The Study on the Method of Vehicle Detection and Tracking Based on Gaussian Mixture Model and Kalman Filter

2014 ◽  
Vol 644-650 ◽  
pp. 1266-1269 ◽  
Author(s):  
Li Yuan Lin ◽  
Lin Chen
Keyword(s):  
Kalman Filter ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Vehicle Detection ◽  
Gaussian Mixture ◽  
Detection And Tracking ◽  
Frame Difference ◽  
Vehicle Detection And Tracking ◽  
Target Extraction ◽  
Detection Stage

In the vehicle detection stage,in order to solve the problem of Gaussian Mixture Model having poor adapting capacity on the sudden changes of the illumination,this paper designs a illumination judgement factor.When the factor is greater than a certain threshold,this paper uses three frame difference method for target extraction,otherwise uses the Gaussian Mixture Model.In the vehicle tracking stage,the Kalman Filter is introduced to improve tarcking accuracy and tracking efficiency,at the same time,a tracking list is designed for single and multi objectives tracking.The results show that the method can adapte the sudden changes of the illumination and can achive a better effect of vehicle detection and tracking.

scholarly journals Vehicle Speed Estimation Using Gaussian Mixture Model and Kalman Filter

2021 ◽  
Vol 16 (4) ◽  
Author(s):  
Ahmed Abdulwahab Tayeb ◽  
Rabah Wasel Aldhaheri ◽  
Muhammad Shehzad Hanif
Keyword(s):  
Kalman Filter ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Vehicle Detection ◽  
Gaussian Mixture ◽  
Automated System ◽  
Speed Estimation ◽  
Vehicle Speed ◽  
Robust Solution ◽  
Geometry Model

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 using the Kalman Filter. Finally, an estimate the speed of each vehicle is determined by using the perspective geometry model. The complete system is tested at our university campus and the results are promising.

Object Modeling Using Gaussian Mixture Model for Infrared Image and its Application to Vehicle Detection

2006 ◽  
Vol 18 (6) ◽  
pp. 738-743 ◽  
Author(s):  
Makito Seki ◽  
◽  
Haruhisa Okuda ◽  
Manabu Hashimoto ◽  
Nami Hirata
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Infrared Image ◽  
Vehicle Detection ◽  
Gaussian Mixture ◽  
Modeling Method ◽  
Object Modeling ◽  
Visible Image ◽  
Low Contrast ◽  
Gradient Orientation

In this paper, we propose a new object modeling method for infrared (IR) image. It is based on the modeling method using Gaussian Mixture Model (GMM) that has been originally proposed for general visible image. The original method is one of effective object modeling algorithms that can describe the topological structures of the internal patterns of object. This approach can also eliminate the influences due to small differences between patterns. On the other hand, an IR image is often used instead of visible image in actual applications such as outdoor surveillance. IR images make it easy to extract foreground object regions from background scenes, but their low-contrast makes object modeling difficult. We therefore propose a modeling method using Orientation-Code for IR image. Orientation-Code of each pixel has information about the maximum-gradient orientation of image, not intensity information. Gradient orientation information does not depend on contrast and describes internal pattern structures of objects even in unclear IR images. We also applied proposed method to vehicle detection for outdoor scenes, where it extracts multiple foreground regions as vehicle candidates using background subtraction for IR image, and they are described as models by our method. Models are finally compared with standard vehicle view models pre-memorized to determine which candidate is true vehicle or not. Evaluation tests with actual IR video sequences have proved that our proposed algorithm detects objects robustly.

Moving Object Detection Based on Improved Background Updating Method for Gaussian Mixture Model

2014 ◽  
Vol 1049-1050 ◽  
pp. 1561-1565
Author(s):  
Wu Wen ◽  
Tao Jiang ◽  
Yu Fang Gou
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Moving Object ◽  
Improved Method ◽  
Background Region ◽  
Frame Difference ◽  
Foreground Region ◽  
Improvement Method ◽  
Background Models

An effective improvement method was put forward caused by the traditional Gaussian mixture model has poor adaptability to illumination mutation. When illumination mutation is detected, improved Frame difference could detect the foreground region and background region, and then adopts a new replacing update methods to the Gaussian distribution with the least weights of Gaussian mixture background models in different regions. The experimental results show that improved method makes Gaussian mixture model can quickly adaptive to the light mutation, and exactly detect the moving object.

Sign in / Sign up

Export Citation Format

Share Document