公开(公告)号：WO2014092550A3

公开(公告)日：2014-09-12

申请号：PCT/MY2013000264

申请日：2013-12-10

Applicant: MIMOS BERHAD

Inventor： BINTI KADIM ZULAIKHA ,  HON HOCK WOON ,  BINTI SAMUDIN NORSHUHADA

IPC: G06T7/20 ,  G06T7/00

CPC classification number: G06T7/285 ,  G06T7/194 ,  G06T7/246 ,  G06T7/75 ,  G06T2207/10021 ,  G06T2207/30232 ,  G06T2207/30244

Abstract: The present invention provides a method of processing sequence of image frames captured through an imaging device. The method comprises extracting feature points from a current frame of the sequence of the image frames; estimating disparity of the feature points; identifying an object from the current frame that occupies a large area of the current frame through the disparity of the feature points; matching feature points between the current image frame and a previous image frame to determine presence of a moving object; filtering out the matched feature points that correspond to the moving object to obtain matched feature points that correspond to background; estimating motion model based on the feature points that correspond to the background.

Abstract translation: 本发明提供了一种处理通过成像装置捕获的图像帧的序列的方法。 该方法包括从图像帧的序列的当前帧中提取特征点; 估计特征点的差异; 通过特征点的不均匀性来识别当前帧占据当前帧的大面积的对象; 在当前图像帧和先前图像帧之间匹配特征点以确定移动对象的存在; 滤除与移动对象相对应的匹配特征点，以获得对应于背景的匹配特征点; 基于与背景对应的特征点估计运动模型。