A Multiple Object Tracking Method Using Kalman Filter Xin Li Kejun Wang,Wei Wang and Yang Li Engineering Training Center of HarBin Engineering University Automation College of Harbin Engneering University Harbin, Heilongjiang Province, 150001, China xinxin_forever@sohu.com Abstract –It is important to maintain the identity of multiple targets while tracking them in some applications such as behavior understanding. However, unsatisfying tracking results may be produced due to different real-time conditions. These conditions include: inter-object occlusion, occlusion of the ocjects by background obstacles, splits and merges, which are observed when objects are being tracked in real-time. In this paper, an algorithm of feature-based using Kalman filter motion to handle multiple objects tracking is proposed. The system is fully automatic and requires no manual input of any kind for initialization of tracking. Through establishing Kalman filter motion model with the features centroid and area of moving objects in a single fixed camera monitoring scene, using information obtained by detection to judge whether merge or split occurred, the calculation of the cost function can be used to solve the problems of correspondence after split happened. The algorithm proposed is validated on human and vehicle image sequence algorithm proposed achieve efficient tracking of multiple moving objects under the confusing situations. Index Terms - Kalam filter, motion model, multi-object tracking , Occlusion I. INTRODUCTION Moving object tracking of video image sequences is one of the most important subjects in computer vision. It has already been applied in many computer vision field, such as video surveillance, artificial intelligence, military guidance, safety detection, and robot navigation, medical and biological application etc..[1]. In recent years, a number of successful single-object tracking system appeared, but In the presence of several objects, the problem is one of multiple object tracking where targets and observations need to be matched from frame to frame in a video sequence. he multiple object tracking is still a challenging, and it will be harder especially in the case of that the objects have a similar appearance [2]. To deal with these problems, researchers did a lot of works.and gained many good achievements. Nguyen et al. [3] used Kalman filter in distributed tracking system for tracking multiple moving people in a room using multiple cameras. Whereas Chang et al. [4] use both Bayesian network and Kalman filtering to solve the correspondence problem between multiple objects. In [5], a video surveillance system is proposed where detection, recognition and tracking of object is carried out. However, multiple objects are tracked by using the c-constant velocity Kalman algorithm. The performance of the approach is dependent on the proposed detection and recognition algorithms. In another work [6], vector Kalman is proposed for tracking objects. In this paper, separate methods for occlusion and merge are applied to handle the confusing situations. Further states of the corresponding moving objects are searched using spiral searching prior to tracking. Medioni et al. [7] proposed an approach based on graph theory for tracking multiple targets. Their algorithm considered splits only, and they used gray level correlation between objects and segmented blobs to detect and handle splits. Recently Czyzewski and Dalka [8] used Kalman filter with RGB color-based approach to measure the similarity between moving objects. A threshold is applied to measure the similarity between the detected regions which fails in fully occluded scenarios. In this paper, we use Kalman filter to establish object motion model, using the current object’s information to predict object's position, so that we can reduce the search scope and search time of moving object to achieve fast tracking. Establishing corresponding relationship through moving object features matching to deal with separation after objects merged. Experimental results show the proposed method is able to ensure an efficient and robust tracking with merge and split of multi-object. II. OBJECT TRACKING USING KALMAN FILTER A. Typical Kalman filter Mathematically, Kalman filer is an estimator that predicts and corrects the states of wide range of linear processes[9]. It is not only efficient practically but attractive theoretically as well Precisely, the optimal state is found with smallest possible variance error, recursively. However, an accurate model is an essential requirement. In Kalman filer, we consider a tracking system where k x is the state vector which represents the dynamic behaviour of the object, where subscript k indicate the discrete time. The objective is to estimate k x from the measurement k z . Following is the mathematical description of Kalman filer, which for understanding we have sectioned into four phases. 1) Process equation 1 1 k k k x x w     A (1) 1862 978-1-4244-5704-5/10/$26.00 ©2010 IEEE Proceedings of the 2010 IEEE International Conference on Information and Automation June 20 - 23, Harbin, China