Mobile Target Tracking Based on Hybrid Open-Loop Monocular Vision Motion Control Strategy

Cao Yuan, Ma Lianchuan and Weigang Ma

Discrete Dynamics in Nature and Society, 2015, vol. 2015, 1-10

Abstract:

This paper proposes a new real-time target tracking method based on the open-loop monocular vision motion control. It uses the particle filter technique to predict the moving target’s position in an image. Due to the properties of the particle filter, the method can effectively master the motion behaviors of the linear and nonlinear. In addition, the method uses the simple mathematical operation to transfer the image information in the mobile target to its real coordinate information. Therefore, it requires few operating resources. Moreover, the method adopts the monocular vision approach, which is a single camera, to achieve its objective by using few hardware resources. Firstly, the method evaluates the next time’s position and size of the target in an image. Later, the real position of the objective corresponding to the obtained information is predicted. At last, the mobile robot should be controlled in the center of the camera’s vision. The paper conducts the tracking test to the L-type and the S-type and compares with the Kalman filtering method. The experimental results show that the method achieves a better tracking effect in the L-shape experiment, and its effect is superior to the Kalman filter technique in the L-type or S-type tracking experiment.

Date: 2015
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/DDNS/2015/690576.pdf (application/pdf)
http://downloads.hindawi.com/journals/DDNS/2015/690576.xml (text/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnddns:690576

DOI: 10.1155/2015/690576

Access Statistics for this article

More articles in Discrete Dynamics in Nature and Society from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().