Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection

Mohamed Afifi, Mohamed ElHelw

TL;DR

This work proposes a novel framework for real-time LiDAR odometry and mapping based on LOAM architecture for fast moving platforms that utilizes semantic information produced by a deep learning model to improve point-to-line and point-to-plane matching between LiDAR scans and build a semantic map of the environment, leading to more accurate motion estimation using LiDAR data.

Abstract

Perception is a key element for enabling intelligent autonomous navigation. Understanding the semantics of the surrounding environment and accurate vehicle pose estimation are essential capabilities for autonomous vehicles, including self-driving cars and mobile robots that perform complex tasks. Fast moving platforms like self-driving cars impose a hard challenge for localization and mapping algorithms. In this work, we propose a novel framework for real-time LiDAR odometry and mapping based on LOAM architecture for fast moving platforms. Our framework utilizes semantic information produced by a deep learning model to improve point-to-line and point-to-plane matching between LiDAR scans and build a semantic map of the environment, leading to more accurate motion estimation using LiDAR data. We observe that including semantic information in the matching process introduces a new type of outlier matches to the process, where matching occur between different objects of the same semantic class. To this end, we propose a novel algorithm that explicitly identifies and discards potential outliers in the matching process. In our experiments, we study the effect of improving the matching process on the robustness of LiDAR odometry against high speed motion. Our experimental evaluations on KITTI dataset demonstrate that utilizing semantic information and rejecting outliers significantly enhance the robustness of LiDAR odometry and mapping when there are large gaps between scan acquisition poses, which is typical for fast moving platforms.

Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection

TL;DR

This work proposes a novel framework for real-time LiDAR odometry and mapping based on LOAM architecture for fast moving platforms that utilizes semantic information produced by a deep learning model to improve point-to-line and point-to-plane matching between LiDAR scans and build a semantic map of the environment, leading to more accurate motion estimation using LiDAR data.

Abstract

Perception is a key element for enabling intelligent autonomous navigation. Understanding the semantics of the surrounding environment and accurate vehicle pose estimation are essential capabilities for autonomous vehicles, including self-driving cars and mobile robots that perform complex tasks. Fast moving platforms like self-driving cars impose a hard challenge for localization and mapping algorithms. In this work, we propose a novel framework for real-time LiDAR odometry and mapping based on LOAM architecture for fast moving platforms. Our framework utilizes semantic information produced by a deep learning model to improve point-to-line and point-to-plane matching between LiDAR scans and build a semantic map of the environment, leading to more accurate motion estimation using LiDAR data. We observe that including semantic information in the matching process introduces a new type of outlier matches to the process, where matching occur between different objects of the same semantic class. To this end, we propose a novel algorithm that explicitly identifies and discards potential outliers in the matching process. In our experiments, we study the effect of improving the matching process on the robustness of LiDAR odometry against high speed motion. Our experimental evaluations on KITTI dataset demonstrate that utilizing semantic information and rejecting outliers significantly enhance the robustness of LiDAR odometry and mapping when there are large gaps between scan acquisition poses, which is typical for fast moving platforms.
Paper Structure (21 sections, 3 equations, 12 figures, 1 table, 2 algorithms)

This paper contains 21 sections, 3 equations, 12 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed Framework
  4. Deep Semantic Segmentation
  5. Semantic LiDAR Odometry
  6. Notation
  7. Keypoints Extraction and Matching
  8. Outliers Rejection and Motion Estimation
  9. Semantic Localization and Mapping
  10. Scan to Map Registration
  11. Map Update
  12. Experiments and Results
  13. Dataset
  14. Hyper-parameters Tuning
  15. Experimental Evaluation
  16. ...and 6 more sections

Figures (12)

  • Figure S1: Block diagram of our proposed framework.
  • Figure S2: Visualizing matches between the first and fifth scans in KITTI sequence 0 with and without exploiting semantic information. Lines are drawn between keypoints in the current scan and the center of their selected neighbors in the previous scan. Points are colored according to their semantic class labels assigned by the deep semantic segmentation model.
  • Figure S3: Visualizing matches between the first and fifth scans in KITTI sequence 0 with and without outliers rejection. Lines are drawn between keypoints in the current scan and the center of their selected neighbors in the previous scan. Points are colored according to their semantic class labels assigned by the deep semantic segmentation model.
  • Figure S4: Heat map for tuning the parameters of the outliers rejection algorithm
  • Figure S5: Motion estimation between scan $0$ and scan $1$ in KITTI sequence $00$ without using semantics or outliers rejection.
  • ...and 7 more figures