A Joint Optimization Approach of LiDAR-Camera Fusion for Accurate Dense 3D Reconstructions

TL;DR

This paper introduces a joint optimization method for LiDAR-camera data fusion that produces dense, accurate 3D reconstructions by jointly solving bundle adjustment and cloud registration, achieving high precision and improved calibration.

Contribution

It presents a novel offline fusion approach that jointly optimizes camera poses and sensor calibration, outperforming existing methods in accuracy and resolution.

Findings

Achieved an average accuracy of 2.7mm in 3D reconstruction

Produced a resolution of 70 points per square cm

Outperformed state-of-the-art calibration methods

Abstract

Fusing data from LiDAR and camera is conceptually attractive because of their complementary properties. For instance, camera images are higher resolution and have colors, while LiDAR data provide more accurate range measurements and have a wider Field Of View (FOV). However, the sensor fusion problem remains challenging since it is difficult to find reliable correlations between data of very different characteristics (geometry vs. texture, sparse vs. dense). This paper proposes an offline LiDAR-camera fusion method to build dense, accurate 3D models. Specifically, our method jointly solves a bundle adjustment (BA) problem and a cloud registration problem to compute camera poses and the sensor extrinsic calibration. In experiments, we show that our method can achieve an averaged accuracy of 2.7mm and resolution of 70 points per square cm by comparing to the ground truth data from a survey scanner. Furthermore, the extrinsic calibration result is discussed and shown to outperform the state-of-the-art method.