A distributed estimator for on-road target tracking with lane estimation and identification

作者：Chen YangSheng^*

来源：Science China Information Sciences, 2010, 53(12): 2495-2505.

DOI：10.1007/s11432-010-4121-7

• on-road target tracking
• road representation
• lateral motion
• interact multi-model (IMM) algorithm
• fusion
• lane identification

For ground target tracking with road constraints, the existing methods ignore the road width, which can lead to significant biases of the target state estimates when the road width is large. In this paper, based on the proposed novel two-dimensional (2D) road representation which additionally allows to model target lateral motion, a distributed estimator (DE) with lane estimation and identification is proposed. This estimator uses radar and image sensor based local estimates to provide a global estimate of the target displacement from the road axis. In local estimators, the updated lane estimations are used for iterations. The representative simulation results show that the proposed estimator achieves much better estimation performance than the mileage estimator (ME), and the lane identifier can effectively identify the lane which the target is in.

• 出版日期2010-12
• 单位中国电子科技集团公司第三十八研究所