A multiclass TrAdaBoost transfer learning algorithm for the classification of mobile lidar data

Hanxian He, Kourosh Khoshelham, Clive Fraser

Research output: Contribution to journalArticleResearchpeer-review

22 Citations (Scopus)


A major challenge in the application of state-of-the-art deep learning methods to the classification of mobile lidar data is the lack of sufficient training samples for different object categories. The transfer learning technique based on pre-trained networks, which is widely used in deep learning for image classification, is not directly applicable to point clouds, because pre-trained networks trained by a large number of samples from multiple sources are not available. To solve this problem, we design a framework incorporating a state-of-the-art deep learning network, i.e. VoxNet, and propose an extended Multiclass TrAdaBoost algorithm, which can be trained with complementary training samples from other source datasets to improve the classification accuracy in the target domain. In this framework, we first train the VoxNet model with the combined dataset and extract the feature vectors from the fully connected layer, and then use these to train the Multiclass TrAdaBoost. Experimental results show that the proposed method achieves both improvement in the overall accuracy and a more balanced performance in each category.

Original languageEnglish
Pages (from-to)118-127
Number of pages10
JournalISPRS Journal of Photogrammetry and Remote Sensing
Publication statusPublished - Aug 2020
Externally publishedYes


  • 3DCNN
  • Deep learning
  • Multiclass classification
  • Point Cloud
  • TrAdaBoost
  • Transfer learning
  • VoxNet

Cite this