6D Object Pose Estimation in Cluttered Scenes from RGB Images  

作　　者：Xiao-Long Yang Xiao-Hong Jia Yuan Liang Lu-Bin Fan 杨小龙;贾晓红;梁缘;樊鲁宾(Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China;Alibaba DAMO Academy,Alibaba Group,Hangzhou 311121,China)

机构地区：[1]Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China [2]University of Chinese Academy of Sciences,Beijing 100049,China [3]Alibaba DAMO Academy,Alibaba Group,Hangzhou 311121,China

出　　处：《Journal of Computer Science & Technology》2022年第3期719-730,共12页计算机科学技术学报（英文版）

基　　金：the National Key Research and Development Program of China under Grant No.2021YFB1715900;the National Natural Science Foundation of China under Grant Nos.12022117 and 61802406;the Beijing Natural Science Foundation under Grant No.Z190004;the Beijing Advanced Discipline Fund under Grant No.115200S001;Alibaba Group through Alibaba Innovative Research Program.

摘　　要：We propose a feature-fusion network for pose estimation directly from RGB images without any depth information in this study.First,we introduce a two-stream architecture consisting of segmentation and regression streams.The segmentation stream processes the spatial embedding features and obtains the corresponding image crop.These features are further coupled with the image crop in the fusion network.Second,we use an efficient perspective-n-point(E-PnP)algorithm in the regression stream to extract robust spatial features between 3D and 2D keypoints.Finally,we perform iterative refinement with an end-to-end mechanism to improve the estimation performance.We conduct experiments on two public datasets of YCB-Video and the challenging Occluded-LineMOD.The results show that our method outperforms state-of-the-art approaches in both the speed and the accuracy.

关 键 词：two-stream network 6D pose estimation fusion feature 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]