典型文献
Local Homography Estimation on User-Specified Textureless Regions
文献摘要：
This paper presents a novel deep neural network for designated point tracking(DPT)in a monocular RGB video,VideoInNet.More concretely,the aim is to track four designated points correlated by a local homography on a textureless planar region in the scene.DPT can be applied to augmented reality and video editing,especially in the field of video advertising.Existing methods predict the location of four designated points without appropriately considering the point correlation.To solve this problem,VideoInNet predicts the motion of the four designated points correlated by a local homography within the heatmap prediction framework.Our network refines the heatmaps of designated points through two stages.On the first stage,we introduce a context-aware and location-aware structure to learn a local homography for the designated plane in a supervised way.On the second stage,we introduce an iterative heatmap refinement module to improve the tracking accuracy.We propose a dataset focusing on textureless planar regions,named ScanDPT,for training and evaluation.We show that the error rate of VideoInNet is about 29％lower than that of the state-of-the-art approach when testing in the first 120 frames of testing videos on ScanDPT.
文献关键词：
中图分类号：
作者姓名：
Zheng Chen;Xiao-Nan Fang;Song-Hai Zhang
作者机构：
Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China
文献出处：
引用格式：
[1]Zheng Chen;Xiao-Nan Fang;Song-Hai Zhang-.Local Homography Estimation on User-Specified Textureless Regions)[J].计算机科学技术学报（英文版）,2022(03):615-625
A类：
Specified,Textureless,VideoInNet,homography,textureless,heatmaps,ScanDPT
B类：
Local,Homography,Estimation,User,Regions,This,paper,presents,novel,deep,neural,network,designated,tracking,monocular,RGB,More,concretely,aim,four,points,correlated,by,local,planar,scene,be,applied,augmented,reality,editing,especially,field,advertising,Existing,methods,location,without,appropriately,considering,correlation,To,solve,this,problem,predicts,motion,within,prediction,framework,Our,refines,through,stages,On,first,introduce,context,aware,structure,learn,plane,supervised,way,second,iterative,refinement,module,improve,accuracy,We,propose,dataset,focusing,regions,named,training,evaluation,show,that,error,rate,about,lower,than,state,art,approach,when,testing,frames,videos
AB值：
0.496806
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
