彩色圖像序列中運(yùn)動(dòng)目標(biāo)外輪廓的自動(dòng)提取
Contour Extraction of Moving Objects in Color Image Sequences
-
摘要: 該文提出了一種新的多運(yùn)動(dòng)目標(biāo)精確外輪廓自動(dòng)提取算法。算法的主要?jiǎng)?chuàng)新點(diǎn)是：采用指數(shù)濾波計(jì)算彩色圖像的梯度強(qiáng)度，改善了彩色圖像梯度局部極值點(diǎn)的定位精度，所得到的梯度強(qiáng)度和運(yùn)動(dòng)邊緣位置信息供隨后的輪廓迭代中使用，成功地避免了動(dòng)態(tài)輪廓的過收縮。此外，充分利用輪廓的方向信息，又有效地克服了動(dòng)態(tài)輪廓迭代中的外擴(kuò)展。從而，算法自動(dòng)地提取出一個(gè)真正緊貼的目標(biāo)外輪廓。分析和實(shí)驗(yàn)表明，該算法抗干擾能力強(qiáng)，對(duì)復(fù)雜背景及不重疊物體，可以精確定位并提取出各個(gè)運(yùn)動(dòng)目標(biāo)的外輪廓。Abstract: A new algorithm to extract accurate contours of multiple moving objects is proposed in this paper. The main contributions of this paper include two parts: firstly, exponential filter is used to calculate the gradient magnitude of color image and the localization accuracy of local maximum of gradient in color image is increased, the gradient magnitude and the motion edges are used subsequently in contour iteration to prevent the contour from shrinking successfully; secondly, the directions of contour are used to prevent the active contour from expanding effectively. As a result, the real compact contours would be extracted automatically by using this algorithm. The experiments show the high efficiency of this algorithm for contours extraction of moving objects from color image sequence with complex background.
-
Kass M, Witkin A, Terzopoulos D. Snake: Active contour models[J].International Journal of Computer Vision.1988, 1(4):321-331[2]Rhee P K, La C W. Boundary extraction of moving objects from image sequence. Proc. of the IEEE Region 10 Conference TENCON99, Cheju-Korea, 1999, 1(15-17): 621-624.[3]Kim Munchurl, Choi Jae Gark, Kim Daehee, Lee Hyung, Lee Myoung Ho, Ahn Chieteuk, Ho Yo-Sung. A VOP generation tool: Automatic segmentation of moving objects in image sequences based on spatio-temporal information[J].IEEE Trans.on Circuit and System for Video Technology.1999, 9( 8):1216-1226[4]Cucchiara R, Grana C, Piccardi M, Prati A. Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2003, 25(10):[5]37-1342.[6]Williams D J, Shah M. A fast algorithm for active contours and curvature estimation. CVGIP: Image understanding, 1991, 55(1): 14-26.[7]Amini A, Whemouth T, Jain R. Using dynamic programming for solving variational problems in vision[J].IEEE Trans. on Pattern Analysis and Machine Intelligence.1990, 12(9):855-867[8]李玉山, 楊莉, 劉洋, 張大樸. 多個(gè)運(yùn)動(dòng)物體的外輪廓自動(dòng)提取.智能視覺監(jiān)測(cè)研究進(jìn)展，北京：科學(xué)出版社，2003: 87-91.[9]Shen Jun.[J].Castan S. An optimal linear operator for edge detection. Proc, CVPR86, Miami.1986,:- -
計(jì)量
- 文章訪問數(shù): 2155
- HTML全文瀏覽量: 106
- PDF下載量: 1256
- 被引次數(shù): 0
下載:
