False Positive Removal for 3D Vehicle Detection with Penetrated Point Classifier

TL;DR

This paper introduces the Penetrated Point Classifier (PPC), a novel method that reduces false positives in 3D vehicle detection by leveraging LiDAR point properties, significantly improving precision at high recall levels.

Contribution

The paper proposes a new PPC method that effectively distinguishes false positives by analyzing penetrated points behind vehicles, enhancing detection accuracy.

Findings

Precision at high recall improved by over 14 percentage points.

Method evaluated on KITTI dataset shows significant false positive reduction.

Performance boost achieved over state-of-the-art PointRCNN.

Abstract

Recently, researchers have been leveraging LiDAR point cloud for higher accuracy in 3D vehicle detection. Most state-of-the-art methods are deep learning based, but are easily affected by the number of points generated on the object. This vulnerability leads to numerous false positive boxes at high recall positions, where objects are occasionally predicted with few points. To address the issue, we introduce Penetrated Point Classifier (PPC) based on the underlying property of LiDAR that points cannot be generated behind vehicles. It determines whether a point exists behind the vehicle of the predicted box, and if does, the box is distinguished as false positive. Our straightforward yet unprecedented approach is evaluated on KITTI dataset and achieved performance improvement of PointRCNN, one of the state-of-the-art methods. The experiment results show that precision at the highest recall position is dramatically increased by 15.46 percentage points and 14.63 percentage points on the moderate and hard difficulty of car class, respectively.