电子学报 ›› 2017, Vol. 45 ›› Issue (1): 173-180.DOI: 10.3969/j.issn.0372-2112.2017.01.024

• 学术论文 • 上一篇    下一篇

基于子块运动补偿的运动目标检测

于红绯1,2, 刘威1,2, 袁淮1, 赵宏1   

  1. 1. 东北大学研究院, 辽宁沈阳 110819;
    2. 东软集团股份有限公司, 辽宁沈阳 110179
  • 收稿日期:2015-05-28 修回日期:2015-09-06 出版日期:2017-01-25
    • 作者简介:
    • 于红绯,女,1982年5月出生,辽宁沈阳人,博士,东北大学研究院研究员,东软汽车电子研究员.主要研究领域为汽车辅助驾驶、自动驾驶,研究方向为计算机视觉、图像处理.E-mail:yuhf@neusoft.com;刘威,男,1975年6月出生,辽宁沈阳人,博士,东北大学副教授,教授级高级工程师.主要研究领域为汽车辅助驾驶、智能交通、智能安防,研究方向为计算机视觉、图像处理、模式识别.E-mail:lwei@neusoft.com
    • 基金资助:
    • 国家自然科学基金 (No.61273239)

Moving Object Detection Based on Sub-Block Motion Compensation

YU Hong-fei1,2, LIU Wei1,2, YUAN Huai1, ZHAO Hong1   

  1. 1. Research Academy, Northeastern University, Shenyang, Liaoning 110819, China;
    2. Neusoft Corporation, Shenyang, Liaoning 110179, China
  • Received:2015-05-28 Revised:2015-09-06 Online:2017-01-25 Published:2017-01-25

摘要:

鱼眼相机成像视角大,获得信息丰富,在车载应用中具有广阔应用前景.本文提出了一种适用于移动单目鱼眼相机的运动目标检测方法.首先,提出一种子块运动补偿模型补偿图像背景运动,解决了现有运动补偿模型对强视差背景补偿效果不好的问题.其次,在子块运动补偿模型参数求解时,通过引入自车运动参数简化模型参数个数,并结合直接方法求解,避免了传统基于特征点匹配方法求解参数时易受误匹配特征点影响的问题.然后,针对鱼眼相机的成像形变问题,本文提出了一种三平面校正方法获取鱼眼图像的子块运动补偿图像.最后,利用鱼眼图像的子块运动补偿图像和真实拍摄图像的差异信息实现运动目标检测.多种测试场景下的实验结果表明了本文方法的有效性.

关键词: 运动目标检测, 子块运动补偿, 单目视觉, 鱼眼相机

Abstract:

With its wide-angle imaging and information richness,the fish-eye camera has a brilliant prospect in application.This paper presents a moving object detection method for on-board monocular fish-eye cameras.Firstly,a sub-block motion compensation model is proposed to compensate image background motion,which solves the ineffective strong parallax scene compensation problem.Secondly,when it comes to solve the parameters of sub-block motion compensation model,ego-vehicle motion parameters are introduced to simplify the number of model parameters,and the direct method is used to avoid the problem that the traditional feature-point-based matching method is susceptible to mismatching feature points.Then for the image distortion problem,this paper proposes a three-plane rectification method to obtain sub-block motion compensation images.Finally,the moving object detection is realized using the difference between sub-block motion compensation images and captured images.Experimental results show the effectiveness of the proposed method.

Key words: moving object detection, sub-block motion compensation, monocular vision, fish-eye camera

中图分类号: