Search

Shape representation for 3D models is an important topic in computer vision, multimedia analysis, and computer graphics. Recent multiview-based methods demonstrate promising performance for 3D model recognition and retrieval. However, most of the multiview-based methods focus on the visual information from the taken views and ignore correlation information among these views, which means the similarity and differentiation of multiple views have lost in their methods. In order to address this issue, we propose a novel two-stream network architecture for 3D model recognition and retrieval. The proposed network includes two sub-networks: a multi-view convolutional neural network (MVCNN) that extracts the view information from the taken views, and an Visual Saliency model that defines the weight of views based on the similarity and differentiation information of multiple views. Special, the weight of views defined by the Visual Saliency model can effectively be used to guide the visual information fusion in MVCNN model. This design can make the MVCNN model save visual information and the correlation information of these views in the learning step. Finally, we employ early-fusion method to fuse the feature vectors from MVCNN model and Visual Saliency model respectively, to generate the shape descriptor for 3D model recognition and retrieval. The experimental result on two public datasets, ModelNet40 and ShapeNetCore55, demonstrates the correlation information of multiple views is crucial for view-based 3D model recognition methods and the proposed method can achieve the state-of-the-art performance on both 3D object classification and retrieval.

Cross-media 3D model recognition is an important and challenging task in computer vision, which can be utilized in many applications such as landmark detection, image set classification, etc. In recent years, with the development of deep learning, many approaches have been proposed to handle the 3D model recognition problem. However, all of these methods focus on the structure information representation and the multi-view information fusion, and ignore the spatial and temporal information. So that it is not suitable for the cross-media 3D model recognition. In this paper, we utilize the sequence views to represent each 3D model and propose a novel Multi-view Convolutional LSTM Network (MVCLN), which utilizes the LSTM structure to extract temporal information and applies the convolutional operation to extract spatial information. More especially, the spatial and temporal information both are considered during the training process, which can effectively utilize the differences between the view's spatial information to improve the final performance. Meanwhile, we also introduce the classic attention model to define the weight of each view, which can reduce the redundant information of view's spatial information in the information fusion step. We evaluate the proposed method on the ModelNet40 for 3D model classification and retrieval task. We also construct a dataset utilizing the overlap categories of MV-RED, ShapenetCore and ModelNet to demonstrate the effectiveness of our approach for the cross-media 3D model recognition. Experimental results and comparisons with the state-of-the-art methods demonstrate that our framework can achieve superior performance.

This paper is mainly devoted to a distributed iterative learning control design for a class of nonlinear discrete-time multi-agent systems in the presence of randomly varying iteration lengths. A stochastic variable is introduced and utilized to construct a consensus error with iteration-varying lengths. The distributed ILC law using the consensus error term is considered, contraction mapping and λ-norm technique methods are employed to develop a sufficient condition for the asymptotic stability of ILC. It is shown that all agents can be guaranteed to achieve finite-time tracking with randomly varying iteration lengths, even under the condition that the desired trajectory is available to not all, but only a portion of agents. The proposed algorithm is also extended to achieve consensus control for switching topologies multi-agent systems with iteration-varying lengths. Two illustrative examples are given to demonstrate the effectiveness of the theoretical results.

The deformation compatibility relationship of the general contact object under external normal force and the single secondary internal gear pairs of involute RV reducer under a load torque is derived. By transforming the deformation coordination relationship into a linear programming form, a mathematical model for the analysis of the single secondary internal gear pairs with the tooth surface contact of the involute RV reducer is established. An improved simplex method is used to solve the linear programming problem. The calculation results are compared with the ANSYS simulation values from the three aspects of contact tooth pairs, gear tooth load and tooth surface contact force. The results show that the values obtained by the two methods are almost the same on the contact tooth pairs and the tooth load. In terms of tooth surface contact force, the contact area calculated using the finite element linear programming method is slightly smaller than the ANSYS results, but most of the errors are below 12%, indicating that the tooth surface contact conditions obtained using the two calculation methods are consistent. The accuracy and effectiveness of the finite element-linear programming method are thus verified.