Low-Cost Multimodal Fusion of 2D LiDAR and RGB Camera for Accurate Object-Level Perception

¹ Electronics and Communication Department, Indian Institute of Information Technology, Dharwad. India.
^2,3 Automation and Robotics Department, KLE Technological University, Hubli. India.

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it. (Vinod Kumar V. Meti)

Abstract

Sensor fusion between LiDAR and camera modalities has emerged as an effective approach for improving perception in autonomous robotic systems. However, most existing solutions rely on high-cost sensors and computationally intensive algorithms. This paper presents a low-cost LiDAR–camera fusion framework using a YDLiDAR TG30 2D LiDAR and a Logitech C270 RGB camera to achieve real-time object-level perception. The system is developed using ROS 2 Humble and integrates intrinsic and extrinsic calibration to accurately project LiDAR point clouds onto camera images. A custom fusion node performs coordinate transformation and depth-based visualization in real time. Experimental validation conducted in indoor environments demonstrates reliable projection accuracy within near-range distances, even under low-light conditions. The proposed framework offers an affordable, modular, and computationally efficient solution suitable for educational robotics, indoor navigation, and resource-constrained mobile platforms.