Vehicle-Classification Based on Edge Extraction and Background Difference

2011 ◽  
Vol 128-129 ◽  
pp. 1109-1113
Author(s):  
Chan Yang ◽  
Zhong Jian Dai
Keyword(s):  
Real Time ◽  
Intelligent Transportation System ◽  
Weather Conditions ◽  
Extraction Process ◽  
Detection Algorithm ◽  
Vehicle Classification ◽  
Experimental Result ◽  
Support Vector ◽  
Real Time System ◽  
Background Difference

The real-time vehicle classification plays an important role in Intelligent Transportation System (ITS). How to effectively improve the accuracy rate and the speed of the vehicle classification is still a hot research issue, the classification algorithm has to be effective but simple. In this paper, a vehicle detection algorithm based on edge-based background difference and region-based background difference is proposed. This algorithm can extract the moving vehicle completely, eliminate vehicle shadow effectively, and it is still significant despite the variations of illumination and weather conditions. The algorithm is simple with low computation quantity and suitable for real-time system. In the feature extraction process, the feature vector can be obtained in short time. Support vector machine (SVM) is also discussed in the classification process. The experimental result shows that the system can accurately recognize the vehicles.

scholarly journals Research on a Fast Human-Detection Algorithm for Unmanned Surveillance Area in Bulk Ports

2014 ◽  
Vol 2014 ◽  
pp. 1-17 ◽  
Author(s):  
Chao Mi ◽  
Xin He ◽  
Haiwei Liu ◽  
Youfang Huang ◽  
Weijian Mi
Keyword(s):  
Real Time ◽  
Computing Time ◽  
Training Sample ◽  
Detection Algorithm ◽  
Human Detection ◽  
Security Requirements ◽  
Support Vector ◽  
Svm Classifier ◽  
Histograms Of Oriented Gradients ◽  
Heavy Equipment

With the development of port automation, most operational fields utilizing heavy equipment have gradually become unmanned. It is therefore imperative to monitor these fields in an effective and real-time manner. In this paper, a fast human-detection algorithm is proposed based on image processing. To speed up the detection process, the optimized histograms of oriented gradients (HOG) algorithm that can avoid the large number of double calculations of the original HOG and ignore insignificant features is used to describe the contour of the human body in real time. Based on the HOG features, using a training sample set consisting of scene images of a bulk port, a support vector machine (SVM) classifier combined with the AdaBoost classifier is trained to detect human. Finally, the results of the human detection experiments on Tianjin Port show that the accuracy of the proposed optimized algorithm has roughly the same accuracy as a traditional algorithm, while the proposed algorithm only takes 1/7 the amount of time. The accuracy and computing time of the proposed fast human-detection algorithm were verified to meet the security requirements of unmanned port areas.

scholarly journals Predicting Coronavirus Pandemic in Real-Time Using Machine Learning and Big Data Streaming System

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Xiongwei Zhang ◽  
Hager Saleh ◽  
Eman M. G. Younis ◽  
Radhya Sahal ◽  
Abdelmgeid A. Ali
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Sentiment Analysis ◽  
Real Time ◽  
Machine Learning Algorithms ◽  
Streaming Data ◽  
Support Vector ◽  
Real Time System ◽  
Online Prediction ◽  
Analysis Prediction

Twitter is a virtual social network where people share their posts and opinions about the current situation, such as the coronavirus pandemic. It is considered the most significant streaming data source for machine learning research in terms of analysis, prediction, knowledge extraction, and opinions. Sentiment analysis is a text analysis method that has gained further significance due to social networks’ emergence. Therefore, this paper introduces a real-time system for sentiment prediction on Twitter streaming data for tweets about the coronavirus pandemic. The proposed system aims to find the optimal machine learning model that obtains the best performance for coronavirus sentiment analysis prediction and then uses it in real-time. The proposed system has been developed into two components: developing an offline sentiment analysis and modeling an online prediction pipeline. The system has two components: the offline and the online components. For the offline component of the system, the historical tweets’ dataset was collected in duration 23/01/2020 and 01/06/2020 and filtered by #COVID-19 and #Coronavirus hashtags. Two feature extraction methods of textual data analysis were used, n-gram and TF-ID, to extract the dataset’s essential features, collected using coronavirus hashtags. Then, five regular machine learning algorithms were performed and compared: decision tree, logistic regression, k-nearest neighbors, random forest, and support vector machine to select the best model for the online prediction component. The online prediction pipeline was developed using Twitter Streaming API, Apache Kafka, and Apache Spark. The experimental results indicate that the RF model using the unigram feature extraction method has achieved the best performance, and it is used for sentiment prediction on Twitter streaming data for coronavirus.

Snow Detection using In-Vehicle Video Camera with Texture-Based Image Features Utilizing K-Nearest Neighbor, Support Vector Machine, and Random Forest

2019 ◽  
Vol 2673 (8) ◽  
pp. 221-232 ◽  
Author(s):  
Md Nasim Khan ◽  
Mohamed M. Ahmed
Keyword(s):  
Real Time ◽  
Prediction Accuracy ◽  
Nearest Neighbor ◽  
Detection System ◽  
Weather Conditions ◽  
Video Camera ◽  
Image Features ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Weather Information

Snowfall negatively affects pavement and visibility conditions, making it one of the major causes of motor vehicle crashes in winter weather. Therefore, providing drivers with real-time roadway weather information during adverse weather is crucial for safe driving. Although road weather stations can provide weather information, these stations are expensive and often do not represent real-time trajectory-level weather information. The main motivation of this study was to develop an affordable in-vehicle snow detection system which can provide trajectory-level weather information in real time. The system utilized SHRP2 Naturalistic Driving Study video data and was based on machine learning techniques. To train the snow detection models, two texture-based image features including gray level co-occurrence matrix (GLCM) and local binary pattern (LBP), and three classification algorithms: support vector machine (SVM), k-nearest neighbor (K-NN), and random forest (RF) were used. The analysis was done on an image dataset consisting of three weather conditions: clear, light snow, and heavy snow. While the highest overall prediction accuracy of the models based on the GLCM features was found to be around 86%, the models considering the LBP based features provided a much higher prediction accuracy of 96%. The snow detection system proposed in this study is cost effective, does not require a lot of technical support, and only needs a single video camera. With the advances in smartphone cameras, simple mobile apps with proper data connectivity can effectively be used to detect roadway weather conditions in real time with reasonable accuracy.

A Robust Real-Time Object Detection and Recognition Algorithm for Multiple Objects

2019 ◽  
Vol 12 ◽  
Author(s):  
Garv Modwel ◽  
Anu Mehra ◽  
Nitin Rakesh ◽  
K K Mishra
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Hybrid Method ◽  
Hybrid Algorithm ◽  
Time Lag ◽  
Detection Algorithm ◽  
Recognition Algorithm ◽  
Real Time System ◽  
Real Time Processing ◽  
Detection And Recognition

Background: Object detection algorithm scans every frame in the video to detect the objects present which is time consuming. This process becomes undesirable while dealing with real time system, which needs to act with in a predefined time constraint. To have quick response we need reliable detection and recognition for objects. Methods: To deal with the above problem a hybrid method is being implemented. This hybrid method combines three important algorithms to reduce scanning task for every frame. Recursive Density Estimation (RDE) algorithm decides which frame need to be scanned. You Look at Once (YOLO) algorithm does the detection and recognition in the selected frame. Detected objects are being tracked through Speed-up Robust Feature (SURF) algorithm to track the objects in subsequent frames. Results: Through the experimental study, we demonstrate that hybrid algorithm is more efficient compared to two different algorithm of same level. The algorithm is having high accuracy and low time latency (which is necessary for real time processing). Conclusion: The hybrid algorithm is able to detect with a minimum accuracy of 97 percent for all the conducted experiments and time lag experienced is also negligible, which makes it considerably efficient for real time application.

Density based Traffic Monitoring system in Haze and FOG Conditions

2021 ◽  
Vol 9 (3) ◽  
pp. 286-293
Keyword(s):  
Real Time ◽  
Traffic Congestion ◽  
Traffic Management ◽  
New Technologies ◽  
Weather Conditions ◽  
Extraction Process ◽  
Traffic Monitoring ◽  
Traffic Density ◽  
Morphological Operations ◽  
Conventional Methods

The problem of traffic congestion has increased now-a-day’s due to the rapid growth of population in major cities. Overwhelming number of vehicles and insufficient roads are the major causes of traffic congestion. This needs new technologies to be adopted, and a better approach for effective traffic management. In the literature, researchers use conventional methods such as IR sensor, wireless sensor, and Fuzzy logic to measure the traffic density. The main limitations of such conventional methods are that they require personal monitoring of the traffic and ineffective to work in foggy weather. The main aim of this work is to develop a real-time adaptive density-based traffic management system that can quantify number of vehicles on roads under foggy weather conditions. The proposed system involves video acquisition, frame extraction, fog removal and vehicle counting. At first, the video is captured by camera and split into number of frames using frame extraction process. The Dark channel prior (DCP) algorithm is used to remove the fog from each frame and the background subtraction method and certain morphological operations are used to count the number of vehicles in real-time. Based on the vehicle count, the system specifies the time required to clear the traffic. This could facilitate ease traffic flow, save time, and even operate in foggy weather conditions, which is an improvement from the conventional timer-based operations of traffic signals.

A Study of Real Time Security Monitoring of Commercial Vehicles Using a Microscopic Traffic Simulation Model

2011 ◽  
Vol 55-57 ◽  
pp. 1293-1298
Author(s):  
Hao Wang ◽  
Ruey Cheu ◽  
Der Horng Lee
Keyword(s):  
Simulation Model ◽  
Real Time ◽  
Detection Algorithm ◽  
Commercial Vehicles ◽  
Microscopic Simulation ◽  
Real Time System ◽  
Security Monitoring ◽  
Positioning Systems ◽  
Good Potential ◽  
Security Monitoring System

This paper involves a study of a real-time system for monitoring the security of commercial vehicles in road networks. Embedded in the security monitoring system is a commercial vehicle tracking and incident detection algorithm which relies on a combination of vehicle telemetry data obtained from Global Positioning Systems and on-board sensors to continuously monitor the route choice and car-following behavior of the driver. The performance of this algorithm has been tested in a microscopic simulation model, on a set of hypothetical scenarios, which included deviations from the approved routes, forced to travel at unreasonably low speeds, or even stopped at unexpected places in the network. The initial results indicate that the proposed system has good potential in detecting abnormal driving behaviors, with 100% detection rate, 6.0 seconds of mean detection time, and less than 1% false alarm rate.

An adaptive SVM-based real-time scheduling mechanism and simulation for multiple-load carriers in automobile assembly lines

2017 ◽  
Vol 08 (04) ◽  
pp. 1750048 ◽  
Author(s):  
Binghai Zhou ◽  
Jiahui Xu
Keyword(s):  
Real Time ◽  
System Performance ◽  
Manufacturing Systems ◽  
Batch Size ◽  
Support Vector ◽  
Real Time System ◽  
Real Time Scheduling ◽  
Automobile Assembly ◽  
Time Scheduling ◽  
Multiple Load

Multiple-load carriers are widely introduced for material delivery in manufacturing systems. The real-time scheduling of multiple-load carriers is so complex that it deserves attention to pursue higher productivity and better system performance. In this paper, a support vector machine (SVM)-based real-time scheduling mechanism was proposed to tackle the scheduling problem of parts replenishment with multiple-load carriers in automobile assembly plants under dynamic environment. The SVM-based scheduling mechanism was trained first and then used to make the optimal real-time decisions between “wait” and “deliver” on the basis of real-time system states. An objective function considering throughput and delivery distances was established to evaluate the system performance. Moreover, a simulation model in eM-Plant software was developed to validate and compare the proposed SVM-based scheduling mechanism with the classic minimum batch size (MBS) heuristic. It simulated both the steady and dynamic environments which are characterized by the uncertainty of demands or scheduling criteria. The simulation results demonstrated that the SVM-based scheduling mechanism could dynamically make optimal real-time decisions for multiple-load carriers and outperform the MBS heuristic as well.

An FPGA-Based Real-Time Human Eye Pupil Detection System Using E2V Smart Camera

2019 ◽  
Vol 16 (2) ◽  
pp. 649-654
Author(s):  
S. Navaneethan ◽  
N. Nandhagopal ◽  
V. Nivedita
Keyword(s):  
Real Time ◽  
Detection System ◽  
Detection Algorithm ◽  
Video Frame ◽  
Smart Camera ◽  
Verilog Hdl ◽  
Real Time System ◽  
Human Eye ◽  
Pupil Detection ◽  
Main Motive

Threshold based pupil detection algorithm was found tobe most efficient method to detect human eye. An implementation of a real-time system on an FPGA board to detect and track a human's eye is the main motive to obtain from proposed work. The Pupil detection algorithm involved thresholding and image filtering. The Pupil location was identified by computing the center value of the detected region. The proposed hardware architecture is designed using Verilog HDL and implemented on aAltera DE2 cyclone II FPGA for prototyping and logic utilizations are compared with Existing work. The overall setup included Cyclone II FPGA, a E2V camera, SDRAM and a VGA monitor. Experimental results proved the accuracy and effectiveness of the hardware realtime implementation as the algorithm was able to manage various types of input video frame. All calculation was performed in real time. Although the system can be furthered improved to obtain better results, overall the project was a success as it enabled any inputted eye to be accurately detected and tracked.

scholarly journals Electric Vehicle Charging Process and Parking Guidance App

Energies ◽  
2019 ◽  
Vol 12 (11) ◽  
pp. 2123
Author(s):  
Gonçalo Alface ◽  
João C. Ferreira ◽  
Rúben Pereira
Keyword(s):  
Real Time ◽  
Electric Vehicle ◽  
Smart Cities ◽  
Research Work ◽  
Weather Conditions ◽  
Real Time System ◽  
Related Data ◽  
Charging Station ◽  
Electric Vehicle Charging ◽  
Prediction Approach

This research work presents an information system to handle the problem of real-time guidance towards free charging slot in a city using past date and prediction and collaborative algorithms since there is no real-time system available to provide information if a charging spot is free or occupied. We explore the prediction approach using past data correlated with weather conditions. This approach will help the driver in the daily use of his electric vehicle, minimizing the problem of range anxiety, provide guidance towards charging spots with a probability value of being available for charging in a context for the app and smart cities. This work handles the uncertainty of the drivers to get a suitable and vacant place at a charging station because missing real-time information from the system and also during the driving process towards the free charging spot can be taken. We introduce a framework to allow collaboration and prediction process using past related data.

Sign in / Sign up

Export Citation Format

Share Document