Probabilistic Multimodal Depth Estimation Based on Camera-LiDAR Sensor Fusion

TL;DR

This paper introduces a low-level sensor fusion method for depth estimation that combines raw camera and LiDAR data using a Conditional Random Field model, resulting in dense and accurate depth maps for autonomous perception.

Contribution

It presents a novel low-level fusion approach with a CRF model that effectively integrates raw sensor streams for improved depth estimation.

Findings

Outperforms state-of-the-art methods on KITTI benchmark

Produces dense and precise depth maps

Efficient optimization with Conjugate Gradient Squared

Abstract

Multi-modal depth estimation is one of the key challenges for endowing autonomous machines with robust robotic perception capabilities. There have been outstanding advances in the development of uni-modal depth estimation techniques based on either monocular cameras, because of their rich resolution, or LiDAR sensors, due to the precise geometric data they provide. However, each of these suffers from some inherent drawbacks, such as high sensitivity to changes in illumination conditions in the case of cameras and limited resolution for the LiDARs. Sensor fusion can be used to combine the merits and compensate for the downsides of these two kinds of sensors. Nevertheless, current fusion methods work at a high level. They process the sensor data streams independently and combine the high-level estimates obtained for each sensor. In this paper, we tackle the problem at a low level, fusing the raw sensor streams, thus obtaining depth estimates which are both dense and precise, and can be used as a unified multi-modal data source for higher level estimation problems. This work proposes a Conditional Random Field model with multiple geometry and appearance potentials. It seamlessly represents the problem of estimating dense depth maps from camera and LiDAR data. The model can be optimized efficiently using the Conjugate Gradient Squared algorithm. The proposed method was evaluated and compared with the state-of-the-art using the commonly used KITTI benchmark dataset.