针对静态背景下的背景差法，通过研究如何得到、以及如何及时更新背景模型，增强运动目标检测随环境变化的鲁棒性，提出了多级分块的背景估计方法。
Background estimation based on block is proposed to solve the problem of building background model and updating background which can enhance the robust of moving object detection.
借助于图像运动的变阶参数模型和鲁棒回归分析，提出一种基于运动分割的图像运动估计方法。
A motion based segmentation scheme for image motion estimation is proposed using variable order parameterized models of image motion and robust regression.
该文在分析光流模型约束条件的基础上，提出了一种鲁棒的多分辨率光流估计方法，并对光流应用于目标检测的一些实际问题进行了探讨。
Based on the detail analysis of optical flow model, a robust multi-resolution estimation approach of optical flow is proposed, and some practical problems are also discussed on target detection.
应用推荐