Background Subtraction and Frame Difference Based Moving Obiect Detection for Real-Time Surveillance

A new real-time algorithm is proposed in this paper for detecting moving object in color image sequences taken from stationary cameras. This algorithm combines a temporal difference with an adaptive background subtraction where the combination is novel. When changes occur, the background is automatically adapted to suit the new conditions. For the background model, a new model is proposed with each frame decomposed into regions and the model is based not only upon single pixel but also on the characteristic of a region. The hybrid presentation includes a model for single pixel information and a model for the pixel's neighboring area information.This new model of background can both improve the accuracy of segmentation due to that spatial information is taken into account and saliently speed up the processing procedure because portion of neighboring pixel can be selected into modeling. The algorithm was successfully used in a video surveillance system and the experiment result shows it can obtain a clearer foreground than the single frame difference or background subtraction method.     

基于网络最大流的立体匹配算法

为得到立体图像对的全局最优匹配,将视差搜索范围离散化,与图像坐标一起构成三维空间网络。恰当定义网络各边的容量,使之兼顾立体匹配的相容性和光滑性约束,将立体匹配转化为网络优化问题。通过求解网络的最大流和最小切割,获得全局最优的视差分布数据。实验表明,算法生成的视差数据不仅连续稠密而且保留了细节信息。     

Motion Geometric Active Contours： Tracking Nonrigid Objects in Clutter Background

MGAC (Motion Geometric Active Contours), a new variational framework of geometric active contours to track multiple nonrigid moving object‘s in the clutter background in image sequences is presented. This framework, incorporating with the motion edge information, consists of motion detection and tracking stages. At the motion detection stage, the motion edge map provides an approximate edge map of the moving objects. Then, a tracking stage, merely using thestatic edge information, is considered to improve the motion detection result. Force field regularization method is used to extend the capture range of the edge attraction force field in both stages.Experiments demonstrate that the proposed framework is valid for tracking multiple nonrigid objects in the clutter background.     

Background Subtraction and Frame Difference Based Moving Object Detection for Real-Time Surveillance

A new real-drie algorithm is proposed in this paperfor detecting moving object in color image sequencestaken from stationary cameras. This algorithmcombines a temporal difference with an adaptivebackground subtraction where the combination isnovel. When changes occur, the background isautomatically adapted to suit the new conditions. Forthe background model, a new model is proposed witheach frame decomposed into regions and the model isbased not only upon single pixel but also on the     

矩形箱梁力学性能分析的修正计算方法

本文对矩形箱梁翼板设置了不同的剪滞翘曲位移差函数,继而综合考虑剪力滞效应、剪切变形以及剪滞翘曲应力和弯矩自平衡条件等因素,且以能量变分原理为基础建立了矩形箱梁的弹性控制微分方程和自然边界条件,基于此修正了现行薄壁结构分析方法。与传统剪滞理论相比,本文方法深刻反映了矩形箱梁的力学特性。研究表明,(1)由于剪滞翘曲应力和弯矩自平衡条件的引入,矩形箱梁力学性能分解为独立的初等梁理论和剪滞理论体系,且箱梁力学性能为两者的叠加效应;(2)矩形箱梁断面尺寸确定,剪滞效应对其正应力的影响值不变,即剪滞效应的竖向力学行为与箱梁跨径无关;(3)尽管矩形箱梁的梁高对箱形梁剪滞翘曲应力和初等梁理论的应力值皆有一定影响,但其剪力滞系数不变,因此剪力滞效应与梁高无关;(4)剪力滞效应不仅影响箱梁翼板力学性能,而且对其腹板力学行为的影响不可忽视。因而,与传统剪滞理论相比,本文修正法不仅计算精度明显提高,而且更能真实反映矩形箱梁的力学性能。