False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation

TL;DR

This paper introduces LidarMetaSeg, a post-processing tool that estimates the quality of LiDAR point cloud segmentation segments and predicts false positives without ground truth, improving over standard methods.

Contribution

The paper presents a novel meta classification and regression approach for segmentwise false positive detection and quality estimation in LiDAR segmentation.

Findings

Outperforms standard approaches in false positive detection

Accurately predicts segmentwise intersection over union

Works across different models and datasets

Abstract

We present a novel post-processing tool for semantic segmentation of LiDAR point cloud data, called LidarMetaSeg, which estimates the prediction quality segmentwise. For this purpose we compute dispersion measures based on network probability outputs as well as feature measures based on point cloud input features and aggregate them on segment level. These aggregated measures are used to train a meta classification model to predict whether a predicted segment is a false positive or not and a meta regression model to predict the segmentwise intersection over union. Both models can then be applied to semantic segmentation inferences without knowing the ground truth. In our experiments we use different LiDAR segmentation models and datasets and analyze the power of our method. We show that our results outperform other standard approaches.