Research on Track Management of Multi-Target Tracking Based on Modified Fast Algorithm for Data Association 2018-01-1619
With the development of autonomous vehicle technology, there is an increasing tendency toward the application of intelligent sensors in environment-perception system on autonomous vehicle to assist vehicle in intelligent decision making relevant to autonomous driving. As for environment-perception system, a good track management method serves as the foundation, while multi-target tracking and multi-sensor data fusion are recognized as the key. In this paper, a track management method is proposed to deal with multi-target tracking based on the target-level data of multisource environmental sensors for autonomous vehicle. The track management includes four procedures as following: track initiation; point-track association; track update; track deletion. A modified fast algorithm for data association is applied in the point-track association procedure. Afterwards Kalman filter is implemented to update the track information of target. The algorithm has got through a simulation test. The data used in the simulation comes from sensors of a low-speed Autonomous sweeping vehicle which can achieve autonomous driving in certain semi-enclosed region. And the algorithm proves to be an effective resolution to the change of obstacles’ ID and temp missing of data as well as smoothing data and decreasing error to a certain extent. Compared with other association algorithms like nearest neighbor algorithm, joint probability data algorithm, it combines the advantages of good tracking performance in dense clutter environment and high efficiency of calculation. Meanwhile some problems remain to be further discussed like how to decrease the measurement error in a large scale and data fusion in multiple-sensor system. In conclusion, it has a good effect on the low-speed autonomous vehicle system.
Citation: Yu, Y. and Luo, F., "Research on Track Management of Multi-Target Tracking Based on Modified Fast Algorithm for Data Association," SAE Technical Paper 2018-01-1619, 2018, https://doi.org/10.4271/2018-01-1619. Download Citation
Author(s):
Yongjun Yu, Feng Luo
Affiliated:
Tongji Univ.
Pages: 8
Event:
Intelligent and Connected Vehicles Symposium
ISSN:
0148-7191
e-ISSN:
2688-3627
Related Topics:
Autonomous vehicles
Mathematical models
Simulation and modeling
Sensors and actuators
SAE MOBILUS
Subscribers can view annotate, and download all of SAE's content.
Learn More »