基于信息融合的視頻序列圖像中運動目標(biāo)分割的研究
Studies on Moving Object Segmentation Based on Information Fusion in Video Sequences
-
摘要: 該文提出一種基于信息融合的方法分割視頻序列圖像運動目標(biāo)。在彩色圖像分割中，將部分空間信息介入到迭代均值偏移過程，實現(xiàn)無參數(shù)聚類。然后利用所提出的求等同標(biāo)志連通區(qū)域的方法，將聚類后的圖像劃分成不同的獨立區(qū)域；再利用HOS(高階統(tǒng)計)方法進行運動檢測，經(jīng)后處理，得到運動目標(biāo)粗模板。統(tǒng)計這個運動粗模板中等同顏色區(qū)域占原圖像相應(yīng)獨立區(qū)域的比重，比重超過預(yù)置閾值的，則將該獨立區(qū)域作為待融合區(qū)域。最后，將所有的待融合區(qū)域連接起來，就構(gòu)成了運動目標(biāo)模板。
-
關(guān)鍵詞:
- 密度梯度估計; 均值偏移過程; 高階統(tǒng)計量
Abstract: A method extracting moving object is proposed by utilizing the information fusion. Color image segmentation primarily uses a non-parametric clustering method based on partial space information intervening iterative mean shift procedure. A way of finding connected areas with identical marks is introduced to divide the image into different independent areas. HOS(Higher-Order Statistics) is used for motion detection. Then through post-processing, A rough motion template can be got. In such a template, the ratio of regions with identical marks to the corresponding independent region in the original image can be computed. If the ratio is larger than a predetermined threshold, the corresponding independent region will be fused. Finally, the moving object can be extracted by fusing all the predetermined regions to be fused. -
計量
- 文章訪問數(shù): 2180
- HTML全文瀏覽量: 87
- PDF下載量: 687
- 被引次數(shù): 0
下載:
