Detection of Condensed Vehicle Gas Exhaust in LiDAR Point Clouds

TL;DR

This paper introduces a novel two-step method for detecting condensed vehicle gas exhaust in LiDAR point clouds, addressing a specific adverse weather effect that impacts autonomous vehicle perception.

Contribution

The paper presents a new approach for identifying vehicle gas exhaust in LiDAR data without relying on large labeled datasets, combining emission area detection and temporal cloud modeling.

Findings

Reliable detection of gas exhaust in urban LiDAR data

Effective for offline pre-labeling and online ghost object detection

Works across different scenarios

Abstract

LiDAR sensors used in autonomous driving applications are negatively affected by adverse weather conditions. One common, but understudied effect, is the condensation of vehicle gas exhaust in cold weather. This everyday phenomenon can severely impact the quality of LiDAR measurements, resulting in a less accurate environment perception by creating artifacts like ghost object detections. In the literature, the semantic segmentation of adverse weather effects like rain and fog is achieved using learning-based approaches. However, such methods require large sets of labeled data, which can be extremely expensive and laborious to get. We address this problem by presenting a two-step approach for the detection of condensed vehicle gas exhaust. First, we identify for each vehicle in a scene its emission area and detect gas exhaust if present. Then, isolated clouds are detected by modeling through time the regions of space where gas exhaust is likely to be present. We test our method on real urban data, showing that our approach can reliably detect gas exhaust in different scenarios, making it appealing for offline pre-labeling and online applications such as ghost object detection.