Loading...
Please wait, while we are loading the content...
Similar Documents
MLNet: Multi-level Classification Network
| Content Provider | Scilit |
|---|---|
| Author | Xue, Doudou Cheng, Yinglei Wen, Pei Zhang, Liyin |
| Copyright Year | 2021 |
| Description | Journal: Journal of Physics: Conference Series The point cloud classification network only uses point cloud structure features or edge features to construct the feature vector, so that the classification accuracy is low. To solve this problem, this paper proposes a multi-level classification network. First, the original point cloud is divided into small samples using the preprocessing algorithm to obtain batch input and improve training efficiency; then construct structural features and edge features for point cloud feature extraction, and obtain local fine-grained descriptions through multi-level expressions within and between points; then design a convolutional neural network for feature learning. With the deepening of the network level, the degree of feature abstraction level is higher and higher, and the degree of distinction increases, so as to effectively improve the accuracy. Using the Vaihingen dataset to test the MLMS-Net network, the accuracy rate reached 85.4%. |
| Related Links | https://iopscience.iop.org/article/10.1088/1742-6596/1748/3/032038/pdf |
| ISSN | 17426588 |
| e-ISSN | 17426596 |
| DOI | 10.1088/1742-6596/1748/3/032038 |
| Journal | Journal of Physics: Conference Series |
| Issue Number | 3 |
| Volume Number | 1748 |
| Language | English |
| Publisher | IOP Publishing |
| Publisher Date | 2021-01-28 |
| Access Restriction | Open |
| Subject Keyword | Journal: Journal of Physics: Conference Series Cybernetical Science Point Cloud Classification Network Edge Features |
| Content Type | Text |
| Resource Type | Article |
| Subject | Physics and Astronomy |
