Authors:
Joy Mazumder
1
;
2
;
Mohsen Zand
1
;
2
;
Sheikh Ziauddin
1
;
2
and
Michael Greenspan
1
;
2
;
3
Affiliations:
1
Department of Electrical and Computer Engineering, Queen’s University, Kingston, Ontario, Canada
;
2
Ingenuity Labs, Queen’s University, Kingston, Ontario, Canada
;
3
School of Computing, Queen’s University, Kingston, Ontario, Canada
Keyword(s):
Surface Registration, 3D Object Recognition, Validation, Shared mlp Network.
Abstract:
This paper proposes a novel deep learning architecture called ValidNet to automatically validate 3D surface registration algorithms for object recognition and pose determination tasks. The performance of many tasks such as object detection mainly depends on the applied registration algorithms, which themselves are susceptible to local minima. Revealing this tendency and verifying the success of registration algorithms is a difficult task. We treat this as a classification problem, and propose a two-class classifier to distinguish clearly between true positive and false positive instances. Our proposed ValidNet deploys a shared mlp architecture which works on the raw and unordered numeric data of scene and model points. This network is able to perform two fundamental tasks of feature extraction and similarity matching using the powerful capability of deep neural network. Experiments on a large synthetic datasets show that the proposed method can effectively be used in automatic valida
tion of registration.
(More)