Journal article
CurveNet: Curvature-based multitask learning deep networks for 3D object recognition
IEEE/CAA Journal of Automatica Sinica, Vol.8(6), pp.1177-1187
2020
Abstract
In computer vision fields, 3D object recognition is one of the most important tasks for many real-world applications. Three-dimensional convolutional neural networks ( CNNs ) have demonstrated their advantages in 3D object recognition. In this paper, we propose to use the principal curvature directions of 3D objects ( using a CAD model ) to represent the geometric features as inputs for the 3D CNN. Our framework, namely CurveNet, learns perceptually relevant salient features and predicts object class labels. Curvature directions incorporate complex surface information of a 3D object, which helps our framework to produce more precise and discriminative features for object recognition. Multitask learning is inspired by sharing features between two related tasks, where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification. Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification. We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs. A Cross-Stitch module was adopted to learn effective shared features across multiple representations. We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task.
Details
- Title
- CurveNet: Curvature-based multitask learning deep networks for 3D object recognition
- Authors/Creators
- A.A.M. Muzahid (Author/Creator) - Shanghai UniversityW. Wan (Author/Creator) - Shanghai UniversityF. Sohel (Author/Creator) - Murdoch UniversityL. Wu (Author/Creator) - Shanghai UniversityL. Hou (Author/Creator) - Huangshan University
- Publication Details
- IEEE/CAA Journal of Automatica Sinica, Vol.8(6), pp.1177-1187
- Publisher
- IEEE
- Identifiers
- 991005540597307891
- Copyright
- © 2020 IEEE
- Murdoch Affiliation
- Information Technology, Mathematics and Statistics
- Language
- English
- Resource Type
- Journal article
Metrics
61 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- International collaboration
- Citation topics
- 4 Electrical Engineering, Electronics & Computer Science
- 4.17 Computer Vision & Graphics
- 4.17.2798 Stereo Depth Estimation
- Web Of Science research areas
- Automation & Control Systems
- ESI research areas
- Engineering