Loading [a11y]/accessibility-menu.js
Simulation based data acquisition system for object detection in multi-LiDAR networks | IEEE Conference Publication | IEEE Xplore

Simulation based data acquisition system for object detection in multi-LiDAR networks


Abstract:

The use of light-detection-and-ranging (LiDAR) has been widely considered for object detection in smart monitoring and autonomous driving. Training deep learning models t...Show More

Abstract:

The use of light-detection-and-ranging (LiDAR) has been widely considered for object detection in smart monitoring and autonomous driving. Training deep learning models to perform object detection is costly and time-consuming due to the need for data labeling. Currently, using simulators to collect simulated data can address this issue. However, data from a single LiDAR suffers from blind spots and data sparsity, which makes the use and development of multi-LiDAR networks become increasingly important. This paper presents a system using a simulator to obtain simulated data. By implementing this system with multiple LiDARs within the simulator, we collect higher-quality and denser point-cloud data compared to using a single LiDAR. We validate this system with experimental evaluations and performance tests.
Date of Conference: 29 October 2024 - 01 November 2024
Date Added to IEEE Xplore: 28 November 2024
ISBN Information:

ISSN Information:

Conference Location: Kitakyushu, Japan

References

References is not available for this document.