计算机工程
計算機工程
계산궤공정
COMPUTER ENGINEERING
2015年
5期
254-258,263
,共6页
冀续烨%陈明%冯国富%赵海乐
冀續燁%陳明%馮國富%趙海樂
기속엽%진명%풍국부%조해악
目标提取%高斯混合模型%光线检测模型%场景状态检测模型%阴影检测模型%背景更新
目標提取%高斯混閤模型%光線檢測模型%場景狀態檢測模型%陰影檢測模型%揹景更新
목표제취%고사혼합모형%광선검측모형%장경상태검측모형%음영검측모형%배경경신
object extraction%Gaussian Mixture Model (GMM)%light detection model%scene state detection model%shadow detection model%background update
固定摄像机目标提取多以高斯混合模型为背景模型，在检测运动缓慢、间歇停滞的目标时会出现前景目标空洞的问题。为此，提出一种能够适应目标间歇停滞的多模型协同目标提取方法。采用高斯混合模型进行背景学习，通过光线检测模型和场景状态检测模型协同控制背景适时更新，利用阴影检测模型剔除阴影。实验结果表明，与KaewTraKulPong P方法相比，该方法能较完整地提取到目标轮廓，且单帧处理时间较少。
固定攝像機目標提取多以高斯混閤模型為揹景模型，在檢測運動緩慢、間歇停滯的目標時會齣現前景目標空洞的問題。為此，提齣一種能夠適應目標間歇停滯的多模型協同目標提取方法。採用高斯混閤模型進行揹景學習，通過光線檢測模型和場景狀態檢測模型協同控製揹景適時更新，利用陰影檢測模型剔除陰影。實驗結果錶明，與KaewTraKulPong P方法相比，該方法能較完整地提取到目標輪廓，且單幀處理時間較少。
고정섭상궤목표제취다이고사혼합모형위배경모형，재검측운동완만、간헐정체적목표시회출현전경목표공동적문제。위차，제출일충능구괄응목표간헐정체적다모형협동목표제취방법。채용고사혼합모형진행배경학습，통과광선검측모형화장경상태검측모형협동공제배경괄시경신，이용음영검측모형척제음영。실험결과표명，여KaewTraKulPong P방법상비，해방법능교완정지제취도목표륜곽，차단정처리시간교소。
Gaussian Mixture Model( GMM) is adopted to solve foreground detection problems. However,GMM can not detect objects in which do not move in the scene. This paper proposes the multi-model cooperative method to detect foreground objects in complex scene. Under the assumption that the camera is fixed,it first uses the adaptive GMM to build a background which is updated by the light detection model and the scene detection model. A shadow detection model is also used in this paper at last. It mades a comparison with two algorithms. Experimental results show that this method can completely extract the object contour,and single frame processing time is less.
