Multiple Vehicle Tracking using Adaptive Gaussian Mixture Model and Kalman Filter (original) (raw)

Vehicle detection and tracking using Gaussian Mixture Model and Kalman Filter

2016

Intelligent Transport System (ITS) is a method used in traffic arrangements to make efficient road transport system. One of the ITS application is the detection and tracking of vehicle objects. In this research, Gaussian Mixture Model (GMM) method was applied for vehicle detection and Kalman Filter method was applied for object tracking. The data used are vehicles video under two different conditions. First condition is light traffic and second condition is heavy traffic. Validation of detection system is conducted using Receiver Operating Characteristic (ROC) analysis. The result of this research shows that the light traffic condition gets 100% for the precision value, 94.44% for sensitivity, 100% for specificity, and 97.22% for accuracy. While the heavy traffic condition gets 75.79% for the precision value, 88.89% for sensitivity, 70.37% for specificity, and 79.63% for accuracy. With avarage consistency of Kalman Filter for object tracking is 100%.

Vehicle Speed Estimation Using Gaussian Mixture Model and Kalman Filter

INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 2021

Many countries use traffic enforcement camera to monitor the speed limit and capture over speed violations. The main objective of such a system is to enforce the speed limits which results in the reduction of number of accidents, fatalities, and serious injuries. Traditionally, the task is carried out manually by the enforcement agencies with the help of specialized hardware such as radar and camera. To automate the process, an efficient and robust solution is needed. Vehicle detection, tracking and speed estimation are the main tasks in an automated system which are not trivial. In this paper, we address the problem of vehicle detection, tracking, and speed estimation using a single fixed camera. A background subtraction method based on the Gaussian Mixture Model (GMM) is employed to detect vehicles because of its capability in dealing with complex backgrounds and variations in the appearance due to illumination and scale. Next, the detected vehicles are tracked in each frame by us...

Improved Gaussian Mixture Model for the Task of Object Tracking

Lecture Notes in Computer Science, 2011

This paper presents various motion detection methods: temporal averaging (TA), Bayes decision rules (BDR), Gaussian mixture model (GMM), and improved Gaussian mixture model (iGMM). This last model is improved by adapting the number of selected Gaussian, detecting and removing shadows, handling stopped object by locally modifying the updating process. Then we compare these methods on specific cases, such as lighting changes and stopped objects. We further present four tracking methods. Finally, we test the two motion detection methods offering the best results on an object tracking task, in a traffic monitoring context, to evaluate these methods on outdoor sequences.

Gaussian Mixture Models optimization for counting the numbers of vehicle by adjusting the Region of Interest under heavy traffic condition

2015 International Seminar on Intelligent Technology and Its Applications (ISITIA), 2015

Mixture Model research has been widely implemented for numerous purpose in motion tracking applications. This method usually applied for tracking and counting the vehicles in Intelligent Transport System (ITS). In this context, Mixture Model chosen is Gaussian Mixture Model (GMM) method, due to its powerful features. Unlike many motion tracking-based methods, GMM achieves satisfactory performance from its ability to handle background subtractions. However, its implementation in detecting vehicle still have unsatisfactory result in accuration and identifying object, mainly under heavy traffic condition. The problem turn to poor accuration of object detection. Therefore, in this paper, we propose optimization of GMM performance by adjusting the Region of Interest (ROI). The propose technique to completing the report by compare the result before and after experiment in separate condition. The result show that this approach leads to improvement in tracking and counting average of accuration of motorcycle by 6.97% and car by 39.04% in several condition. Our approach to modified the method has been experimentally validated showing better segmentation performance, and this is an unbiased approach for assessing the practical usefulness of object detection methods for vehicle under heavy traffic condition on the highway.

Vehicle Detection, Tracking and Counting Using Gaussian Mixture Model and Optical Flow

Journal of Engineering Research and Reports

Vehicle detection, tracking, and counting play a significant role in traffic surveillance and are principle applications of the Intelligent Transport System (ITS). Traffic congestion and accidents can be prevented with an adequate solution to problems. In this paper, we implemented different image processing techniques to detect and track the moving vehicle from the videos captured by a stationary camera and count the total number of vehicles passed by. The proposed approach consists of an optical flow method with a Gaussian mixture model (GMM) to obtain an absolute shape of particular moving objects which improves the detection performance of moving targets.

Multiple Object Detection using GMM Technique and Tracking using Kalman Filter

International Journal of Computer Applications

The continuous research in the technology of video acquisition devices increases the number of applications with best performance and less cost. For object recognition, navigation and surveillance systems, object detection and tracking are the indispensable steps. Object detection means segmentation of images between foreground and background objects. Object tracking establish the correspondence between the objects in successive frames of video sequence. In this paper, we have proposed algorithms consists of two stages i.e. object detection using Gaussian Mixture Model (GMM) and multiple moving objects tracking using Kalman filter. While tracking the moving object, problems occur during occlusion of persons with each other. However, it can be effectively deal with various video sequences such as indoor, outdoor and cluttered scenes. The experimental results shows that proposed algorithm achieve accurate, robust and efficient results for detection as well as for tracking the foreground objects from complex and dynamics scenes.

Vehicle Tracking Using Kalman Filter and

Vehicle tracking has a wide variety of applications. The image resolution of the video available from most traffic camera system is low. In many cases for tracking multi object, distinguishing them from another isn't easy because of their similarity. In this paper we describe a method, for tracking multiple objects, where the objects are vehicles. The number of vehicles is unknown and varies. We detect all moving objects, and for tracking of vehicle we use the kalman filter and color feature and distance of it from one frame to the next. So the method can distinguish and tracking all vehicles individually. The proposed algorithm can be applied to multiple moving objects.

Vehicle speed detection based on gaussian mixture model

Intelligent Transportation System is one of the important components in the development of smart cities. Detection of vehicle speed on the highway is supporting the management of traffic engineering. The purpose of this study is to detect the speed of the moving vehicles using digital image processing.Our approach is as follows : The inputs are a sequence of frames, frame rate (fps) and ROI. The steps are following : First we separate foreground and background using Gaussian Mixture Model (GMM) in each frames. Then in each frame, we calculate the location of object and its centroid. Next we determine the speed by computing the movement of centroid in sequence of frames. In the calculation of speed, we only consider frames when the centroid is inside the predefined region of interest (ROI). Finally we transform the pixel displacement into a time unit of km/hour. Validation of the system is done by comparing the speed calculated manually and obtained by the system. The results of software testing can detect the speed of vehicles with the highest accuracy is 97.52% and the lowest accuracy is 77.41%. And the detection results of testing by using real video footage on the road is included with real speed of the vehicle. 1. Introduction Along with the ease of having vehicles and increased population growth, the amount of vehicle is now increasing rapidly. But, the road facilities are not good enough to handle this increased vehicle amount, so that there are many traffic problems, such as traffic jam and traffic violation for exceeding the speed limit which can be very dangerous. So that, the regulations must be implemented to rule this speed violation. Speed limitation is an effective way to rule the speed violation and prevent traffic accidents caused by speed violation. To implement this rule, a surveillance system is needed and be the most important thing to monitor the traffic condition and detect the vehicle speed. For detecting the vehicle speed, the methods which most used are Laser Infrared Detection and Ranging (LIDAR) or Radio Detection and Ranging (RADAR), but these methods need high cost and specialized skill for the operation. The alternative way to monitor traffic condition, which is now performed, is to utilize CCTV cameras named Road Traffic Monitoring Service (RMTC). CCTV cameras installation is now widely performed and be used only to monitor traffic condition, whereas the video recorded from CCTV cameras can be used to detect the vehicles speed based on digital image processing.

Vehicle Detection, Tracking and Counting on M4 Motorway Pakistan

Communications in Computer and Information Science, 2019

An immense interest of the researchers in real time vehicle detection, tracking and counting is a need of society for trouble free and safer travelling in cities. Automatic tracking and detection of vehicles is a laborious task in traffic monitoring. The proposed method processes an input video to track and detects the vehicle through its motion and also counts the total number of vehicles on the road. To enhance the process, we use consolidation of different image processing and computer vision techniques. The proposed method of detection and tracking of vehicles on a road has been implemented on hardware raspberry Pi 3B using MATLAB as software for the simulation. The video is captured on the M4 motorway in Pakistan by a camera attached with raspberry pi then it is processed through the proposed algorithm. The Gaussian Mixture Model (GMM) along with optical flow parameters are used to detect vehicles which are in motion. To segment objects from the background vector threshold is used. The filtering process is applied to suppress the noise and then blob analysis is used to identify the vehicles from an input video. The outcomes demonstrate that the proposed framework effectively distinguishes and tracks moving objects in the urban recordings.

Illegal Parking Detection Using Gaussian Mixture Model and Kalman Filter

2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), 2017

Automatic analysis of videos for traffic monitoring has been an area of significant research in the recent past. In this paper, we proposed a system to detect and track illegal vehicle parking using Gaussian Mixture Model and Kalman Filter. i-LIDS dataset is used to test and evaluate the algorithm by comparing the results with the ground truth provided, we have tested the system using 4 full videos from i-LIDS to detect parked vehicle whiten specific area. Region of interest has been used to detect Vehicle parks in a no parking zone over sixty seconds and remains stationary. Within the scope of this work, we highlighted the components of an automated traffic surveillance system, including background modeling, foreground extraction, Kalman filter and Gaussian mixture model.