Paper Info
Title
Aspp-Df-Pvnet: Atrous Spatial Pyramid Pooling And Distance-Filtered Pvnet For Occlusion Resistant 6d Estimation
Abstract
Detecting objects and estimating their 6D poses from a single RGB image is quite challenging under severe occlusions. Recently, vector-field based methods have shown certain robustness to occlusion and truncation. Based on the vector-field representation, applying voting strategy to localize 2D keypoints can further reduce the influence of outliers. To improve the effectiveness of vector-field based deep network and voting scheme, we propose Atrous Spatial Pyramid Pooling and Distance-Filtered PVNet (ASPP-DF-PVNet), an occlusion resistant framework for 6D object pose estimation. ASPP-DF-PVNet utilizes the effective Atrous Spatial Pyramid Pooling (ASPP) module of Deeplabv3 to capture multi-scale features and encode global context information, which improves the accuracy of segmentation and vector-field prediction comparing to the original PVNet, especially under severe occlusions. Considering that the distances between pixels and keypoint hypotheses will affect the voting deviations, we then present a distance-filtered voting scheme which takes the voting distances into consideration to filter out the votes with large deviations. Experiments demonstrate that our method outperforms the state-of-the-art methods by a considerable margin without using pose refinement, and obtains competitive results against the methods with refinement on the LINEMOD and Occlusion LINEMOD datasets.
Year
DOI
Venue
2021
10.1016/j.image.2021.116268
SIGNAL PROCESSING-IMAGE COMMUNICATION
Keywords
DocType
Volume
6D object pose estimation, Vector fields, Voting based keypoint localization, Semantic segmentation, ASPP
Journal
95
ISSN
Citations 
PageRank 
0923-5965
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Yazhi Zhu100.34
Li-Li Wan2157.72
Wanru Xu34714.23
Shenghui Wang457.69