CAJ | 학술논문

针对复杂环境中道路背景图像的快速获取问题，提出了一种快速有效的道路背景提取和更新算法。应用改进的多帧平均算法提取背景，采用改进的Surendra算法对背景进行更新。实验结果表明，该算法能够减轻初始静止车辆对背景建立的影响，能及时消除由于初始帧中目标移动而造成的鬼影，对光线变化鲁棒性高、速度快、更新效果好。
침대복잡배경중도로배경도상적쾌속획취문제，제출료일충쾌속유효적도로배경제취화경신산법。응용개진적다정평균산법제취배경，채용개진적Surendra산법대배경진행경신。실험결과표명，해산법능구감경초시정지차량대배경건립적영향，능급시소제유우초시정중목표이동이조성적귀영，대광선변화로봉성고、속도쾌、경신효과호。
Aiming at the problem of fast extracting road background image in complex scenes, an effective algorithm about road background extraction and updating is presented. An improved algorithm for time averaged background images （TABI） is used to the background extraction, then an improved surendra algorithm is applied to the background updating. Experimental results show that the proposed algorithm can reduce the influence of initial static vehicle on the background extraction and eliminate in time the ghosts caused by the motion of objects in the initial frame. The proposed algorithm is robust under lighting variations,fast in speed and satisfactory in updating performance.