已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Image Matching by Bare Homography

单应性 人工智能 成对比较 匹配(统计) 计算机视觉 相似性(几何) 数学 模式识别(心理学) 仿射变换 计算机科学 修剪 平面的 图像(数学) 几何学 统计 投射试验 计算机图形学(图像) 生物 射影空间 农学
作者
Fabio Bellavia
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:33: 696-708 被引量:7
标识
DOI:10.1109/tip.2023.3346682
摘要

This paper presents Slime, a novel non-deep image matching framework which models the scene as rough local overlapping planes. This intermediate representation sits in-between the local affine approximation of the keypoint patches and the global matching based on both spatial and similarity constraints, providing a progressive pruning of the correspondences, as planes are easier to handle with respect to general scenes. Slime decomposes the images into overlapping regions at different scales and computes loose planar homographies. Planes are mutually extended by compatible matches and the images are split into fixed tiles, with only the best homographies retained for each pair of tiles. Stable matches are identified according to the consensus of the admissible stereo configurations provided by pairwise homographies. Within tiles, the rough planes are then merged according to their overlap in terms of matches and further consistent correspondences are extracted. The whole process only involves homography constraints. As a result, both the coverage and the stability of correct matches over the scene are amplified, together with the ability to spot matches in challenging scenes, allowing traditional hybrid matching pipelines to make up lost ground against recent end-to-end deep matching methods. In addition, the paper gives a thorough comparative analysis of recent state-of-the-art in image matching represented by end-to-end deep networks and hybrid pipelines. The evaluation considers both planar and non-planar scenes, taking into account critical and challenging scenarios including abrupt temporal image changes and strong variations in relative image rotations. According to this analysis, although the impressive progress done in this field, there is still a wide room for improvements to be investigated in future research.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
gjww发布了新的文献求助30
1秒前
星火完成签到,获得积分10
2秒前
张欢馨应助晴天采纳,获得10
5秒前
6秒前
8秒前
斯文败类应助zf采纳,获得10
10秒前
杨啸林完成签到 ,获得积分10
11秒前
11秒前
活力鑫磊发布了新的文献求助10
14秒前
zf完成签到,获得积分10
16秒前
L_Gary完成签到 ,获得积分10
17秒前
路豐遙应助明亮的落地窗采纳,获得10
19秒前
20秒前
21秒前
刘荣鑫完成签到 ,获得积分10
21秒前
青衫完成签到 ,获得积分0
22秒前
22秒前
22秒前
SiboN完成签到,获得积分10
23秒前
Yue完成签到 ,获得积分10
24秒前
25秒前
27秒前
团子呀完成签到 ,获得积分10
28秒前
科研通AI6.4应助Jelly采纳,获得10
28秒前
俊逸绮玉发布了新的文献求助10
29秒前
gjww发布了新的文献求助30
32秒前
詹国丹完成签到 ,获得积分10
35秒前
aa关闭了aa文献求助
36秒前
36秒前
123发布了新的文献求助10
41秒前
欣喜越泽完成签到,获得积分10
43秒前
安详的迎丝完成签到 ,获得积分10
43秒前
TAT完成签到 ,获得积分10
45秒前
yipmyonphu完成签到,获得积分0
46秒前
完美世界应助傲娇擎汉采纳,获得10
47秒前
鱼鱼完成签到 ,获得积分10
47秒前
wzm发布了新的文献求助20
48秒前
50秒前
随风沙ZYX完成签到 ,获得积分10
50秒前
清脆的芒果完成签到,获得积分10
50秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
China Pluperfect I: Epistemology of Past and Outside in Chinese Art 520
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
Cosmos as Art Object: Studies in Plato's Timaeus and Other Dialogues 500
What is the Future of Psychotherapy in Digital Age? Technology, AI Bots, and Psychotherapy after Covid 444
Management and the Arts 310
Teaching Social and Emotional Learning in Physical Education 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7633224
求助须知:如何正确求助?哪些是违规求助? 9207529
关于积分的说明 19747543
捐赠科研通 7202109
什么是DOI,文献DOI怎么找? 3274916
关于科研通互助平台的介绍 2436834
邀请新用户注册赠送积分活动 2271747