Improved Semantic Stixels via Multimodal Sensor Fusion

TL;DR

This paper introduces a multimodal sensor fusion approach that combines LiDAR and camera data to produce a compact, accurate, and semantically rich 3D scene representation with reduced data size and computational cost.

Contribution

It extends the Stixel model to incorporate multimodal data, improving geometric and semantic accuracy with minimal additional computation.

Findings

Enhanced 3D scene representation accuracy

Reduced data size compared to single modality

Maintained low computational overhead

Abstract

This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-established Stixel model originally developed for stereo vision applications. We extend this Stixel concept to incorporate data from multiple sensor modalities. The resulting mid-level fusion scheme takes full advantage of the geometric accuracy of LiDAR measurements as well as the high resolution and semantic detail of RGB images. The obtained environment model provides a geometrically and semantically consistent representation of the 3D scene at a significantly reduced amount of data while minimizing information loss at the same time. Since the different sensor modalities are considered as input to a joint optimization problem, the solution is obtained with only minor computational overhead. We demonstrate the effectiveness of the proposed multimodal Stixel algorithm on a manually annotated ground truth dataset. Our results indicate that the proposed mid-level fusion of LiDAR and camera data improves both the geometric and semantic accuracy of the Stixel model significantly while reducing the computational overhead as well as the amount of generated data in comparison to using a single modality on its own.