用于視頻對(duì)象平面生成的運(yùn)動(dòng)對(duì)象自動(dòng)分割
GENERATING VIDEO OBJECT PLANE BY AUTOMATIC SEGMENTATION OF MOVING OBJECTS
-
摘要: 新的視頻編碼標(biāo)準(zhǔn)MPEG-4具有基于內(nèi)容的功能。它把圖像序列分解成視頻對(duì)象平面(VOP),每個(gè)VOP代表一個(gè)運(yùn)動(dòng)對(duì)象。文中提出了一種提取運(yùn)動(dòng)對(duì)象的新的視頻序列分割算法,算法的核心是一個(gè)對(duì)象跟蹤器,它利用Hausdorff距離將對(duì)象的二維二值模型與后續(xù)幀進(jìn)行匹配,然后采用一種新的基于運(yùn)動(dòng)相連成分的模型刷新方法對(duì)模型的每一幀進(jìn)行刷新。初始的模型自動(dòng)產(chǎn)生,再利用濾波技術(shù)濾除靜止背景,最后,利用二值模型從序列中提取出VOP。
-
關(guān)鍵詞:
- MPEG-4; 視頻對(duì)象平面; 對(duì)象跟蹤; 視頻序列分割
Abstract: The new video coding standard MPEG4 is enabling content-based functionality. It decomposes sequences into video object planes (VOPs) so that each VOP represents one moving object. This paper presents a new automatic video sequence segmentation algorithm that extracts moving objects. The core of this algorithm is an object tracker that matches a two-dimensional binary model of the object against subsequent frames using the Hausdorff distance. The initial model is derived automatically and a new model update method based on the concept of the moving connected components is proposed. The stationary background is removed by a filtering technique. Finally, the VOPs are extracted from the binary model sequence. -
R. Mech, M. Wollborn, A nice roust method for segmentation of moving objects in video sequences, in IEEE Int. Conf. Acoust., Speech, Signal Processing, ICASSP97 Munich, Germany,1997, 4(4), 2657-2660.[2]R. Mech, P. Gerken, Automatic segmentation of moving objects(partial results of core experimentn2) in ISO/IEC JTCI/SC29/WG11MPEG97/m1949, Bristol, U.K., Apr., 1997. ［3］G. Adiv, Determining three-dimensional motion and structure from optical flow generated by several moving objects, IEEE Trans. on Pattern Anal. Machine Intell., 1985, 7(7), 384-401.[3]J. Canny, A computational approach to edge detection, IEEE Irans. on Pattern Anal. Machine Intell., 1986, 8(11), 679 698. -
計(jì)量
- 文章訪(fǎng)問(wèn)數(shù): 2178
- HTML全文瀏覽量: 115
- PDF下載量: 439
- 被引次數(shù): 0
下載:
