An aerial point cloud classification using point transformer via multi-feature fusion.

7 , it can be seen that under the multi-feature strategy, the overall metrics mIoU, mAcc, and OA show an increasing trend in the sequence of adding L λ , P λ , S λ , and C λ .

also in 63,971 other papers

ded to the network is able to achieve a significant improvement in the classification accuracy of the features that were originally extracted with low accuracy; Ground, Vegetation, Building, Water also improved the classification accuracy when adding geometric features, Wall and Traffic Road showed a decreasing trend in classification accuracy when adding four features; Rail and Bike were not detected.

also in 47,180 other papers