Three-frame corner matching and moving object extraction in a sequence of images

Computer Vision, Graphics, and Image Processing Pub Date : 1990-11-01 DOI:10.1016/0734-189X(90)90055-Z

Hsi-Jian Lee, Hsi-Chou Deng

{"title":"Three-frame corner matching and moving object extraction in a sequence of images","authors":"Hsi-Jian Lee, Hsi-Chou Deng","doi":"10.1016/0734-189X(90)90055-Z","DOIUrl":null,"url":null,"abstract":"<div><p>This paper presents a three-frame matching method for finding the correspondences of corner points. After a two-stage corner detector is applied to each frame to extract a set of corner points as the matching primitives, candidate transition paths, which are formed by three corner points among three consecutive corner sets, are found by utilizing the smoothness constraint of motion due to inertia. Initially, each transition path is assigned an initial probability of being correct transition based on the similarity of curvatures of the three corner points. These probabilities are iteratively modified by a relaxation process according to the consistency properties of both acceleration and velocity. After several iterations, the paths with sufficiently high probabilities are taken as the correct transition paths. A new segmentation process which integrates both velocity and contrast information is presented to extract regions of moving objects. Several experimental results show that the approach is very effective.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 2","pages":"Pages 210-238"},"PeriodicalIF":0.0000,"publicationDate":"1990-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90055-Z","citationCount":"13","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision, Graphics, and Image Processing","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/0734189X9090055Z","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 13

Abstract

This paper presents a three-frame matching method for finding the correspondences of corner points. After a two-stage corner detector is applied to each frame to extract a set of corner points as the matching primitives, candidate transition paths, which are formed by three corner points among three consecutive corner sets, are found by utilizing the smoothness constraint of motion due to inertia. Initially, each transition path is assigned an initial probability of being correct transition based on the similarity of curvatures of the three corner points. These probabilities are iteratively modified by a relaxation process according to the consistency properties of both acceleration and velocity. After several iterations, the paths with sufficiently high probabilities are taken as the correct transition paths. A new segmentation process which integrates both velocity and contrast information is presented to extract regions of moving objects. Several experimental results show that the approach is very effective.

查看原文本刊更多论文

序列图像中三帧角匹配与运动目标提取

提出了一种寻找角点对应关系的三帧匹配方法。对每一帧应用两级角点检测器提取一组角点作为匹配原语，利用惯性运动的平滑性约束，找到由三个连续角点集合中的三个角点组成的候选过渡路径。首先，根据三个角点曲率的相似性，为每条过渡路径分配一个正确过渡的初始概率。根据加速度和速度的一致性，通过松弛过程对这些概率进行迭代修正。经过多次迭代，选取概率足够高的路径作为正确的过渡路径。提出了一种结合速度信息和对比度信息的运动目标区域分割方法。实验结果表明，该方法是非常有效的。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Computer Vision, Graphics, and Image Processing

自引率

0.00%

发文量