakova Sabina ◽  
Mardieva Sevara ◽  
Young-Im Cho
Keyword(s):  
Detection System ◽  
Fire Detection ◽  
Specific Area ◽  
Developed Countries ◽  
Surveillance Systems ◽  
Feature Map ◽  
Proposed Model ◽  
Different Seasons ◽  
Classification Of Images

A fire is an extraordinary event that can damage property and have a notable effect on people’s lives. However, the early detection of smoke and fire has been identified as a challenge in many recent studies. Therefore, different solutions have been proposed to approach the timely detection of fire events and avoid human casualties. As a solution, we used an affordable visual detection system. This method is possibly effective because early fire detection is recognized. In most developed countries, CCTV surveillance systems are installed in almost every public location to take periodic images of a specific area. Notwithstanding, cameras are used under different types of ambient light, and they experience occlusions, distortions of view, and changes in the resulting images from different camera angles and the different seasons of the year, all of which affect the accuracy of currently established models. To address these problems, we developed an approach based on an attention feature map used in a capsule network designed to classify fire and smoke locations at different distances outdoors, given only an image of a single fire and smoke as input. The proposed model was designed to solve two main limitations of the base capsule network input and the analysis of large-sized images, as well as to compensate the absence of a deep network using an attention-based approach to improve the classification of the fire and smoke results. In term of practicality, our method is comparable with prior strategies based on machine learning and deep learning methods. We trained and tested the proposed model using our datasets collected from different sources. As the results indicate, a high classification accuracy in comparison with other modern architectures was achieved. Further, the results indicate that the proposed approach is robust and stable for the classification of images from outdoor CCTV cameras with different viewpoints given the presence of smoke and fire.

Flow Based Classification for Specification Based Intrusion Detection in Software Defined Networking

2019 ◽  
Vol 7 (2) ◽  
pp. 1-8
Author(s):  
Nithya Sampath ◽  
Dinakaran M.
Keyword(s):  
Intrusion Detection ◽  
Information Gain ◽  
Detection System ◽  
Software Defined Networking ◽  
Network Attack ◽  
Detection Systems ◽  
Learning Techniques ◽  
Proposed Model ◽  
And Control

Software defined networking assures the space for network management, SDNs will possibly replace traditional networks by decoupling the data plane and control plane which provides security by means of a global visibility of the network state. This separation provides a solution for developing secure framework efficiently. Open flow protocol provides a programmatic control over the network traffic by writing rules, which acts as a network attack defence. A robust framework is proposed for intrusion detection systems by integrating the feature ranking using information gain for minimizing the irrelevant features for SDN, writing fuzzy-association flow rules and supervised learning techniques for effective classification of intruders. The experimental results obtained on the KDD dataset shows that the proposed model performs with a higher accuracy, and generates an effective intrusion detection system and reduces the ratio of attack traffic.

Growing 3D-SOMs with 2D-Input Layer as a Classification Tool in a Motion Detection System

1997 ◽  
Vol 08 (01) ◽  
pp. 81-89 ◽  
Author(s):  
Udo Seiffert ◽  
Bernd Michaelis
Keyword(s):  
Detection System ◽  
Three Dimensional ◽  
Short Description ◽  
Three Dimensions ◽  
Self Organizing Map ◽  
Input Layer ◽  
Motion Detection System ◽  
Classification Of Images ◽  
Classification Tool

This paper describes the employment of an 'Adaptive Growing Three-Dimensional Self-Organizing Map' for the classification of images. First a short description of growing SOMs is given and the fundamental advantages are mentioned. Then an extension of the original SOM from two to three dimensions with growing feature is presented. By means of some selected examples the general behavior of the algorithm is illustrated.

Loan Default Prediction Model Using Sample, Explore, Modify, Model, and Assess (SEMMA)

2019 ◽  
Vol 16 (8) ◽  
pp. 3489-3503
Author(s):  
Hafiz Ilyas Tariq ◽  
Asim Sohail ◽  
Uzair Aslam ◽  
Nowshath Kadhar Batcha
Keyword(s):  
Data Mining ◽  
Financial Sector ◽  
Developed Countries ◽  
Loan Default ◽  
Data Mining Techniques ◽  
Default Prediction ◽  
Proposed Model ◽  
Loan Defaults ◽  
Significant Factors

The purpose of this study is to provide a comprehensive research and to develop a model to predict the loan defaults. This kind of models becomes inevitable as the issue of bad loans are very much critical in the financial sector especially in micro financing banks of various underdeveloped and developed countries. To cope up with this problem a comprehensive literature review was done to study the significant factors that leads to this issue. Moreover, these reviewed studies were critically focused towards applying data mining techniques for the prediction and classification of the loan defaults. This study used methodologies named KDD, CRISP-DM and SEMMA. While in the experimentation phase, three different data mining techniques were applied for the proposed model and their performances were evaluated on various parameters. Based on these parameters, the best method was selected, explained and suggested because of its significant characteristics regarding the prediction of the loan defaults in the financial sector.

scholarly journals Recognition of Real-World Texture Images Under Challenging Conditions With Deep Learning

2018 ◽  
pp. 122-126
Author(s):  
Ozal Yildirim ◽  
Aysegul Ucar ◽  
Ulas Baran Baloglu
Keyword(s):  
Real World ◽  
Motion Tracking ◽  
Recognition Performance ◽  
Research Area ◽  
Performance Evaluations ◽  
System Model ◽  
Proposed Model ◽  
Important Research Area ◽  
Classification Of Images

Images obtained from the real world environments usually have various distortions in image quality. For example, when an object in motion is filmed, or when an environment is being filmed on the move, motion tracking effects occur on the image. Increasing the recognition performance of expert systems, which perform image recognition on data obtained under such conditions, is an important research area. In this study, we propose a Convolutional Neural Network (CNN) based Deep System Model (CNN-DSM) for accurate classification of images under challenging conditions. In the proposed model, a new layer is designed in addition to the classical CNN layers. This layer works as an enhancement layer. For the performance evaluations, various real world surface images were selected from the Curet database. Finally, results are presented and discussed.

Method of determination of the text direction on the image with the use of convolutional neural network

2020 ◽  
pp. 96-99
Author(s):  
P.L. Nikolaev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Binary Classification ◽  
Synthetic Data ◽  
Real Data ◽  
Method Of Determination ◽  
Classification Of Images

This article deals with method of binary classification of images with small text on them Classification is based on the fact that the text can have 2 directions – it can be positioned horizontally and read from left to right or it can be turned 180 degrees so the image must be rotated to read the sign. This type of text can be found on the covers of a variety of books, so in case of recognizing the covers, it is necessary first to determine the direction of the text before we will directly recognize it. The article suggests the development of a deep neural network for determination of the text position in the context of book covers recognizing. The results of training and testing of a convolutional neural network on synthetic data as well as the examples of the network functioning on the real data are presented.

Using clusterization principles for the selection of repair sections of main oil pipelines based on diagnostic data

2011 ◽  
Vol 8 (1) ◽  
pp. 201-210
Author(s):  
R.M. Bogdanov
Keyword(s):  
Cluster Analysis ◽  
Defect Density ◽  
Density Variation ◽  
Distance Functions ◽  
Oil Pipeline ◽  
Oil Pipelines ◽  
Classification Of Images ◽  
Main Oil Pipeline ◽  
Selection Of

The problem of determining the repair sections of the main oil pipeline is solved, basing on the classification of images using distance functions and the clustering principle, The criteria characterizing the cluster are determined by certain given values, based on a comparison with which the defect is assigned to a given cluster, procedures for the redistribution of defects in cluster zones are provided, and the cluster zones parameters are being changed. Calculations are demonstrating the range of defect density variation depending on pipeline sections and the universal capabilities of linear objects configuration with arbitrary density, provided by cluster analysis.

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 Deep Learning Model Comparison for Vision-Based Classification of Full/Empty-Load Trucks in Earthmoving Operations

2019 ◽  
Vol 9 (22) ◽  
pp. 4871 ◽  
Author(s):  
Quan Liu ◽  
Chen Feng ◽  
Zida Song ◽  
Joseph Louis ◽  
Jian Zhou
Keyword(s):  
Deep Learning ◽  
Model Comparison ◽  
Surveillance Systems ◽  
Comparison Study ◽  
Learning Models ◽  
The Core ◽  
Dump Trucks ◽  
Deep Learning Model ◽  
Contact Field

Earthmoving is an integral civil engineering operation of significance, and tracking its productivity requires the statistics of loads moved by dump trucks. Since current truck loads’ statistics methods are laborious, costly, and limited in application, this paper presents the framework of a novel, automated, non-contact field earthmoving quantity statistics (FEQS) for projects with large earthmoving demands that use uniform and uncovered trucks. The proposed FEQS framework utilizes field surveillance systems and adopts vision-based deep learning for full/empty-load truck classification as the core work. Since convolutional neural network (CNN) and its transfer learning (TL) forms are popular vision-based deep learning models and numerous in type, a comparison study is conducted to test the framework’s core work feasibility and evaluate the performance of different deep learning models in implementation. The comparison study involved 12 CNN or CNN-TL models in full/empty-load truck classification, and the results revealed that while several provided satisfactory performance, the VGG16-FineTune provided the optimal performance. This proved the core work feasibility of the proposed FEQS framework. Further discussion provides model choice suggestions that CNN-TL models are more feasible than CNN prototypes, and models that adopt different TL methods have advantages in either working accuracy or speed for different tasks.

scholarly journals A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Forests ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 768
Author(s):  
Jin Pan ◽  
Xiaoming Ou ◽  
Liang Xu
Keyword(s):  
Forest Fire ◽  
Forest Fires ◽  
Learning Strategy ◽  
Early Stage ◽  
Fire Detection ◽  
Surveillance Systems ◽  
Region Detection ◽  
Decision Network ◽  
Fire Smoke ◽  
Weakly Supervised

Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document