计算机工程

• 专栏 • 上一篇    下一篇

基于全景摄像头的柱面展开及实时目标跟踪

周明晖1,胡士强1,陈思聪2   

  1. (1. 上海交通大学航空航天学院,上海 200240;2. 加州大学伯克利分校应用数学与经济系,美国 伯克利 94720)
  • 收稿日期:2012-10-22 出版日期:2013-11-15 发布日期:2013-11-13
  • 作者简介:周明晖(1988-),女,硕士研究生,主研方向:图像处理,机器视觉;胡士强,教授、博士生导师;陈思聪,学士
  • 基金项目:

    国家自然科学基金资助项目(61074106)

Cylinder Unwarping and Real-time Target Tracking Based on Omni-directional Camera

ZHOU Ming-hui 1, HU Shi-qiang 1, CHEN Si-cong 2   

  1. (1. School of Aeronautics and Astronautics, Shanghai Jiaotong University, Shanghai 200240, China; 2. Department of Applied Math and Economics, University of California, Berkeley 94720, USA)
  • Received:2012-10-22 Online:2013-11-15 Published:2013-11-13

摘要:

传统摄像头在获取大范围复杂场景中的感兴趣目标时,容易出现目标物体丢失或遮挡等问题。为此,提出一种基于全景摄像头的柱面展开及运动目标实时跟踪算法。通过改进的柱面展开算法对360°摄像头获取的全景图像进行还原展开,解决全景图像中的成像扭曲问题。利用CamShift和Kalman预测相结合的算法跟踪运动目标。实验结果表明,在运动目标存在遮挡、短暂消失或同色物体干扰的情况下,该方法能实现对全景范围复杂环境中运动目标实时鲁棒的跟踪。

关键词: 全景摄像头, 柱面展开, 双线性插值算法, CamShift算法, 卡尔曼滤波, 目标跟踪

Abstract:

Aiming at the problem that the interested target is disappeared or occluded easily in large range of complex scenes by using the traditional camera, a cylinder unwrapping and real-time target tracking method based on panoramic camera is proposed. In this paper, an improved unwrapping algorithm is adopted to transform the panoramic image from omni-directional image. This algorithm effectively solves the distortion problem of panoramic image, and then CamShift combing with Kalman filter algorithm is used to track the moving target. Experimental results demonstrate that the proposed algorithm realizes a real-time and robustness target tracking under large-scale and complex scenes, which contains moving target occluded, temporary disappearance or interference from objects with same color.

Key words: omni-directional camera, cylinder unwrapping, bilinear interpolation algorithm, CamShift algorithm, Kalman fliterin, target tracking

中图分类号: