计算机科学 ›› 2011, Vol. 38 ›› Issue (5): 272-274.

• 图形图像 • 上一篇    下一篇

基于全自动生长分割的梯度彩色光流场计算

廖彬,杜明辉,胡金龙   

  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)(华南理工大学信息网络工程研究中心 广州510640)
  • 出版日期:2018-11-16 发布日期:2018-11-16
  • 基金资助:
    本文受国家自然科学基金(U0735004),国家科技支撑计划(2008BAH37H08)资助。

Gradient Field Optical Flow Estimation for Color Image Sequences Based on Automatic Growcut

LIAO Bin,DU Ming-hui,HU Jin-long   

  • Online:2018-11-16 Published:2018-11-16

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

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.

Key words: Optical flow, Growcut, Gradient field, Color images

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!