Impact of LiDAR point cloud compression on 3D object detection evaluated on the KITTI dataset.
Saved in:
| Title: | Impact of LiDAR point cloud compression on 3D object detection evaluated on the KITTI dataset. |
|---|---|
| Authors: | Martins, Nuno A. B.1,2 (AUTHOR) nuno.martins@student.uc.pt, Cruz, Luís A. da Silva1,2 (AUTHOR), Lopes, Fernando2,3 (AUTHOR) |
| Source: | EURASIP Journal on Image & Video Processing. 6/17/2024, Vol. 2024 Issue 1, p1-28. 28p. |
| Subjects: | Object recognition (Computer vision), MPEG (Video coding standard), Point cloud, LIDAR, Optical radar, Computer vision, Huffman codes |
| Abstract: | The rapid growth on the amount of generated 3D data, particularly in the form of Light Detection And Ranging (LiDAR) point clouds (PCs), poses very significant challenges in terms of data storage, transmission, and processing. Point cloud (PC) representation of 3D visual information has shown to be a very flexible format with many applications ranging from multimedia immersive communication to machine vision tasks in the robotics and autonomous driving domains. In this paper, we investigate the performance of four reference 3D object detection techniques, when the input PCs are compressed with varying levels of degradation. Compression is performed using two MPEG standard coders based on 2D projections and octree decomposition, as well as two coding methods based on Deep Learning (DL). For the DL coding methods, we used a Joint Photographic Experts Group (JPEG) reference PC coder, that we adapted to accept LiDAR PCs in both Cartesian and cylindrical coordinate systems. The detection performance of the four reference 3D object detection methods was evaluated using both pre-trained models and models specifically trained using degraded PCs reconstructed from compressed representations. It is shown that LiDAR PCs can be compressed down to 6 bits per point with no significant degradation on the object detection precision. Furthermore, employing specifically trained detection models improves the detection capabilities even at compression rates as low as 2 bits per point. These results show that LiDAR PCs can be coded to enable efficient storage and transmission, without significant object detection performance loss. [ABSTRACT FROM AUTHOR] |
| Copyright of EURASIP Journal on Image & Video Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 177949724 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Impact of LiDAR point cloud compression on 3D object detection evaluated on the KITTI dataset. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Martins%2C+Nuno+A%2E+B%2E%22">Martins, Nuno A. B.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> nuno.martins@student.uc.pt</i><br /><searchLink fieldCode="AR" term="%22Cruz%2C+Luís+A%2E+da+Silva%22">Cruz, Luís A. da Silva</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lopes%2C+Fernando%22">Lopes, Fernando</searchLink><relatesTo>2,3</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22EURASIP+Journal+on+Image+%26+Video+Processing%22">EURASIP Journal on Image & Video Processing</searchLink>. 6/17/2024, Vol. 2024 Issue 1, p1-28. 28p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22MPEG+%28Video+coding+standard%29%22">MPEG (Video coding standard)</searchLink><br /><searchLink fieldCode="DE" term="%22Point+cloud%22">Point cloud</searchLink><br /><searchLink fieldCode="DE" term="%22LIDAR%22">LIDAR</searchLink><br /><searchLink fieldCode="DE" term="%22Optical+radar%22">Optical radar</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Huffman+codes%22">Huffman codes</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The rapid growth on the amount of generated 3D data, particularly in the form of Light Detection And Ranging (LiDAR) point clouds (PCs), poses very significant challenges in terms of data storage, transmission, and processing. Point cloud (PC) representation of 3D visual information has shown to be a very flexible format with many applications ranging from multimedia immersive communication to machine vision tasks in the robotics and autonomous driving domains. In this paper, we investigate the performance of four reference 3D object detection techniques, when the input PCs are compressed with varying levels of degradation. Compression is performed using two MPEG standard coders based on 2D projections and octree decomposition, as well as two coding methods based on Deep Learning (DL). For the DL coding methods, we used a Joint Photographic Experts Group (JPEG) reference PC coder, that we adapted to accept LiDAR PCs in both Cartesian and cylindrical coordinate systems. The detection performance of the four reference 3D object detection methods was evaluated using both pre-trained models and models specifically trained using degraded PCs reconstructed from compressed representations. It is shown that LiDAR PCs can be compressed down to 6 bits per point with no significant degradation on the object detection precision. Furthermore, employing specifically trained detection models improves the detection capabilities even at compression rates as low as 2 bits per point. These results show that LiDAR PCs can be coded to enable efficient storage and transmission, without significant object detection performance loss. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of EURASIP Journal on Image & Video Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=177949724 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1186/s13640-024-00633-4 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 28 StartPage: 1 Subjects: – SubjectFull: Object recognition (Computer vision) Type: general – SubjectFull: MPEG (Video coding standard) Type: general – SubjectFull: Point cloud Type: general – SubjectFull: LIDAR Type: general – SubjectFull: Optical radar Type: general – SubjectFull: Computer vision Type: general – SubjectFull: Huffman codes Type: general Titles: – TitleFull: Impact of LiDAR point cloud compression on 3D object detection evaluated on the KITTI dataset. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Martins, Nuno A. B. – PersonEntity: Name: NameFull: Cruz, Luís A. da Silva – PersonEntity: Name: NameFull: Lopes, Fernando IsPartOfRelationships: – BibEntity: Dates: – D: 17 M: 06 Text: 6/17/2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 16875176 Numbering: – Type: volume Value: 2024 – Type: issue Value: 1 Titles: – TitleFull: EURASIP Journal on Image & Video Processing Type: main |
| ResultId | 1 |
