Li Liangqun

Online Visual Multiple Target Tracking by Intuitionistic Fuzzy Data Association

Abstract In this paper, a novel frame-by-frame data association algorithm based on intuitionistic fuzzy sets is proposed for online visual multiple target tracking. In the proposed algorithm, the association costs between targets and measurements are replaced by the intuitionistic fuzzy membership degrees which are obtained by a modified intuitionistic fuzzy c-means clustering algorithm. In addition, in order to mine useful information from the uncertain measurements, a new intuitionistic index is defined and the intuitionistic fuzzy point operator is applied to extract valuable information from the intuitionistic index. Experiments with challenging public datasets demonstrate that the proposed visual tracking algorithm improves tracking performance compared to other algorithms.

Fuzzy logic approach to visual multi-object tracking

Abstract In this paper, a novel fuzzy logic data association algorithm is proposed for online visual multi-object tracking. Firstly, in the proposed algorithm, in order to incorporate expert experience into the data association for the improvement of performance in multi-object tracking, a fuzzy inference system based on knowledge is designed by using a set of fuzzy if-then rules. Given the error and change of error of motion, shape and appearance models in the last prediction, these rules are used to determine the fuzzy membership degrees that can be used to substitute the association probabilities between the objects and the measurements (or detection responses). Secondly, in order to deal with the fragmented trajectories caused by long-term occlusions, a track-to-track association approach based on the fuzzy synthetic function is proposed, which can effectively stitch track fragments (tracklets). Because of this, the proposed algorithm has the advantage that it does require no assumption of statistical models of measurement noise and of object dynamics. The experiment results on several public data sets show the efficiency and the ability to minimize the number of fragment tracks of the proposed algorithm.

Multiple model Rao-Blackwellized particle filter

In this paper, we proposed a new multiple model Rao-Blackwellized particle filter (MMRBPF) based algorithm for maneuvering target tracking. The advantage of the proposed approach is that the Rao-Blackwellization allows the algorithm to be partitioned into target tracking and model selection sub-problems, where the target tracking can be solved by the probabilistic data association filter, and the model selection by sequential importance sampling. The analytical relationship between target state and model is exploited to improve the efficiency and accuracy of the proposed algorithm. Finally, the experiment results show that the proposed algorithm results in more accurate tracking than the existing one.

A novel particle filtering algorithm for the noncooperative target tracking in general aviation

For the problem of noncooperative target tracking in General Aviations air traffic control system, a novel particle filtering algorithm is proposed. Firstly, in order to obtain the target azimuth information accurately, the Infrared sensor is inducted to search/track the noncooperative target by using the radar track information, and then the new measurement is reconstructed by utilizing the Infrared azimuth information and the radar track information. Secondly, in order to adaptively track and obtain the 3-D tracking information of the noncooperative target, an importance density based on maneuver index is proposed. Finally, the simulation results show that the proposed algorithm is effective and its performance is superiority over the Interacting Multiple Model method (IMM).