Semantic Geometric Fusion Multi-object Tracking and Lidar Odometry in Dynamic Environment

TL;DR

This paper introduces a semantic geometric fusion approach for multi-object tracking and lidar odometry in dynamic environments, improving localization accuracy and robustness by integrating semantic detection and static map building.

Contribution

It proposes a novel multi-object dynamic lidar odometry system that combines semantic detection with geometric constraints for accurate localization and mapping in dynamic scenes.

Findings

Enhanced tracking accuracy in complex scenes

Improved localization robustness against dynamic objects

Better real-time performance on KITTI dataset

Abstract

The SLAM system based on static scene assumption will introduce huge estimation errors when moving objects appear in the field of view. This paper proposes a novel multi-object dynamic lidar odometry (MLO) based on semantic object detection technology to solve this problem. The MLO system can provide reliable localization of robot and semantic objects and build long-term static maps in complex dynamic scenes. For ego-motion estimation, we use the environment features that take semantic and geometric consistency constraints into account in the extraction process. The filtering features are robust to semantic movable and unknown dynamic objects. At the same time, a least square estimator using the semantic bounding box and object point cloud is proposed to achieve accurate and stable multi-object tracking between frames. In the mapping module, we further realize dynamic semantic object detection based on the absolute trajectory tracking list (ATTL). Then, static semantic objects and environmental features can be used to eliminate accumulated localization errors and build pure static maps. Experiments on public KITTI data sets show that the proposed system can achieve more accurate and robust tracking of the object and better real-time localization accuracy in complex scenes compared with existing technologies.