Entity

Time filter

Source Type

Pohang, South Korea

Park S.,Yonsei University | Pil Hwang J.,Yonsei University | Kim E.,Yonsei University | Lee H.,Hankyong National University | Gi Jung H.,Mando Central Research Center
Expert Systems with Applications | Year: 2010

As a sensor in the active safety system of vehicles, the microwave radar (MWR) would be a good choice for the localization of the nearby targets but could be a bad choice for their classification or identification. In this paper, a target classification system using a 24 GHz microwave radar sensor is proposed for the active safety system. The basic idea of this paper is that the pedestrians and the vehicles have different reflection characteristics for a microwave. A multilayer perceptron (MLP) neural network is employed to classify the targets and the probabilistic fusion is conduct over time to improve the classification accuracy. Some experiments are performed to show the validity of the proposed system. © 2009 Elsevier Ltd. All rights reserved. Source


Park S.,Yonsei University | Pil Hwang J.,Yonsei University | Kim E.,Yonsei University | Kang H.-J.,Mando Central Research Center
Control Engineering Practice | Year: 2010

In this paper, a probabilistic target vehicle tracking method is proposed for situation awareness of intelligent cruise control (ICC) vehicle. The ICC vehicle considered herein is equipped with a 24 GHz microwave radar for tracking the preceding vehicle. To overcome the severe dispersion and noise of the microwave radar, a statistical model for the radar is built and it is applied to the hybrid particle filter. The hybrid particle filter is combined with the interacting multiple models (IMM) to track the preceding vehicle and predict the driver's intention. Furthermore, the modified hybrid particle filter is proposed to cope with the missing or multiple measurements of the microwave radar. Finally, a computer simulation is conducted and the validity of the proposed method is demonstrated. © 2009 Elsevier Ltd. All rights reserved. Source

Discover hidden collaborations