AI-Based Point Cloud Upsampling for Autonomous Driving Systems
Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Centro Latinoamericano de Estudios en Informática
2025-05-01
|
| Series: | CLEI Electronic Journal |
| Online Access: | https://clei.org/cleiej/index.php/cleiej/article/view/811 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850138425969082368 |
|---|---|
| author | Nicolás Salomón Claudio A. Delrieux Damián A. Morero Leandro E. Borgnino |
| author_facet | Nicolás Salomón Claudio A. Delrieux Damián A. Morero Leandro E. Borgnino |
| author_sort | Nicolás Salomón |
| collection | DOAJ |
| description |
Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups.
This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented.
By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird's eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems.
|
| format | Article |
| id | doaj-art-762167a5007b4300937e758d95cee08a |
| institution | OA Journals |
| issn | 0717-5000 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Centro Latinoamericano de Estudios en Informática |
| record_format | Article |
| series | CLEI Electronic Journal |
| spelling | doaj-art-762167a5007b4300937e758d95cee08a2025-08-20T02:30:35ZengCentro Latinoamericano de Estudios en InformáticaCLEI Electronic Journal0717-50002025-05-0128310.19153/cleiej.28.3.3AI-Based Point Cloud Upsampling for Autonomous Driving SystemsNicolás Salomón0Claudio A. Delrieux1Damián A. Morero2Leandro E. Borgnino3Fundación Fulgor / UNSDepartamento de Ingeniería Eléctrica y Computadoras, Universidad Nacional del Sur Laboratorio de Comunicaciones Digitales, Universidad Nacional de CórdobaDepartamento de Electrónica, Universidad Nacional de Córdoba Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups. This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented. By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird's eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems. https://clei.org/cleiej/index.php/cleiej/article/view/811 |
| spellingShingle | Nicolás Salomón Claudio A. Delrieux Damián A. Morero Leandro E. Borgnino AI-Based Point Cloud Upsampling for Autonomous Driving Systems CLEI Electronic Journal |
| title | AI-Based Point Cloud Upsampling for Autonomous Driving Systems |
| title_full | AI-Based Point Cloud Upsampling for Autonomous Driving Systems |
| title_fullStr | AI-Based Point Cloud Upsampling for Autonomous Driving Systems |
| title_full_unstemmed | AI-Based Point Cloud Upsampling for Autonomous Driving Systems |
| title_short | AI-Based Point Cloud Upsampling for Autonomous Driving Systems |
| title_sort | ai based point cloud upsampling for autonomous driving systems |
| url | https://clei.org/cleiej/index.php/cleiej/article/view/811 |
| work_keys_str_mv | AT nicolassalomon aibasedpointcloudupsamplingforautonomousdrivingsystems AT claudioadelrieux aibasedpointcloudupsamplingforautonomousdrivingsystems AT damianamorero aibasedpointcloudupsamplingforautonomousdrivingsystems AT leandroeborgnino aibasedpointcloudupsamplingforautonomousdrivingsystems |