|
|||||
|
|
| 基于全自动生长分割的梯度彩色光流场计算 | |
| 引用本文： | 廖彬,杜明辉,胡金龙.基于全自动生长分割的梯度彩色光流场计算[J].计算机科学,2011,38(5):272-274,300. |
| 作者姓名： | 廖彬 杜明辉 胡金龙 |
| 作者单位： | 1. 华南理工大学电子与信息学院,广州,510640;华南农业大学理学院数学系,广州,510640 2. 华南理工大学电子与信息学院,广州,510640 3. 华南理工大学信息网络工程研究中心,广州,510640 |
| 基金项目： | 本文受国家自然科学基金(U0735004)，国家科技支撑计划(2008BAH37H08)资助。 |
| 摘 要： | 形变物体边界的准确定位是光流估计的难点之一，仅依靠改进光流算法收效甚微。提出了全自动生长分割，以准确提取形变运动物体，从而将视频分割结果与梯度彩色光流算法相结合来提高光流法对形变物体的检测准确法度 |
| 关 键 词： | 光流，生长分割，图像梯度场，彩色图像 |
Gradient Field Optical Flow Estimation for Color Image Sequences Based on Automatic Growcut |
|
| LIAO Bin,DU Ming-hui,HU Jin-long.Gradient Field Optical Flow Estimation for Color Image Sequences Based on Automatic Growcut[J].Computer Science,2011,38(5):272-274,300. | |
| Authors: | LIAO Bin DU Ming-hui HU Jin-long |
| Affiliation: | (School of Electronic and Information Engineering,South China University of Technology,Guangzhou 510640,China)(Mathematics Department,South China Agriculture University,Guangzhou 510640,China)(Network Engineering and Research Center,South China University of Technology,Guangzhou 510640,China) |
| Abstract: | Detecting the boundaries of deformation objects is one of of the difficulties of optical flow estimation and it is hard to solve only using improved optical flow algorithms. Gradient field optical flow estimation for color image sequences based on automatic growcut was presented. It combined the segmented information with gradient field optical flow estimation to improve the detection accuracy for deformation objects. |
| Keywords: | Optical flow Growcut Gradient field Color images |
| 本文献已被 万方数据 等数据库收录！ | |
| 点击此处可从《计算机科学》下载全文 | |