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

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/cm 2 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.

On the Integration of Enabling Wireless Technologies and Sensor Fusion for Next-Generation Connected and Autonomous Vehicles

“…This requires upsampling of the sparse and irregular data by depth completion. Here, a method based on LiDAR-camera fusion turns out to be extremely useful as it produces high-resolution depth images [177].…”

CFNet: LiDAR-Camera Registration Using Calibration Flow Network

“…Hand-eye calibration can provide initial extrinsic parameters, but it depends heavily on visual odometry and LiDAR odometry accuracy [39]. A series of other studies [40][41][42] combined LiDAR-camera calibration with sensor fusion localization and mapping to establish a joint optimization function. The odometry and extrinsic parameters are optimized simultaneously for stable mapping.…”

Humans as Path-Finders for Safe Navigation

“…However, recognising a specific person from a slice of a 2D point cloud is hopeless. For this reason, moving along a direction frequently taken in robotics [22], [23], [24], we apply a combination of cameras and LIDARS. The use of separate systems for depth estimation and classification improves the robustness of the tracking system when one of the sensors fails; e.g., if the leader falls outside the camera field of view, we can still use the LIDAR sensor for some time assuming a certain degree of reliability of the specific-person following.…”