Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding
This is an incremental improvement for 3D object detection in autonomous driving or robotics.
The paper tackles 3D object detection in point clouds by enhancing Frustum PointNet with local neighborhood embedding to compute point features based on neighbors, achieving better performance than the baseline.
We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed method considers the point neighborhood when computing point features. The newly introduced local neighborhood embedding operation mimics the convolutional operations in 2D neural networks. Thus features of each point are not only computed with the features of its own or of the whole point cloud but also computed especially with respect to the features of its neighbors. Experiments show that our proposed method achieves better performance than the F-Pointnet baseline on 3D object detection tasks.