VEHICLE TRACKING USING KALMAN FILTER AND FEATURES
Signal & Image Processing : An International Journal (SIPIJ) Vol.2, No.2, June 2011
VEHICLE TRACKING USING KALMAN FILTER AND
FEATURES
Amir Salarpour1and Arezoo Salarpour2and Mahmoud Fathi2and MirHossein
Dezfoulian1
1
Department of Computer Engineering, BuAliSina University, Hamedan, Iran
{a.salarpour, dezfoulian}@basu.ac.ir
2
Department of Computer Engineering, Iran University of Science and
Technology,Tehran, Iran arezoo.salarpour@gmail.com ,mahfathi@iust.ac.ir
ABSTRACT
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.
KEYWORDS
Kalman filter, occlusion, active contour
1. INTRODUCTION
There are a number of traffic monitoring technologies being used. Traffic cameras provide a more flexible way of monitoring traffic. These cameras not only can be used in simple tasks like counting cars, they also have the potential to be used in more complex applications like tracking.
Multiple object tracking is an important research topic in computer vision. It has the ability of deal with the single object difficulties such as occlusion with background changing appearance, illumination, non rigid motion and the multi object difficulties such as occlusion between objects and object confusion. In [1] tracking fix number of objects. In [2] an efficient algorithm to track multiple people is presented. [3] proposed a bayesian
VEHICLE TRACKING USING KALMAN FILTER AND
FEATURES
Amir Salarpour1and Arezoo Salarpour2and Mahmoud Fathi2and MirHossein
Dezfoulian1
1
Department of Computer Engineering, BuAliSina University, Hamedan, Iran
{a.salarpour, dezfoulian}@basu.ac.ir
2
Department of Computer Engineering, Iran University of Science and
Technology,Tehran, Iran arezoo.salarpour@gmail.com ,mahfathi@iust.ac.ir
ABSTRACT
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.
KEYWORDS
Kalman filter, occlusion, active contour
1. INTRODUCTION
There are a number of traffic monitoring technologies being used. Traffic cameras provide a more flexible way of monitoring traffic. These cameras not only can be used in simple tasks like counting cars, they also have the potential to be used in more complex applications like tracking.
Multiple object tracking is an important research topic in computer vision. It has the ability of deal with the single object difficulties such as occlusion with background changing appearance, illumination, non rigid motion and the multi object difficulties such as occlusion between objects and object confusion. In [1] tracking fix number of objects. In [2] an efficient algorithm to track multiple people is presented. [3] proposed a bayesian
References: for point correspondence”, IEEE conference of Computer Vision and Pattern Recognition, 704709. Automation, 2189-2195. [9] Zhimin Fan, Jie Zhou, Dashan Gao and Zhiheng Li, (2002) “Contour Extraction And Tracking Of [13] J Lou, H Yang,Wei Ming Hu, Tieniu Tan, (2002) “Visual vehicle tracking using an improved