About this document

False Positive Reduction in 3D Vehicle Detection by Asil Asila is a document available to read on EtoBox.

1. The document proposes a method called a Penetrated Point Classifier (PPC) to remove false positive vehicle detections by leveraging the property that LiDAR points cannot pass through objects. 2. The PPC determines if any points exist behind a predicted vehicle box, which would indicate penetration and a false positive. 3. In experiments on the KITTI dataset, the PPC significantly improved precision at high recall levels for vehicle detection, removing many false positives while preserving true detecti

Author

Asil Asila

Language

EN